3 papers
cs.CV2026
On-Policy Self-Distillation in Diffusion Models
Wei Zhou, Xiongwei Zhu, Lingdong Kong +14
Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction…
cs.CV2026
OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs
Xianyun Sun, Chaoyou Fu, Zhengye Zhang +6
Recent omni-modal large language models (Omni-LLMs) show great potential as real-time video assistants, which continuously perceive environments and guide users to achieve specific…
cs.IR2026
Mosaic: A Fleet of User Embedding Specialists for Recommendation at Meta
John Zhiyuan Zheng, Xian Sun, Xiangyang Mou +6
User representation is one of the highest-leverage modeling problems in industrial recommendation systems: a single advancement in how users are encoded can propagate across retrie…