The Functional Structure of Post-Compression Recovery in Low-Rank LLMs
Research
Research News
New papers, breakthroughs and academic AI research
More Claims, Less Evidence: Bounded Verification of AI-Generated Digital Knowledge Artifacts
Research
LifeLong Digital Twin: A Unified Modeling Paradigm and Agent Harness for Event-Driven Lifelong Health State Trajectories
Research
From Abusive Language Classification to Sequence Labeling Identification
Research
DialectSentEval 2026: Arabic Dialect Sentiment Analysis and Swapping Shared Task
Research
Agentic schema-guided extraction of materials process knowledge from scientific literature
Research
Breaking Bureaucracy: Evaluating open-source LLMs for legal document review
Research
Ontology Concept Overlap as a Training Signal: Knowledge-Grounded Reinforcement Learning for Clinical Question Answering
Research
Do Speech Representations Preserve Regional Accent Across Read and Spontaneous Speech?
Research
The Assistance Dilemma: Learning to Teach via Multi-Turn Reinforcement Learning
Research
Behavior-Preserving KV Cache Compression
Research
Your Temporal Link Predictor Is Blind to Who Is Active: A Missing Factor That Transfers Across Models
Research