PairAudit: Guiding Human Review with Graph Tokens under Distribution Shift
Research
Research News
New papers, breakthroughs and academic AI research
Physics-Aligned Electronic Ground-State Learning Improves Generalization
Research
Self-Indexing Attention for Compression-Compatible Sparse Long-Context LLM Inference
Research
Shared Gaussianization: What Gaussian Regularizers Certify About Contrastive Learning, and What They Miss
Research
Detecting Adversarial Images through Response Profiles of Vision-Language Models
Research
MORCA: Offline-to-Online Reinforcement Learning for Adaptive Cache Reuse in Video Diffusion Acceleration
Research
Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice
Research
Faster-WAM: Do World Action Models Need Deep Action Modules?
Research
COMPASS: Finding Where Reasoning Lives in Language Models
Research
RSIGym: A Flexible Environment for Recursive Self-Improvement
Research
Revisiting Explainable AI through Model-Independent Concept Dictionaries
Research
SGF+: Decoupling Gradient Flows for Autoregressive Video Generation
Research