EQ-5D Classification Using Biomedical Entity-Enriched Pre-trained Language Models and Multiple Instance Learning

EQ-5D Classification Using Biomedical Entity-Enriched Pre-trained Language Models and Multiple Instance Learning

• Computer Science > Computation and Language [Submitted on 30 Jan 2026] Title:EQ-5D Classification Using Biomedical Entity-Enriched Pre-trained Language Models and Multiple Instan

Research & Labs · February 26, 2026 (updated February 26, 2026) · 2 min · 246 words
Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human Experts

Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human Experts

• Computer Science > Artificial Intelligence [Submitted on 25 Feb 2026] Title:Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human Experts View PDF HTML

Research & Labs · February 26, 2026 (updated February 26, 2026) · 2 min · 260 words
LLMTailor: A Layer-wise Tailoring Tool for Efficient Checkpointing of Large Language Models

LLMTailor: A Layer-wise Tailoring Tool for Efficient Checkpointing of Large Language Models

• Computer Science > Distributed, Parallel, and Cluster Computing [Submitted on 25 Feb 2026] Title:LLMTailor: A Layer-wise Tailoring Tool for Efficient Checkpointing of Large Langu

Measuring Pragmatic Influence in Large Language Model Instructions

Measuring Pragmatic Influence in Large Language Model Instructions

• Computer Science > Computation and Language [Submitted on 2 Feb 2026] Title:Measuring Pragmatic Influence in Large Language Model Instructions View PDF HTML (experimental)Abstrac

Research & Labs · February 26, 2026 (updated February 26, 2026) · 2 min · 266 words
MSADM: Large Language Model (LLM) Assisted End-to-End Network Health Management Based on Multi-Scale Semanticization

MSADM: Large Language Model (LLM) Assisted End-to-End Network Health Management Based on Multi-Scale Semanticization

• Computer Science > Networking and Internet Architecture [Submitted on 12 Jun 2024 (v1), last revised 25 Feb 2026 (this version, v3)] Title:MSADM: Large Language Model (LLM) Assis

Researchers challenge misleading language around plastic waste solutions

• Solutions to the plastic waste crisis are often pitched using words that can skew value judgments, new research argues. • The paper, authored by the Sustainable Materials Innovat

Science · February 25, 2026 (updated February 25, 2026) · 1 min · 162 words
A Survey on Federated Fine-tuning of Large Language Models

A Survey on Federated Fine-tuning of Large Language Models

• Computer Science > Machine Learning [Submitted on 15 Mar 2025 (v1), last revised 24 Feb 2026 (this version, v3)] Title:A Survey on Federated Fine-tuning of Large Language Models

Benchmarking Distilled Language Models: Performance and Efficiency in Resource-Constrained Settings

Benchmarking Distilled Language Models: Performance and Efficiency in Resource-Constrained Settings

• Computer Science > Computation and Language [Submitted on 28 Jan 2026] Title:Benchmarking Distilled Language Models: Performance and Efficiency in Resource-Constrained Settings V

Research & Labs · February 25, 2026 (updated February 25, 2026) · 2 min · 288 words
From Logs to Language: Learning Optimal Verbalization for LLM-Based Recommendation in Production

From Logs to Language: Learning Optimal Verbalization for LLM-Based Recommendation in Production

• Computer Science > Artificial Intelligence [Submitted on 24 Feb 2026] Title:From Logs to Language: Learning Optimal Verbalization for LLM-Based Recommendation in Production View

Research & Labs · February 25, 2026 (updated February 25, 2026) · 2 min · 254 words
Recursive Belief Vision Language Model

Recursive Belief Vision Language Model

• Computer Science > Artificial Intelligence [Submitted on 24 Feb 2026] Title:Recursive Belief Vision Language Model View PDF HTML (experimental)Abstract:Current vision-language-ac

Research & Labs · February 25, 2026 (updated February 25, 2026) · 1 min · 209 words
Intel Formally Ends Four Of Their Go Language Open-Source Projects

