LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets Paper • 2610.09872 • Published 19 days ago • 62
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Paper • 2609.39600 • Published 26 days ago • 58
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published 27 days ago • 156
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 28 days ago • 220
DecepEval: A Benchmark for Evaluating Deception in LLM Agents Paper • 2610.07967 • Published 20 days ago • 61