Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue Paper • 2609.04250 • Published 27 days ago • 44
Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision Paper • 2608.16812 • Published Aug 17 • 50
KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination Evaluation Paper • 2608.03782 • Published Aug 4 • 1
KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination Evaluation Paper • 2608.03782 • Published Aug 4 • 1
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning Paper • 2607.14777 • Published Jul 16 • 104
DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space Paper • 2607.25675 • Published Jul 28 • 69
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search Paper • 2607.24280 • Published Jul 27 • 85
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search Paper • 2607.24280 • Published Jul 27 • 85
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search Paper • 2607.24280 • Published Jul 27 • 85
Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction Paper • 2607.20911 • Published Jul 23 • 25