Intel Formally Ends Four Of Their Go Language Open-Source Projects

• Intel Formally Ends Four Of Their Go Language Open-Source Projects Following various Intel open-source projects recently being archived with Intel formally discontinuing their de

OS & Internals · February 24, 2026 (updated February 25, 2026) · 2 min · 383 words
A large-scale randomized study of large language model feedback in peer review

A large-scale randomized study of large language model feedback in peer review

• Abstract Peer review is stressed by rapidly rising submission volumes, leading to deteriorating review quality and increased author dissatisfaction. • Here, to address these issu

Research & Labs · February 24, 2026 (updated February 25, 2026) · 2 min · 351 words
Boeing demonstrates large language model for space-grade hardware

Boeing demonstrates large language model for space-grade hardware

• SAN FRANCISCO - Before uploading a large language model to space-grade hardware, Boeing Space Mission Systems engineers sought guidance from the hardware manufacturer. • ‘They to

Space & Aerospace · February 24, 2026 (updated February 25, 2026) · 2 min · 270 words
A flaw in using pretrained protein language models in protein-protein interaction inference models

A flaw in using pretrained protein language models in protein-protein interaction inference models

• Abstract With the growing pervasiveness of pretrained protein language models (pLMs), pLM-based methods are increasingly being put forward for the protein-protein interaction (PP

Research & Labs · February 24, 2026 (updated February 24, 2026) · 2 min · 279 words
Meta-designing quantum experiments with language models

Meta-designing quantum experiments with language models

• Abstract Artificial intelligence can solve complex scientific problems beyond human capabilities, but the resulting solutions offer little insight into the underlying physical pr

Research & Labs · February 24, 2026 (updated February 25, 2026) · 2 min · 367 words
Deploying Open Source Vision Language Models (VLM) on Jetson

Deploying Open Source Vision Language Models (VLM) on Jetson

• Deploying Open Source Vision Language Models (VLM) on Jetson Vision-Language Models (VLMs) mark a significant leap in AI by blending visual perception with semantic reasoning. •

How natural language processing and AI can help policymakers address global food insecurity

• NLP offers powerful opportunities to support the UN Sustainable Development Goals (SDGs)-including SDG2 (Zero Hunger). • In the wake of the COVID-19 pandemic, the Russia-Ukraine

Science · February 23, 2026 (updated February 24, 2026) · 1 min · 152 words
Music is not a universal language - but it can bring us together when words fail

Music is not a universal language - but it can bring us together when words fail

• Thank you for visiting nature.com. • You are using a browser version with limited support for CSS. • To obtain the best experience, we recommend you use a more up to date browser

Science · February 23, 2026 (updated February 23, 2026) · 1 min · 206 words
Neurosymbolic Language Reasoning as Satisfiability Modulo Theory

Neurosymbolic Language Reasoning as Satisfiability Modulo Theory

• Computer Science > Artificial Intelligence [Submitted on 20 Feb 2026] Title:Neurosymbolic Language Reasoning as Satisfiability Modulo Theory View PDF HTML (experimental)Abstract:

Research & Labs · February 23, 2026 (updated February 24, 2026) · 2 min · 254 words
Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge

Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge

• Computer Science > Artificial Intelligence [Submitted on 19 Feb 2026] Title:Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge

Research & Labs · February 23, 2026 (updated February 24, 2026) · 2 min · 298 words
The Token Games: Evaluating Language Model Reasoning with Puzzle Duels

The Token Games: Evaluating Language Model Reasoning with Puzzle Duels

• Computer Science > Artificial Intelligence [Submitted on 19 Feb 2026] Title:The Token Games: Evaluating Language Model Reasoning with Puzzle Duels View PDF HTML (experimental)Abs

Research & Labs · February 23, 2026 (updated February 24, 2026) · 2 min · 273 words

Language barriers slow down the international diffusion of knowledge, study finds

• Rapid technological and scientific advances have fueled a huge wave of innovation over the past decades. • The speed of global innovation is known to be dependent on the exchange

Science · February 22, 2026 (updated February 24, 2026) · 1 min · 139 words
What matters in building vision-language-action models for generalist robots

What matters in building vision-language-action models for generalist robots

• Abstract To utilize foundation vision-language models (VLMs) for robotic tasks and motion planning, the community has proposed different methods for injecting action components i

Research & Labs · February 22, 2026 (updated February 23, 2026) · 2 min · 289 words
When large language models are reliable for judging empathic communication

When large language models are reliable for judging empathic communication

• Abstract Large language models (LLMs) excel at generating empathic responses in text-based conversations. • But, how reliably do they judge the nuances of empathic communication?

