<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Research on Tenu Tech Brief</title>
    <link>https://cluster-site.onrender.com/categories/research/</link>
    <description>Recent content in Research on Tenu Tech Brief</description>
    <generator>Hugo -- 0.146.0</generator>
    <language>en-us</language>
    <lastBuildDate>Thu, 19 Feb 2026 07:42:00 +0000</lastBuildDate>
    <atom:link href="https://cluster-site.onrender.com/categories/research/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Agent Skill Framework: Perspectives on the Potential of Small Language Models in Industrial Environments</title>
      <link>https://cluster-site.onrender.com/posts/agent-skill-framework-perspectives-on-the-potential-of-small-language-models-in-industrial-environments/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/agent-skill-framework-perspectives-on-the-potential-of-small-language-models-in-industrial-environments/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 18 Feb 2026] Title:Agent Skill Framework: Perspectives on the Potential of Small Language Models in Industrial Environmen</description>
    </item>
    <item>
      <title>Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning</title>
      <link>https://cluster-site.onrender.com/posts/causally-guided-automated-feature-engineering-with-multi-agent-reinforcement-learning/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/causally-guided-automated-feature-engineering-with-multi-agent-reinforcement-learning/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 18 Feb 2026] Title:Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning View PDF HTML (e</description>
    </item>
    <item>
      <title>Creating a digital poet</title>
      <link>https://cluster-site.onrender.com/posts/creating-a-digital-poet/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/creating-a-digital-poet/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 18 Feb 2026] Title:Creating a digital poet View PDF HTML (experimental)Abstract:Can a machine write good poetry? • Any po</description>
    </item>
    <item>
      <title>EdgeNav-QE: QLoRA Quantization and Dynamic Early Exit for LAM-based Navigation on Edge Devices</title>
      <link>https://cluster-site.onrender.com/posts/edgenav-qe-qlora-quantization-and-dynamic-early-exit-for-lam-based-navigation-on-edge-devices/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/edgenav-qe-qlora-quantization-and-dynamic-early-exit-for-lam-based-navigation-on-edge-devices/</guid>
      <description>• Computer Science &amp;gt; Robotics [Submitted on 12 Jan 2026] Title:EdgeNav-QE: QLoRA Quantization and Dynamic Early Exit for LAM-based Navigation on Edge Devices View PDF HTML (experim</description>
    </item>
    <item>
      <title>EnterpriseGym Corecraft: Training Generalizable Agents on High-Fidelity RL Environments</title>
      <link>https://cluster-site.onrender.com/posts/enterprisegym-corecraft-training-generalizable-agents-on-high-fidelity-rl-environments/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/enterprisegym-corecraft-training-generalizable-agents-on-high-fidelity-rl-environments/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 18 Feb 2026] Title:EnterpriseGym Corecraft: Training Generalizable Agents on High-Fidelity RL Environments View PDF HTML</description>
    </item>
    <item>
      <title>Evidence-Grounded Subspecialty Reasoning: Evaluating a Curated Clinical Intelligence Layer on the 2025 Endocrinology Board-Style Examination</title>
      <link>https://cluster-site.onrender.com/posts/evidence-grounded-subspecialty-reasoning-evaluating-a-curated-clinical-intelligence-layer-on-the-2025-endocrinology-board-style-examination/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/evidence-grounded-subspecialty-reasoning-evaluating-a-curated-clinical-intelligence-layer-on-the-2025-endocrinology-board-style-examination/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:Evidence-Grounded Subspecialty Reasoning: Evaluating a Curated Clinical Intelligence Layer on the 2025</description>
    </item>
    <item>
      <title>Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs</title>
      <link>https://cluster-site.onrender.com/posts/framework-of-thoughts-a-foundation-framework-for-dynamic-and-optimized-reasoning-based-on-chains-trees-and-graphs/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/framework-of-thoughts-a-foundation-framework-for-dynamic-and-optimized-reasoning-based-on-chains-trees-and-graphs/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 18 Feb 2026] Title:Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Tre</description>
    </item>
    <item>
      <title>GPSBench: Do Large Language Models Understand GPS Coordinates?</title>
      <link>https://cluster-site.onrender.com/posts/gpsbench-do-large-language-models-understand-gps-coordinates/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/gpsbench-do-large-language-models-understand-gps-coordinates/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 18 Feb 2026] Title:GPSBench: Do Large Language Models Understand GPS Coordinates? • View PDF HTML (experimental)Abstract:</description>
    </item>
    <item>
      <title>How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment</title>
      <link>https://cluster-site.onrender.com/posts/how-uncertain-is-the-grade-a-benchmark-of-uncertainty-metrics-for-llm-based-automatic-assessment/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/how-uncertain-is-the-grade-a-benchmark-of-uncertainty-metrics-for-llm-based-automatic-assessment/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:How Uncertain Is the Grade? • A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment Vi</description>
    </item>
    <item>
      <title>Improving Interactive In-Context Learning from Natural Language Feedback</title>
      <link>https://cluster-site.onrender.com/posts/improving-interactive-in-context-learning-from-natural-language-feedback/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/improving-interactive-in-context-learning-from-natural-language-feedback/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:Improving Interactive In-Context Learning from Natural Language Feedback View PDF HTML (experimental)A</description>
    </item>
    <item>
      <title>Learning Personalized Agents from Human Feedback</title>
      <link>https://cluster-site.onrender.com/posts/learning-personalized-agents-from-human-feedback/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/learning-personalized-agents-from-human-feedback/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 18 Feb 2026] Title:Learning Personalized Agents from Human Feedback View PDF HTML (experimental)Abstract:Modern AI agents</description>
    </item>
    <item>
      <title>Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach</title>
