Learning to Reason with Compressed Context: Ground-Truth-Free Adaptation of OmniLLMs via Self-Distillation
Research
Research News
New papers, breakthroughs and academic AI research
Can We Anticipate Violence? Multimodal Learning from Pre-Incident Behavioral Cues
Research
Provable Benefit of SignGD: A Minimal Model Under Heavy-Tailed Class Imbalance
Research
RAISE: Diagnosing Acquisition Collapse in Costly LLM Signals
Research
Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models
Research
T-ARC: Topology-Aware Randomized Clustering via Distributionally Robust Stochastic Block Models
Research
Cryo-Bench: Benchmarking Foundation Models for Cryosphere Mapping
Research
From Answers to Policies: Efficient In-Context Learning System through Emulating Expert Investigation
Research
Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection
Research
When the Right Answer Is Missing: An Arithmetic-Dependent Rejection Bottleneck in Jev
Research
CIDER-FM: Foundation Models for Causal Inference from Diverse Experimental Regimes
Research
Less Data, Better Timing: Student-Curriculum Coupling for VLM On-Policy Distillation in Temporal Video Grounding
Research