Research & Labs · February 22, 2026 (updated February 23, 2026) · 2 min · 231 words
A flaw in using pretrained protein language models in protein-protein interaction inference models

A flaw in using pretrained protein language models in protein-protein interaction inference models

• Abstract With the growing pervasiveness of pretrained protein language models (pLMs), pLM-based methods are increasingly being put forward for the protein-protein interaction (PP

Research & Labs · February 22, 2026 (updated February 23, 2026) · 2 min · 280 words
Meta-designing quantum experiments with language models

Meta-designing quantum experiments with language models

• Abstract Artificial intelligence can solve complex scientific problems beyond human capabilities, but the resulting solutions offer little insight into the underlying physical pr

Research & Labs · February 22, 2026 (updated February 23, 2026) · 2 min · 268 words

Attributing and situating knowledge cannot be left to language models

• 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

Research & Labs · February 21, 2026 (updated February 24, 2026) · 1 min · 212 words
Web 'FIR Language Reference' out of sync with FIRLangRef.md?

Web 'FIR Language Reference' out of sync with FIRLangRef.md?

• Web ‘FIR Language Reference’ out of sync with FIRLangRef.md? • Hello, When I look atFIR Language Reference - The Flang Compiler, it seems different from FIRLangRef.md generated b

Language Internals · February 20, 2026 (updated February 24, 2026) · 1 min · 195 words
Privacy-Aware Split Inference with Speculative Decoding for Large Language Models over Wide-Area Networks

Privacy-Aware Split Inference with Speculative Decoding for Large Language Models over Wide-Area Networks

• Computer Science > Cryptography and Security [Submitted on 18 Feb 2026] Title:Privacy-Aware Split Inference with Speculative Decoding for Large Language Models over Wide-Area Net

Retrieval Augmented (Knowledge Graph), and Large Language Model-Driven Design Structure Matrix (DSM) Generation of Cyber-Physical Systems

Retrieval Augmented (Knowledge Graph), and Large Language Model-Driven Design Structure Matrix (DSM) Generation of Cyber-Physical Systems

• Computer Science > Artificial Intelligence [Submitted on 30 Jan 2026] Title:Retrieval Augmented (Knowledge Graph), and Large Language Model-Driven Design Structure Matrix (DSM) G

Research & Labs · February 20, 2026 (updated February 24, 2026) · 3 min · 438 words
[RFC] TensaLang: A tensor-first language for LLM inference, lowering through MLIR to CPU/CUDA

[RFC] TensaLang: A tensor-first language for LLM inference, lowering through MLIR to CPU/CUDA

• Hello, I’ve been working on a project called TensaLang and it’s finally at a point worth sharing. • It’s a small language + compiler + runtime for writing LLM forward passes dire

Language Internals · February 19, 2026 (updated February 24, 2026) · 2 min · 248 words
Adaptive Rank Allocation for Federated Parameter-Efficient Fine-Tuning of Language Models

Adaptive Rank Allocation for Federated Parameter-Efficient Fine-Tuning of Language Models

• Computer Science > Distributed, Parallel, and Cluster Computing [Submitted on 24 Jan 2025 (v1), last revised 18 Feb 2026 (this version, v4)] Title:Adaptive Rank Allocation for Fe

Agent Skill Framework: Perspectives on the Potential of Small Language Models in Industrial Environments

Agent Skill Framework: Perspectives on the Potential of Small Language Models in Industrial Environments

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Agent Skill Framework: Perspectives on the Potential of Small Language Models in Industrial Environmen

