REALM: Regime-Switching, Explainable, and Activation-Induced Linear Models
Research
Research News
New papers, breakthroughs and academic AI research
LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
Research
TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception
Research
SMARtCARE: Privacy-Preserving Agentic AI Systems for Bounded-Autonomy Clinical Decision Support
Research
Witeness Overlap: Directional Provenance Inside Open-Weight Model Families
Research
EEGAgentBench: Benchmarking LLM Agents on Short- and Long-Horizon EEG Analysis
Research
Context-dependent agent evaluation with orthogonal equilibrium learning
Research
Verification of PETSc with CIVL using LLM-generated ACSL contracts and deterministic driver generation
Research
CP-Agent: A Harness-Engineered Agent for Crystal Plasticity Simulation Workflows
Research
DriveHierarchy: A Benchmark for Diagnosing VLM Driving Capabilities from Open-Loop Understanding to Closed-Loop Execution
Research
FIDAL: Diversity-Aware Federated Active Learning Under Real-World Distribution Shifts
Research
Language-Augmented Video Action Anticipation: Design Fundamentals, Benchmarks, and Open Challenges
Research