      <link>https://cluster-site.onrender.com/posts/leveraging-large-language-models-for-causal-discovery-a-constraint-based-argumentation-driven-approach/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/leveraging-large-language-models-for-causal-discovery-a-constraint-based-argumentation-driven-approach/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 18 Feb 2026] Title:Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approa</description>
    </item>
    <item>
      <title>Multi-agent cooperation through in-context co-player inference</title>
      <link>https://cluster-site.onrender.com/posts/multi-agent-cooperation-through-in-context-co-player-inference/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/multi-agent-cooperation-through-in-context-co-player-inference/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 18 Feb 2026] Title:Multi-agent cooperation through in-context co-player inference View PDF HTML (experimental)Abstract:Ac</description>
    </item>
    <item>
      <title>Optimization Instability in Autonomous Agentic Workflows for Clinical Symptom Detection</title>
      <link>https://cluster-site.onrender.com/posts/optimization-instability-in-autonomous-agentic-workflows-for-clinical-symptom-detection/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/optimization-instability-in-autonomous-agentic-workflows-for-clinical-symptom-detection/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:Optimization Instability in Autonomous Agentic Workflows for Clinical Symptom Detection View PDF HTML</description>
    </item>
    <item>
      <title>Revolutionizing Long-Term Memory in AI: New Horizons with High-Capacity and High-Speed Storage</title>
      <link>https://cluster-site.onrender.com/posts/revolutionizing-long-term-memory-in-ai-new-horizons-with-high-capacity-and-high-speed-storage/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/revolutionizing-long-term-memory-in-ai-new-horizons-with-high-capacity-and-high-speed-storage/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 18 Feb 2026] Title:Revolutionizing Long-Term Memory in AI: New Horizons with High-Capacity and High-Speed Storage View PD</description>
    </item>
    <item>
      <title>Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents</title>
      <link>https://cluster-site.onrender.com/posts/toward-scalable-verifiable-reward-proxy-state-based-evaluation-for-multi-turn-tool-calling-llm-agents/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/toward-scalable-verifiable-reward-proxy-state-based-evaluation-for-multi-turn-tool-calling-llm-agents/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 18 Feb 2026] Title:Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents</description>
    </item>
    <item>
      <title>Towards a Science of AI Agent Reliability</title>
      <link>https://cluster-site.onrender.com/posts/towards-a-science-of-ai-agent-reliability/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/towards-a-science-of-ai-agent-reliability/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 18 Feb 2026] Title:Towards a Science of AI Agent Reliability View PDF HTML (experimental)Abstract:AI agents are increasin</description>
    </item>
    <item>
      <title>Towards Efficient Constraint Handling in Neural Solvers for Routing Problems</title>
      <link>https://cluster-site.onrender.com/posts/towards-efficient-constraint-handling-in-neural-solvers-for-routing-problems/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/towards-efficient-constraint-handling-in-neural-solvers-for-routing-problems/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:Towards Efficient Constraint Handling in Neural Solvers for Routing Problems View PDF HTML (experiment</description>
    </item>
    <item>
      <title>Verifiable Semantics for Agent-to-Agent Communication</title>
      <link>https://cluster-site.onrender.com/posts/verifiable-semantics-for-agent-to-agent-communication/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/verifiable-semantics-for-agent-to-agent-communication/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 18 Feb 2026] Title:Verifiable Semantics for Agent-to-Agent Communication View PDF HTML (experimental)Abstract:Multiagent</description>
    </item>
    <item>
      <title>What Persona Are We Missing? Identifying Unknown Relevant Personas for Faithful User Simulation</title>
      <link>https://cluster-site.onrender.com/posts/what-persona-are-we-missing-identifying-unknown-relevant-personas-for-faithful-user-simulation/</link>
      <pubDate>Thu, 19 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/what-persona-are-we-missing-identifying-unknown-relevant-personas-for-faithful-user-simulation/</guid>
      <description>• Computer Science &amp;gt; Human-Computer Interaction [Submitted on 3 Jan 2026] Title:What Persona Are We Missing? • Identifying Unknown Relevant Personas for Faithful User Simulation Vi</description>
    </item>
    <item>
      <title>Identifying spatial single-cell-level interactions with graph transformer</title>
      <link>https://cluster-site.onrender.com/posts/identifying-spatial-single-cell-level-interactions-with-graph-transformer/</link>
      <pubDate>Thu, 19 Feb 2026 01:48:38 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/identifying-spatial-single-cell-level-interactions-with-graph-transformer/</guid>
      <description>• Subjects Cellular signalling networks Multicellular systems Identifying cell-cell interactions from imaging-based spatial transcriptomics suffers from limited gene panels. • A ne</description>
    </item>
    <item>
      <title>Attributing and situating knowledge cannot be left to language models</title>
      <link>https://cluster-site.onrender.com/posts/attributing-and-situating-knowledge-cannot-be-left-to-language-models/</link>
      <pubDate>Thu, 19 Feb 2026 01:48:35 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/attributing-and-situating-knowledge-cannot-be-left-to-language-models/</guid>
      <description>• Subjects Authorship Ethics Meticulous citation is a marker of well-researched, serious scholarship. • Citations do a lot more than attributing credit; they situate claims within</description>
    </item>
    <item>
      <title>A federated graph learning method to realize multi-party collaboration for molecular discovery</title>
      <link>https://cluster-site.onrender.com/posts/a-federated-graph-learning-method-to-realize-multi-party-collaboration-for-molecular-discovery/</link>
      <pubDate>Thu, 19 Feb 2026 01:48:32 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/a-federated-graph-learning-method-to-realize-multi-party-collaboration-for-molecular-discovery/</guid>
      <description>• Abstract Optimizing molecular resource utilization for molecular discovery requires collaborative efforts across research institutions and organizations to accelerate progress. •</description>
    </item>