Research · February 19, 2026 (updated February 19, 2026) · 2 min · 272 words
Agent Skill Framework: Perspectives on the Potential of Small Language Models in Industrial Environments

Agent Skill Framework: Perspectives on the Potential of Small Language Models in Industrial Environments

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Agent Skill Framework: Perspectives on the Potential of Small Language Models in Industrial Environmen

Research & Labs · February 19, 2026 (updated February 24, 2026) · 2 min · 298 words
Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models

Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models

• Computer Science > Computation and Language [Submitted on 23 Jan 2026] Title:Do Personality Traits Interfere? • Geometric Limitations of Steering in Large Language Models View PD

Research & Labs · February 19, 2026 (updated February 24, 2026) · 2 min · 239 words
GPSBench: Do Large Language Models Understand GPS Coordinates?

GPSBench: Do Large Language Models Understand GPS Coordinates?

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:GPSBench: Do Large Language Models Understand GPS Coordinates? • View PDF HTML (experimental)Abstract:

Research · February 19, 2026 (updated February 19, 2026) · 2 min · 249 words
GPSBench: Do Large Language Models Understand GPS Coordinates?

GPSBench: Do Large Language Models Understand GPS Coordinates?

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:GPSBench: Do Large Language Models Understand GPS Coordinates? • View PDF HTML (experimental)Abstract:

Research & Labs · February 19, 2026 (updated February 24, 2026) · 2 min · 296 words
Improving Interactive In-Context Learning from Natural Language Feedback

Improving Interactive In-Context Learning from Natural Language Feedback

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Improving Interactive In-Context Learning from Natural Language Feedback View PDF HTML (experimental)A

Research · February 19, 2026 (updated February 19, 2026) · 2 min · 224 words
Improving Interactive In-Context Learning from Natural Language Feedback

Improving Interactive In-Context Learning from Natural Language Feedback

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Improving Interactive In-Context Learning from Natural Language Feedback View PDF HTML (experimental)A

Research & Labs · February 19, 2026 (updated February 24, 2026) · 2 min · 240 words
Language Model Representations for Efficient Few-Shot Tabular Classification

Language Model Representations for Efficient Few-Shot Tabular Classification

• Computer Science > Computation and Language [Submitted on 21 Jan 2026] Title:Language Model Representations for Efficient Few-Shot Tabular Classification View PDF HTML (experimen

Research & Labs · February 19, 2026 (updated February 24, 2026) · 2 min · 268 words
Large Language Models for Assisting American College Applications

Large Language Models for Assisting American College Applications

• Computer Science > Computation and Language [Submitted on 23 Jan 2026] Title:Large Language Models for Assisting American College Applications View PDFAbstract:American college a

Research & Labs · February 19, 2026 (updated February 24, 2026) · 2 min · 269 words
Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach

Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approa

Research & Labs · February 19, 2026 (updated February 24, 2026) · 2 min · 257 words
Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach

Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approa

Research · February 19, 2026 (updated February 19, 2026) · 2 min · 251 words

Bilingual courses in Europe: Proper use of language is professors' main concern

• A scientific review carried out by a team in the English and German Philology Department at the UCO explores the pedagogical dimension of bilingual university programs in Europe.

Science · February 19, 2026 (updated February 24, 2026) · 1 min · 185 words
A roadmap for evaluating moral competence in large language models

A roadmap for evaluating moral competence in large language models

• Abstract The question of whether large language models (LLMs) can exhibit moral capabilities is of growing interest and urgency, as these systems are deployed in sensitive roles

Science · February 19, 2026 (updated February 24, 2026) · 1 min · 212 words

Attributing and situating knowledge cannot be left to language models

• 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

Research · February 19, 2026 (updated February 19, 2026) · 2 min · 217 words

When large language models are reliable for judging empathic communication

• 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

Research · February 19, 2026 (updated February 19, 2026) · 1 min · 99 words

A flaw in using pretrained protein language models in protein-protein interaction inference models

• 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

Research · February 19, 2026 (updated February 19, 2026) · 1 min · 98 words
Tesla Can Still Sell Cars in California After 'Autopilot' Language Change

