SearchJev: A Fast and Calibrated System-1 Model for Search Agents Paper • 2610.05107 • Published 23 days ago • 41
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 29 days ago • 220
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published 28 days ago • 157
DecepEval: A Benchmark for Evaluating Deception in LLM Agents Paper • 2610.07967 • Published 21 days ago • 61