    <item>
      <title>What matters in building vision-language-action models for generalist robots</title>
      <link>https://cluster-site.onrender.com/posts/what-matters-in-building-vision-language-action-models-for-generalist-robots/</link>
      <pubDate>Thu, 19 Feb 2026 01:48:22 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/what-matters-in-building-vision-language-action-models-for-generalist-robots/</guid>
      <description>• Nature Machine Intelligence, Published online: 11 February 2026; doi:10.1038/s42256-025-01168-7 Vision-language-action models recently emerged as a tool for robotics. • Here Li a</description>
    </item>
    <item>
      <title>When large language models are reliable for judging empathic communication</title>
      <link>https://cluster-site.onrender.com/posts/when-large-language-models-are-reliable-for-judging-empathic-communication/</link>
      <pubDate>Thu, 19 Feb 2026 01:41:19 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/when-large-language-models-are-reliable-for-judging-empathic-communication/</guid>
      <description>• Nature Machine Intelligence, Published online: 11 February 2026; doi:10.1038/s42256-025-01169-6 Kumar et al. • show that large language models (LLMs) nearly match expert reliabil</description>
    </item>
    <item>
      <title>Reusability Report: Evaluating the performance of a meta-learning foundation model on predicting the antibacterial activity of natural products</title>
      <link>https://cluster-site.onrender.com/posts/reusability-report-evaluating-the-performance-of-a-meta-learning-foundation-model-on-predicting-the-antibacterial-activity-of-natural-products/</link>
      <pubDate>Thu, 19 Feb 2026 01:18:25 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/reusability-report-evaluating-the-performance-of-a-meta-learning-foundation-model-on-predicting-the-antibacterial-activity-of-natural-products/</guid>
      <description>• Nature Machine Intelligence, Published online: 12 February 2026; doi:10.1038/s42256-026-01187-y This Reusability Report tests the ability of a foundation model, ActFound, to pred</description>
    </item>
    <item>
      <title>A flaw in using pretrained protein language models in protein-protein interaction inference models</title>
      <link>https://cluster-site.onrender.com/posts/a-flaw-in-using-pretrained-protein-language-models-in-protein-protein-interaction-inference-models/</link>
      <pubDate>Thu, 19 Feb 2026 01:12:12 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/a-flaw-in-using-pretrained-protein-language-models-in-protein-protein-interaction-inference-models/</guid>
      <description>• Nature Machine Intelligence, Published online: 13 February 2026; doi:10.1038/s42256-025-01176-7 The usage of pretrained protein language models (pLMs) is rapidly growing. • Howev</description>
    </item>
    <item>
      <title>Parallel hierarchical encoding of linguistic representations in the human auditory cortex and recurrent automatic speech recognition systems</title>
      <link>https://cluster-site.onrender.com/posts/parallel-hierarchical-encoding-of-linguistic-representations-in-the-human-auditory-cortex-and-recurrent-automatic-speech-recognition-systems/</link>
      <pubDate>Thu, 19 Feb 2026 01:05:49 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/parallel-hierarchical-encoding-of-linguistic-representations-in-the-human-auditory-cortex-and-recurrent-automatic-speech-recognition-systems/</guid>
      <description>• Nature Machine Intelligence, Published online: 17 February 2026; doi:10.1038/s42256-026-01185-0 Keshishian, Mischler et al. • report that a recurrent automatic speech recognition</description>
    </item>
    <item>
      <title>Grasshopper-inspired wing design improves gliding performance</title>
      <link>https://cluster-site.onrender.com/posts/grasshopper-inspired-wing-design-improves-gliding-performance/</link>
      <pubDate>Wed, 18 Feb 2026 19:31:04 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/grasshopper-inspired-wing-design-improves-gliding-performance/</guid>
      <description>• Science Robotics, Volume 11, Issue 111, February 2026.</description>
    </item>
    <item>
      <title>Low-voltage and high-output dielectric elastomer actuators for untethered soft machines working at 200 volts</title>
      <link>https://cluster-site.onrender.com/posts/low-voltage-and-high-output-dielectric-elastomer-actuators-for-untethered-soft-machines-working-at-200-volts/</link>
      <pubDate>Wed, 18 Feb 2026 19:31:04 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/low-voltage-and-high-output-dielectric-elastomer-actuators-for-untethered-soft-machines-working-at-200-volts/</guid>
      <description>• Science Robotics, Volume 11, Issue 111, February 2026.</description>
    </item>
    <item>
      <title>The codevelopment of soft robotics and assistive technology</title>
      <link>https://cluster-site.onrender.com/posts/the-codevelopment-of-soft-robotics-and-assistive-technology/</link>
      <pubDate>Wed, 18 Feb 2026 19:31:04 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/the-codevelopment-of-soft-robotics-and-assistive-technology/</guid>
      <description>• Science Robotics, Volume 11, Issue 111, February 2026.</description>
    </item>
    <item>
      <title>Five Berkeley Lab Scientists Receive DOE Early Career Research Awards</title>
      <link>https://cluster-site.onrender.com/posts/five-berkeley-lab-scientists-receive-doe-early-career-research-awards/</link>
      <pubDate>Wed, 18 Feb 2026 16:00:34 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/five-berkeley-lab-scientists-receive-doe-early-career-research-awards/</guid>
      <description>• Five Berkeley Lab Scientists Receive DOE Early Career Research Awards Article Emerging Ideas Five scientists from Lawrence Berkeley National Laboratory (Berkeley Lab) have receiv</description>
    </item>
    <item>
      <title>AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents</title>
      <link>https://cluster-site.onrender.com/posts/agriworlda-world-tools-protocol-framework-for-verifiable-agricultural-reasoning-with-code-executing-llm-agents/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/agriworlda-world-tools-protocol-framework-for-verifiable-agricultural-reasoning-with-code-executing-llm-agents/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing L</description>
    </item>
    <item>
      <title>Attention-gated U-Net model for semantic segmentation of brain tumors and feature extraction for survival prognosis</title>
      <link>https://cluster-site.onrender.com/posts/attention-gated-u-net-model-for-semantic-segmentation-of-brain-tumors-and-feature-extraction-for-survival-prognosis/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/attention-gated-u-net-model-for-semantic-segmentation-of-brain-tumors-and-feature-extraction-for-survival-prognosis/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 14 Feb 2026] Title:Attention-gated U-Net model for semantic segmentation of brain tumors and feature extraction for survi</description>