Tesla Can Still Sell Cars in California After 'Autopilot' Language Change

• Home Electric Vehicles Tesla Can Still Sell Cars in California After ‘Autopilot’ Language Change The EV manufacturer avoided a 30-day suspension after an ongoing dispute with the

Consumer Tech · February 18, 2026 (updated February 24, 2026) · 2 min · 250 words
EAA: Automating materials characterization with vision language model agents

EAA: Automating materials characterization with vision language model agents

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:EAA: Automating materials characterization with vision language model agents View PDF HTML (experiment

Research · February 18, 2026 (updated February 19, 2026) · 2 min · 230 words
EAA: Automating materials characterization with vision language model agents

EAA: Automating materials characterization with vision language model agents

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:EAA: Automating materials characterization with vision language model agents View PDF HTML (experiment

Research & Labs · February 18, 2026 (updated February 24, 2026) · 2 min · 230 words
Protecting Language Models Against Unauthorized Distillation through Trace Rewriting

Protecting Language Models Against Unauthorized Distillation through Trace Rewriting

• Computer Science > Artificial Intelligence [Submitted on 16 Feb 2026] Title:Protecting Language Models Against Unauthorized Distillation through Trace Rewriting View PDF HTML (ex

Research · February 18, 2026 (updated February 19, 2026) · 2 min · 235 words
Quantifying construct validity in large language model evaluations

Quantifying construct validity in large language model evaluations

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Quantifying construct validity in large language model evaluations View PDF HTML (experimental)Abstrac

Research · February 18, 2026 (updated February 19, 2026) · 2 min · 222 words
ResearchGym: Evaluating Language Model Agents on Real-World AI Research

ResearchGym: Evaluating Language Model Agents on Real-World AI Research

• Computer Science > Artificial Intelligence [Submitted on 16 Feb 2026] Title:ResearchGym: Evaluating Language Model Agents on Real-World AI Research View PDF HTML (experimental)Ab

Research & Labs · February 18, 2026 (updated February 24, 2026) · 1 min · 209 words
ResearchGym: Evaluating Language Model Agents on Real-World AI Research

ResearchGym: Evaluating Language Model Agents on Real-World AI Research

• Computer Science > Artificial Intelligence [Submitted on 16 Feb 2026] Title:ResearchGym: Evaluating Language Model Agents on Real-World AI Research View PDF HTML (experimental)Ab

Research · February 18, 2026 (updated February 19, 2026) · 1 min · 209 words

AI model learns yeast DNA 'language' to boost protein drug output

• Industrial yeasts are a powerhouse of protein production, used to manufacture vaccines, biopharmaceuticals, and other useful compounds. • In a new study, MIT chemical engineers h

Science · February 17, 2026 (updated February 24, 2026) · 1 min · 104 words
DPBench: Large Language Models Struggle with Simultaneous Coordination

DPBench: Large Language Models Struggle with Simultaneous Coordination

• Computer Science > Artificial Intelligence [Submitted on 2 Feb 2026] Title:DPBench: Large Language Models Struggle with Simultaneous Coordination View PDF HTML (experimental)Abst

Research · February 17, 2026 (updated February 19, 2026) · 2 min · 254 words
DPBench: Large Language Models Struggle with Simultaneous Coordination

DPBench: Large Language Models Struggle with Simultaneous Coordination

• Computer Science > Artificial Intelligence [Submitted on 2 Feb 2026] Title:DPBench: Large Language Models Struggle with Simultaneous Coordination View PDF HTML (experimental)Abst

Research & Labs · February 17, 2026 (updated February 24, 2026) · 2 min · 254 words
NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models

NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models

• Computer Science > Artificial Intelligence [Submitted on 29 Jan 2026] Title:NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models

Research · February 17, 2026 (updated February 19, 2026) · 2 min · 250 words
NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models

NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models

• Computer Science > Artificial Intelligence [Submitted on 29 Jan 2026] Title:NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models

Research & Labs · February 17, 2026 (updated February 24, 2026) · 2 min · 250 words