CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance Paper • 2604.01113 • Published Apr 1 • 3
MINER: Mining Multimodal Internal Representation for Efficient Retrieval Paper • 2605.06460 • Published 23 days ago • 3
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents Paper • 2605.27068 • Published 4 days ago • 18
LLM Safety From Within: Detecting Harmful Content with Internal Representations Paper • 2604.18519 • Published Apr 20 • 26
Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models Paper • 2603.01571 • Published Mar 2 • 33
RubricBench: Aligning Model-Generated Rubrics with Human Standards Paper • 2603.01562 • Published Mar 2 • 63
Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection Paper • 2601.05403 • Published Jan 8 • 11
LOGO -- Long cOntext aliGnment via efficient preference Optimization Paper • 2410.18533 • Published Oct 24, 2024 • 43
Resonance RoPE: Improving Context Length Generalization of Large Language Models Paper • 2403.00071 • Published Feb 29, 2024 • 24