    </item>
    <item>
      <title>Common Belief Revisited</title>
      <link>https://cluster-site.onrender.com/posts/common-belief-revisited/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/common-belief-revisited/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:Common Belief Revisited View PDF HTML (experimental)Abstract:Contrary to common belief, common belief</description>
    </item>
    <item>
      <title>da Costa and Tarski meet Goguen and Carnap: a novel approach for ontological heterogeneity based on consequence systems</title>
      <link>https://cluster-site.onrender.com/posts/da-costa-and-tarski-meet-goguen-and-carnap-a-novel-approach-for-ontological-heterogeneity-based-on-consequence-systems/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/da-costa-and-tarski-meet-goguen-and-carnap-a-novel-approach-for-ontological-heterogeneity-based-on-consequence-systems/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 16 Feb 2026] Title:da Costa and Tarski meet Goguen and Carnap: a novel approach for ontological heterogeneity based on co</description>
    </item>
    <item>
      <title>EAA: Automating materials characterization with vision language model agents</title>
      <link>https://cluster-site.onrender.com/posts/eaa-automating-materials-characterization-with-vision-language-model-agents/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/eaa-automating-materials-characterization-with-vision-language-model-agents/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:EAA: Automating materials characterization with vision language model agents View PDF HTML (experiment</description>
    </item>
    <item>
      <title>Enhancing Diversity and Feasibility: Joint Population Synthesis from Multi-source Data Using Generative Models</title>
      <link>https://cluster-site.onrender.com/posts/enhancing-diversity-and-feasibility-joint-population-synthesis-from-multi-source-data-using-generative-models/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/enhancing-diversity-and-feasibility-joint-population-synthesis-from-multi-source-data-using-generative-models/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:Enhancing Diversity and Feasibility: Joint Population Synthesis from Multi-source Data Using Generativ</description>
    </item>
    <item>
      <title>GenAI-LA: Generative AI and Learning Analytics Workshop (LAK 2026), April 27--May 1, 2026, Bergen, Norway</title>
      <link>https://cluster-site.onrender.com/posts/genai-la-generative-ai-and-learning-analytics-workshop-lak-2026-april-27--may-1-2026-bergen-norway/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/genai-la-generative-ai-and-learning-analytics-workshop-lak-2026-april-27--may-1-2026-bergen-norway/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:GenAI-LA: Generative AI and Learning Analytics Workshop (LAK 2026), April 27&amp;ndash;May 1, 2026, Bergen, Nor</description>
    </item>
    <item>
      <title>Improving LLM Reliability through Hybrid Abstention and Adaptive Detection</title>
      <link>https://cluster-site.onrender.com/posts/improving-llm-reliability-through-hybrid-abstention-and-adaptive-detection/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/improving-llm-reliability-through-hybrid-abstention-and-adaptive-detection/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:Improving LLM Reliability through Hybrid Abstention and Adaptive Detection View PDF HTML (experimental</description>
    </item>
    <item>
      <title>Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs</title>
      <link>https://cluster-site.onrender.com/posts/mind-the-dh-gap-a-contrast-in-risky-choices-between-reasoning-and-conversational-llms/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/mind-the-dh-gap-a-contrast-in-risky-choices-between-reasoning-and-conversational-llms/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 16 Feb 2026] Title:Mind the (DH) Gap! • A Contrast in Risky Choices Between Reasoning and Conversational LLMs View PDF HT</description>
    </item>
    <item>
      <title>Panini: Continual Learning in Token Space via Structured Memory</title>
      <link>https://cluster-site.onrender.com/posts/panini-continual-learning-in-token-space-via-structured-memory/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/panini-continual-learning-in-token-space-via-structured-memory/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 16 Feb 2026] Title:Panini: Continual Learning in Token Space via Structured Memory View PDF HTML (experimental)Abstract:L</description>
    </item>
    <item>
      <title>Predicting Invoice Dilution in Supply Chain Finance with Leakage Free Two Stage XGBoost, KAN (Kolmogorov Arnold Networks), and Ensemble Models</title>
      <link>https://cluster-site.onrender.com/posts/predicting-invoice-dilution-in-supply-chain-finance-with-leakage-free-two-stage-xgboost-kan-kolmogorov-arnold-networks-and-ensemble-models/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/predicting-invoice-dilution-in-supply-chain-finance-with-leakage-free-two-stage-xgboost-kan-kolmogorov-arnold-networks-and-ensemble-models/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 16 Feb 2026] Title:Predicting Invoice Dilution in Supply Chain Finance with Leakage Free Two Stage XGBoost, KAN (Kolmogor</description>
    </item>
    <item>
      <title>Protecting Language Models Against Unauthorized Distillation through Trace Rewriting</title>
      <link>https://cluster-site.onrender.com/posts/protecting-language-models-against-unauthorized-distillation-through-trace-rewriting/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/protecting-language-models-against-unauthorized-distillation-through-trace-rewriting/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 16 Feb 2026] Title:Protecting Language Models Against Unauthorized Distillation through Trace Rewriting View PDF HTML (ex</description>
    </item>
    <item>
      <title>Quantifying construct validity in large language model evaluations</title>
      <link>https://cluster-site.onrender.com/posts/quantifying-construct-validity-in-large-language-model-evaluations/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/quantifying-construct-validity-in-large-language-model-evaluations/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:Quantifying construct validity in large language model evaluations View PDF HTML (experimental)Abstrac</description>
    </item>
    <item>
      <title>ResearchGym: Evaluating Language Model Agents on Real-World AI Research</title>
