• Addresses bidirectional model learnability gap in federated LLM-SLM reasoning collaboration. • Introduces LaDa framework with learnability-aware data filter for high-reward sampl
• Diffusion-based framework refines system prompts via masked denoising in an iterative manner. • Conditions on interaction traces: user queries, model responses, and optional feed
• FedTPG introduces dynamic text-driven prompt generation for vision-language models in federated settings. • Replication evaluated on six datasets, achieving 74.58% seen, 76.00% u
• Code evolution uses LLMs to mutate code, yet lacks baseline comparisons. • Authors test two simple baselines across math bounds, agentic scaffolds, and ML contests. • Baselines m
• 16 critical, high, and medium‑severity vulnerabilities found in Foxit and Apryse PDF platforms. • Flaws include DOM XSS, SSRF, path traversal, and OS command injection. • Attacke