MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 21 days ago • 397
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published 20 days ago • 135
DecepEval: A Benchmark for Evaluating Deception in LLM Agents Paper • 2610.07967 • Published 13 days ago • 86