      <link>https://cluster-site.onrender.com/posts/researchgym-evaluating-language-model-agents-on-real-world-ai-research/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/researchgym-evaluating-language-model-agents-on-real-world-ai-research/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 16 Feb 2026] Title:ResearchGym: Evaluating Language Model Agents on Real-World AI Research View PDF HTML (experimental)Ab</description>
    </item>
    <item>
      <title>Secure and Energy-Efficient Wireless Agentic AI Networks</title>
      <link>https://cluster-site.onrender.com/posts/secure-and-energy-efficient-wireless-agentic-ai-networks/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/secure-and-energy-efficient-wireless-agentic-ai-networks/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 16 Feb 2026] Title:Secure and Energy-Efficient Wireless Agentic AI Networks View PDF HTML (experimental)Abstract:In this</description>
    </item>
    <item>
      <title>When Remembering and Planning are Worth it: Navigating under Change</title>
      <link>https://cluster-site.onrender.com/posts/when-remembering-and-planning-are-worth-it-navigating-under-change/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/when-remembering-and-planning-are-worth-it-navigating-under-change/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:When Remembering and Planning are Worth it: Navigating under Change View PDF HTML (experimental)Abstra</description>
    </item>
    <item>
      <title>World-Model-Augmented Web Agents with Action Correction</title>
      <link>https://cluster-site.onrender.com/posts/world-model-augmented-web-agents-with-action-correction/</link>
      <pubDate>Wed, 18 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/world-model-augmented-web-agents-with-action-correction/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 17 Feb 2026] Title:World-Model-Augmented Web Agents with Action Correction View PDF HTML (experimental)Abstract:Web agent</description>
    </item>
    <item>
      <title>Bioinspired adaptive pupil reflex based on liquid-metal shape-shifters for machine vision</title>
      <link>https://cluster-site.onrender.com/posts/bioinspired-adaptive-pupil-reflex-based-on-liquid-metal-shape-shifters-for-machine-vision/</link>
      <pubDate>Wed, 18 Feb 2026 00:35:08 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/bioinspired-adaptive-pupil-reflex-based-on-liquid-metal-shape-shifters-for-machine-vision/</guid>
      <description>• Science Robotics, Volume 11, Issue 111, February 2026.</description>
    </item>
    <item>
      <title>Scalable robot collective resilience by sharing resources</title>
      <link>https://cluster-site.onrender.com/posts/scalable-robot-collective-resilience-by-sharing-resources/</link>
      <pubDate>Wed, 18 Feb 2026 00:35:08 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/scalable-robot-collective-resilience-by-sharing-resources/</guid>
      <description>• Science Robotics, Volume 11, Issue 111, February 2026.</description>
    </item>
    <item>
      <title>Science on the Double: How an AI-Powered &#39;Digital Twin&#39; Accelerates Chemistry and Materials Discoveries</title>
      <link>https://cluster-site.onrender.com/posts/science-on-the-double-how-an-ai-powered-digital-twin-accelerates-chemistry-and-materials-discoveries/</link>
      <pubDate>Tue, 17 Feb 2026 16:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/science-on-the-double-how-an-ai-powered-digital-twin-accelerates-chemistry-and-materials-discoveries/</guid>
      <description>• The post Science on the Double: How an AI-Powered &amp;lsquo;Digital Twin&amp;rsquo; Accelerates Chemistry and Materials Discoveries appeared first on Berkeley Lab News Center . • The post What Is a</description>
    </item>
    <item>
      <title>What Is a Digital Twin?</title>
      <link>https://cluster-site.onrender.com/posts/what-is-a-digital-twin/</link>
      <pubDate>Tue, 17 Feb 2026 16:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/what-is-a-digital-twin/</guid>
      <description>• What Is a Digital Twin? • Video AI Digital twins are transforming how scientists study and improve complex systems - reducing the time between discovery and delivery. • Learn wha</description>
    </item>
    <item>
      <title>Authorization of prognostic AI medical devices</title>
      <link>https://cluster-site.onrender.com/posts/authorization-of-prognostic-ai-medical-devices/</link>
      <pubDate>Tue, 17 Feb 2026 08:36:25 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/authorization-of-prognostic-ai-medical-devices/</guid>
      <description>• Subjects Health policy Medical humanities Less than 2% of artificial intelligence devices authorized by the US Food and Drug Agency are prognostic, with prediction horizons rangi</description>
    </item>
    <item>
      <title>A Geometric Taxonomy of Hallucinations in LLMs</title>
      <link>https://cluster-site.onrender.com/posts/a-geometric-taxonomy-of-hallucinations-in-llms/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/a-geometric-taxonomy-of-hallucinations-in-llms/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 26 Jan 2026] Title:A Geometric Taxonomy of Hallucinations in LLMs View PDF HTML (experimental)Abstract:The term &amp;lsquo;hallucin</description>
    </item>
    <item>
      <title>Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique</title>
      <link>https://cluster-site.onrender.com/posts/agentic-ai-for-commercial-insurance-underwriting-with-adversarial-self-critique/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/agentic-ai-for-commercial-insurance-underwriting-with-adversarial-self-critique/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 21 Jan 2026] Title:Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique View PDF HTML (experim</description>
    </item>
    <item>
      <title>AST-PAC: AST-guided Membership Inference for Code</title>
      <link>https://cluster-site.onrender.com/posts/ast-pac-ast-guided-membership-inference-for-code/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/ast-pac-ast-guided-membership-inference-for-code/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 30 Jan 2026] Title:AST-PAC: AST-guided Membership Inference for Code View PDF HTML (experimental)Abstract:Code Large Lang</description>
    </item>
    <item>
      <title>BotzoneBench: Scalable LLM Evaluation via Graded AI Anchors</title>
      <link>https://cluster-site.onrender.com/posts/botzonebench-scalable-llm-evaluation-via-graded-ai-anchors/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/botzonebench-scalable-llm-evaluation-via-graded-ai-anchors/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 22 Jan 2026] Title:BotzoneBench: Scalable LLM Evaluation via Graded AI Anchors View PDF HTML (experimental)Abstract:Large</description>
    </item>
    <item>
      <title>DPBench: Large Language Models Struggle with Simultaneous Coordination</title>
