DecepEval: A Benchmark for Evaluating Deception in LLM Agents Paper • 2610.07967 • Published 21 days ago • 61
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization Paper • 2605.21318 • Published 22 days ago • 9
Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model Paper • 2609.18323 • Published Sep 16 • 96
Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions Paper • 2608.29109 • Published Aug 29 • 17
ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding Paper • 2609.07941 • Published Sep 7 • 18
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM Paper • 2609.04098 • Published Sep 3 • 80