LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers Paper • 2608.06867 • Published 11 days ago • 103
What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems Paper • 2608.07565 • Published 15 days ago • 28
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent Paper • 2608.03979 • Published 14 days ago • 50
SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation Paper • 2608.03092 • Published 14 days ago • 10
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System Paper • 2607.27380 • Published 20 days ago • 71
CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition Paper • 2607.25294 • Published 21 days ago • 49