WASD: Wasserstein-based Knowledge Distillation for Large Language Models
Research
Research News
New papers, breakthroughs and academic AI research
Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security
Research
MedCORE: Criteria-Grounded Clinical Reasoning for Interpretable Medical Image Diagnosis
Research
HuC-VideoMAE: Human-Centric Video Masked Autoencoding from synthetic data
Research
Adaptive Model Inversion Attacks Generalize a Privacy-Robustness Tradeoff
Research
Does On-Policy Distillation for Safety Pose Backdoor Risks?
Research
Learning to Retrieve via Reinforcement Learning in Embedding Space
Research
Knee3DVLM: Dual-Sequence Full-Volume Vision-Language Modeling for Comprehensive Knee MRI Assessment
Research
Beyond Perturbation Magnitude: Direction-Dependent Responses in Multimodal Geometric Representations
Research
Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can Tell
Research
RSJEV: Discriminative Remote Sensing Scene Classification with Multimodal Large Language Models
Research
Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence
Research