      <link>https://cluster-site.onrender.com/posts/dpbench-large-language-models-struggle-with-simultaneous-coordination/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/dpbench-large-language-models-struggle-with-simultaneous-coordination/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 2 Feb 2026] Title:DPBench: Large Language Models Struggle with Simultaneous Coordination View PDF HTML (experimental)Abst</description>
    </item>
    <item>
      <title>General learned delegation by clones</title>
      <link>https://cluster-site.onrender.com/posts/general-learned-delegation-by-clones/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/general-learned-delegation-by-clones/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 3 Feb 2026] Title:General learned delegation by clones View PDF HTML (experimental)Abstract:Frontier language models impr</description>
    </item>
    <item>
      <title>Human-Centered Explainable AI for Security Enhancement: A Deep Intrusion Detection Framework</title>
      <link>https://cluster-site.onrender.com/posts/human-centered-explainable-ai-for-security-enhancement-a-deep-intrusion-detection-framework/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/human-centered-explainable-ai-for-security-enhancement-a-deep-intrusion-detection-framework/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 4 Feb 2026] Title:Human-Centered Explainable AI for Security Enhancement: A Deep Intrusion Detection Framework View PDF H</description>
    </item>
    <item>
      <title>Intelligence as Trajectory-Dominant Pareto Optimization</title>
      <link>https://cluster-site.onrender.com/posts/intelligence-as-trajectory-dominant-pareto-optimization/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/intelligence-as-trajectory-dominant-pareto-optimization/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 28 Jan 2026] Title:Intelligence as Trajectory-Dominant Pareto Optimization View PDF HTML (experimental)Abstract:Despite r</description>
    </item>
    <item>
      <title>Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains</title>
      <link>https://cluster-site.onrender.com/posts/lang2act-fine-grained-visual-reasoning-through-self-emergent-linguistic-toolchains/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/lang2act-fine-grained-visual-reasoning-through-self-emergent-linguistic-toolchains/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 29 Jan 2026] Title:Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains View PDF HTML (exp</description>
    </item>
    <item>
      <title>MAPLE: A Sub-Agent Architecture for Memory, Learning, and Personalization in Agentic AI Systems</title>
      <link>https://cluster-site.onrender.com/posts/maple-a-sub-agent-architecture-for-memory-learning-and-personalization-in-agentic-ai-systems/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/maple-a-sub-agent-architecture-for-memory-learning-and-personalization-in-agentic-ai-systems/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 3 Feb 2026] Title:MAPLE: A Sub-Agent Architecture for Memory, Learning, and Personalization in Agentic AI Systems View PD</description>
    </item>
    <item>
      <title>NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models</title>
      <link>https://cluster-site.onrender.com/posts/nl2logic-ast-guided-translation-of-natural-language-into-first-order-logic-with-large-language-models/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/nl2logic-ast-guided-translation-of-natural-language-into-first-order-logic-with-large-language-models/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 29 Jan 2026] Title:NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models</description>
    </item>
    <item>
      <title>PlotChain: Deterministic Checkpointed Evaluation of Multimodal LLMs on Engineering Plot Reading</title>
      <link>https://cluster-site.onrender.com/posts/plotchain-deterministic-checkpointed-evaluation-of-multimodal-llms-on-engineering-plot-reading/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/plotchain-deterministic-checkpointed-evaluation-of-multimodal-llms-on-engineering-plot-reading/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 29 Jan 2026] Title:PlotChain: Deterministic Checkpointed Evaluation of Multimodal LLMs on Engineering Plot Reading View P</description>
    </item>
    <item>
      <title>ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs</title>
      <link>https://cluster-site.onrender.com/posts/promoral-bench-evaluating-prompting-strategies-for-moral-reasoning-and-safety-in-llms/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/promoral-bench-evaluating-prompting-strategies-for-moral-reasoning-and-safety-in-llms/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 5 Feb 2026] Title:ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs View PDF HTML (e</description>
    </item>
    <item>
      <title>Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning</title>
      <link>https://cluster-site.onrender.com/posts/scaling-the-scaling-logic-agentic-meta-synthesis-of-logic-reasoning/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/scaling-the-scaling-logic-agentic-meta-synthesis-of-logic-reasoning/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 23 Jan 2026] Title:Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning View PDF HTML (experimental)Abstr</description>
    </item>
    <item>
      <title>Stay in Character, Stay Safe: Dual-Cycle Adversarial Self-Evolution for Safety Role-Playing Agents</title>
      <link>https://cluster-site.onrender.com/posts/stay-in-character-stay-safe-dual-cycle-adversarial-self-evolution-for-safety-role-playing-agents/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/stay-in-character-stay-safe-dual-cycle-adversarial-self-evolution-for-safety-role-playing-agents/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 29 Jan 2026] Title:Stay in Character, Stay Safe: Dual-Cycle Adversarial Self-Evolution for Safety Role-Playing Agents Vie</description>
    </item>
    <item>
      <title>TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks</title>
      <link>https://cluster-site.onrender.com/posts/temporalbench-a-benchmark-for-evaluating-llm-based-agents-on-contextual-and-event-informed-time-series-tasks/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/temporalbench-a-benchmark-for-evaluating-llm-based-agents-on-contextual-and-event-informed-time-series-tasks/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 5 Feb 2026] Title:TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series</description>
    </item>
    <item>
      <title>Variation is the Key: A Variation-Based Framework for LLM-Generated Text Detection</title>
      <link>https://cluster-site.onrender.com/posts/variation-is-the-key-a-variation-based-framework-for-llm-generated-text-detection/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/variation-is-the-key-a-variation-based-framework-for-llm-generated-text-detection/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 27 Jan 2026] Title:Variation is the Key: A Variation-Based Framework for LLM-Generated Text Detection View PDF HTML (expe</description>
