Attention Manifolds: Steering or Blocking Language Models by Editing Learned B-Spline Surfaces
Research
Research News
New papers, breakthroughs and academic AI research
Meta-Multi-Agent Reinforcement Learning for Fast Adaptation of Interactive Policies with Applications to Autonomous Driving
Research
Legal Research Bench: Measuring End-to-End Reliability in Long-Horizon Legal Research Agents
Research
Sharp Oracle-Regret Tradeoffs for Projection-Free Online Convex Optimization
Research
Ontology-Grounded, Reasoner-Verified Benchmarks for Evaluating LLM Reasoning in Scientific AI
Research
MOVE: Multimodal Open-world Verification and Expansion for Graph Learning
Research
Stable and Counterfactually Robust Physical World Models from Imposed Structure and Learned Physics
Research
Robust Nash Alignment under Preference Uncertainty
Research
FORTE: Adaptive Scoring and Exact Keyframe Selection for Long-Video Question Answering
Research
Gestalt: Large Multimodal Interplay Model
Research
Incident-Arena: Getting agents to the last nine of reliability
Research
Backdoor Containment via Expert Quarantine and Shutdown in LLMs
Research