    </item>
    <item>
      <title>X-Blocks: Linguistic Building Blocks of Natural Language Explanations for Automated Vehicles</title>
      <link>https://cluster-site.onrender.com/posts/x-blocks-linguistic-building-blocks-of-natural-language-explanations-for-automated-vehicles/</link>
      <pubDate>Tue, 17 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/x-blocks-linguistic-building-blocks-of-natural-language-explanations-for-automated-vehicles/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 2 Feb 2026] Title:X-Blocks: Linguistic Building Blocks of Natural Language Explanations for Automated Vehicles View PDF H</description>
    </item>
    <item>
      <title>Basics2Breakthroughs: Studying the Hydraulic Mechanism in Jumping Spiders</title>
      <link>https://cluster-site.onrender.com/posts/basics2breakthroughs-studying-the-hydraulic-mechanism-in-jumping-spiders/</link>
      <pubDate>Fri, 13 Feb 2026 19:20:31 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/basics2breakthroughs-studying-the-hydraulic-mechanism-in-jumping-spiders/</guid>
      <description>• The post Basics2Breakthroughs: Studying the Hydraulic Mechanism in Jumping Spiders appeared first on Berkeley Lab News Center .</description>
    </item>
    <item>
      <title>Crunching Big Data Into 3D Images Accelerates Discovery</title>
      <link>https://cluster-site.onrender.com/posts/crunching-big-data-into-3d-images-accelerates-discovery/</link>
      <pubDate>Thu, 12 Feb 2026 16:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/crunching-big-data-into-3d-images-accelerates-discovery/</guid>
      <description>• The post Crunching Big Data Into 3D Images Accelerates Discovery appeared first on Berkeley Lab News Center .</description>
    </item>
    <item>
      <title>A &#39;Robot Pizza Chef&#39; Serving Up Better Quantum Computers</title>
      <link>https://cluster-site.onrender.com/posts/a-robot-pizza-chef-serving-up-better-quantum-computers/</link>
      <pubDate>Wed, 11 Feb 2026 20:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/a-robot-pizza-chef-serving-up-better-quantum-computers/</guid>
      <description>• The post A &amp;lsquo;Robot Pizza Chef&amp;rsquo; Serving Up Better Quantum Computers appeared first on Berkeley Lab News Center .</description>
    </item>
    <item>
      <title>New AI Sensor &#39;Sniffs&#39; Out Spectral Targets</title>
      <link>https://cluster-site.onrender.com/posts/new-ai-sensor-sniffs-out-spectral-targets/</link>
      <pubDate>Wed, 11 Feb 2026 16:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/new-ai-sensor-sniffs-out-spectral-targets/</guid>
      <description>• The post New AI Sensor &amp;lsquo;Sniffs&amp;rsquo; Out Spectral Targets appeared first on Berkeley Lab News Center .</description>
    </item>
    <item>
      <title>Berkeley Lab Leads Effort to Build AI Assistant for Energy Materials Discovery</title>
      <link>https://cluster-site.onrender.com/posts/berkeley-lab-leads-effort-to-build-ai-assistant-for-energy-materials-discovery/</link>
      <pubDate>Tue, 03 Feb 2026 16:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/berkeley-lab-leads-effort-to-build-ai-assistant-for-energy-materials-discovery/</guid>
      <description>• The post Berkeley Lab Leads Effort to Build AI Assistant for Energy Materials Discovery appeared first on Berkeley Lab News Center .</description>
    </item>
    <item>
      <title>AI for Smarter, More Powerful, More Efficient Particle Accelerators</title>
      <link>https://cluster-site.onrender.com/posts/ai-for-smarter-more-powerful-more-efficient-particle-accelerators/</link>
      <pubDate>Mon, 02 Feb 2026 16:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/ai-for-smarter-more-powerful-more-efficient-particle-accelerators/</guid>
      <description>• AI for Smarter, More Powerful, More Efficient Particle Accelerators Article AI Particle accelerators are powerful tools that have revolutionized research in physics, chemistry, m</description>
    </item>
    <item>
      <title>Foundational AI Models to Accelerate Biological Discovery</title>
      <link>https://cluster-site.onrender.com/posts/foundational-ai-models-to-accelerate-biological-discovery/</link>
      <pubDate>Mon, 02 Feb 2026 16:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/foundational-ai-models-to-accelerate-biological-discovery/</guid>
      <description>• Foundational AI Models to Accelerate Biological Discovery Article AI Researchers from four national laboratories and industry are collaborating to unleash the full potential of b</description>
    </item>
    <item>
      <title>How a Machine Learning Pipeline Could Accelerate Innovation</title>
      <link>https://cluster-site.onrender.com/posts/how-a-machine-learning-pipeline-could-accelerate-innovation/</link>
      <pubDate>Mon, 02 Feb 2026 16:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/how-a-machine-learning-pipeline-could-accelerate-innovation/</guid>
      <description>• How a Machine Learning Pipeline Could Accelerate Innovation Article AI Lawrence Berkeley National Laboratory (Berkeley Lab) is working to transform petabytes of imaging data from</description>
    </item>
    <item>
      <title>AI, Automation, and Biosensors Speed the Path to Synthetic Jet Fuel</title>
      <link>https://cluster-site.onrender.com/posts/ai-automation-and-biosensors-speed-the-path-to-synthetic-jet-fuel/</link>
      <pubDate>Thu, 29 Jan 2026 16:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/ai-automation-and-biosensors-speed-the-path-to-synthetic-jet-fuel/</guid>
      <description>• Key Takeaways - Automation and AI can systematically pinpoint optimal designs among hundreds of thousands of possibilities, increasing isoprenol titers five-fold in weeks. • - Bi</description>
    </item>
    <item>
      <title>EcoFABs Could Help Fuel AI in Agriculture</title>
      <link>https://cluster-site.onrender.com/posts/ecofabs-could-help-fuel-ai-in-agriculture/</link>
      <pubDate>Thu, 22 Jan 2026 16:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/ecofabs-could-help-fuel-ai-in-agriculture/</guid>
      <description>• EcoFABs Could Help Fuel AI in Agriculture Article AI Key Takeaways EcoFABs are takeout-box-sized plastic chambers that give scientists a reproducible way to study plants and thei</description>
    </item>
    <item>
      <title>Expert Interview: Soren Prestemon on Magnet Technology</title>
      <link>https://cluster-site.onrender.com/posts/expert-interview-soren-prestemon-on-magnet-technology/</link>
      <pubDate>Thu, 15 Jan 2026 16:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/expert-interview-soren-prestemon-on-magnet-technology/</guid>
      <description>• Magnets are essential across scientific applications, particularly in particle physics and in light sources. • At Lawrence Berkeley National Laboratory (Berkeley Lab), Soren Pres</description>
    </item>
    <item>
      <title>Leading the Field in Magnets</title>
      <link>https://cluster-site.onrender.com/posts/leading-the-field-in-magnets/</link>
      <pubDate>Thu, 15 Jan 2026 16:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/leading-the-field-in-magnets/</guid>
      <description>• In 1929, Ernest Orlando Lawrence invented the cyclotron: a compact, efficient particle accelerator that used magnets. • Two years later, he founded what would become the Departme</description>
    </item>
    <item>
      <title>RL without TD learning</title>
      <link>https://cluster-site.onrender.com/posts/rl-without-td-learning/</link>
      <pubDate>Sat, 01 Nov 2025 09:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/rl-without-td-learning/</guid>
      <description>• In this post, Iâll introduce a reinforcement learning (RL) algorithm based on an âalternativeâ paradigm: divide and conquer. • Unlike traditional methods, this algorithm is not b</description>
    </item>
    <item>
      <title>What exactly does word2vec learn?</title>
      <link>https://cluster-site.onrender.com/posts/what-exactly-does-word2vec-learn/</link>
      <pubDate>Mon, 01 Sep 2025 09:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/what-exactly-does-word2vec-learn/</guid>
      <description>• What exactly does word2vec learn, and how? • Answering this question amounts to understanding representation learning in a minimal yet interesting language modeling task. • Despi</description>
    </item>
    <item>
      <title>Whole-Body Conditioned Egocentric Video Prediction</title>
      <link>https://cluster-site.onrender.com/posts/whole-body-conditioned-egocentric-video-prediction/</link>
      <pubDate>Tue, 01 Jul 2025 09:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/whole-body-conditioned-egocentric-video-prediction/</guid>
      <description>• Predicting Ego-centric Video from human Actions (PEVA). • Given past video frames and an action specifying a desired change in 3D pose, PEVA predicts the next video frame. • Our</description>
    </item>
    <item>
      <title>Defending against Prompt Injection with Structured Queries (StruQ) and Preference Optimization (SecAlign)</title>
      <link>https://cluster-site.onrender.com/posts/defending-against-prompt-injection-with-structured-queries-struq-and-preference-optimization-secalign/</link>
      <pubDate>Fri, 11 Apr 2025 10:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/defending-against-prompt-injection-with-structured-queries-struq-and-preference-optimization-secalign/</guid>
      <description>• Recent advances in Large Language Models (LLMs) enable exciting LLM-integrated applications. • However, as LLMs have improved, so have the attacks against them.Prompt injection a</description>
    </item>
    <item>
      <title>Repurposing Protein Folding Models for Generation with Latent Diffusion</title>
      <link>https://cluster-site.onrender.com/posts/repurposing-protein-folding-models-for-generation-with-latent-diffusion/</link>
      <pubDate>Tue, 08 Apr 2025 10:30:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/repurposing-protein-folding-models-for-generation-with-latent-diffusion/</guid>
      <description>• PLAID is a multimodal generative model that simultaneously generates protein 1D sequence and 3D structure, by learning the latent space of protein folding models. • The awarding</description>
    </item>
    <item>
      <title>Scaling Up Reinforcement Learning for Traffic Smoothing: A 100-AV Highway Deployment</title>
      <link>https://cluster-site.onrender.com/posts/scaling-up-reinforcement-learning-for-traffic-smoothing-a-100-av-highway-deployment/</link>
      <pubDate>Tue, 25 Mar 2025 09:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/scaling-up-reinforcement-learning-for-traffic-smoothing-a-100-av-highway-deployment/</guid>
      <description>• We deployed 100 reinforcement learning (RL)-controlled cars into rush-hour highway traffic to smooth congestion and reduce fuel consumption for everyone. • Our goal is to tackle</description>
    </item>
    <item>
      <title>Virtual Personas for Language Models via an Anthology of Backstories</title>
      <link>https://cluster-site.onrender.com/posts/virtual-personas-for-language-models-via-an-anthology-of-backstories/</link>
      <pubDate>Tue, 12 Nov 2024 09:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/virtual-personas-for-language-models-via-an-anthology-of-backstories/</guid>
      <description>• We introduce Anthology, a method for conditioning LLMs to representative, consistent, and diverse virtual personas by generating and utilizing naturalistic backstories with rich</description>
    </item>
    <item>
      <title>Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination</title>
      <link>https://cluster-site.onrender.com/posts/linguistic-bias-in-chatgpt-language-models-reinforce-dialect-discrimination/</link>
      <pubDate>Fri, 20 Sep 2024 09:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/linguistic-bias-in-chatgpt-language-models-reinforce-dialect-discrimination/</guid>
      <description>• Sample language model responses to different varieties of English and native speaker reactions. • ChatGPT does amazingly well at communicating with people in English. • Only 15%o</description>
    </item>
    <item>
      <title>How to Evaluate Jailbreak Methods: A Case Study with the StrongREJECT Benchmark</title>
      <link>https://cluster-site.onrender.com/posts/how-to-evaluate-jailbreak-methods-a-case-study-with-the-strongreject-benchmark/</link>
      <pubDate>Wed, 28 Aug 2024 15:30:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/how-to-evaluate-jailbreak-methods-a-case-study-with-the-strongreject-benchmark/</guid>
      <description>• When we began studying jailbreak evaluations, we found a fascinating paper claiming that you could jailbreak frontier LLMs simply by translating forbidden prompts into obscure la</description>
    </item>
    <item>
      <title>Are We Ready for Multi-Image Reasoning? Launching VHs: The Visual Haystacks Benchmark!</title>
      <link>https://cluster-site.onrender.com/posts/are-we-ready-for-multi-image-reasoning-launching-vhs-the-visual-haystacks-benchmark/</link>
      <pubDate>Sat, 20 Jul 2024 09:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/are-we-ready-for-multi-image-reasoning-launching-vhs-the-visual-haystacks-benchmark/</guid>
      <description>• Humans excel at processing vast arrays of visual information, a skill that is crucial for achieving artificial general intelligence (AGI). • Over the decades, AI researchers have</description>
    </item>
  </channel>
</rss>
