7 papers
RECAP: Feedback-Driven Streaming Semantic User Profiles for Short-Video Recommendation
Ziyi Zhao, Xiaoyou Zhou, Xiao Lv +13
Language-based user profiles convert long behavioral histories into explicit semantic representations for recommendation. However, most profile generators are optimized in an open…
Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback
Jianglin Lu, Yuanwei Wu, Ziyi Zhao +4
Complex image restoration aims to recover high-quality images from inputs affected by multiple degradations such as blur, noise, rain, and compression artifacts. Recent restoration…
From Path Signatures to Sequential Modeling: Incremental Signature Contributions for Offline RL
Ziyi Zhao, Qingchuan Li, Yuxuan Xu
Path signatures embed trajectories into tensor algebra and constitute a universal, non-parametric representation of paths; however, in the standard form, they collapse temporal str…
Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs
Ziyi Zhao, Chongming Gao, Yang Zhang +5
Personalization in Large Language Models (LLMs) often relies on user-specific soft prompts. However, these prompts become obsolete when the foundation model is upgraded, necessitat…
FrontierCS: Evolving Challenges for Evolving Intelligence
Qiuyang Mang, Wenhao Chai, Zhifei Li +48
We introduce FrontierCS, a benchmark of 156 open-ended problems across diverse areas of computer science, designed and reviewed by experts, including CS PhDs and top-tier competiti…
EvalTalker: Learning to Evaluate Real-Portrait-Driven Multi-Subject Talking Humans
Yingjie Zhou, Xilei Zhu, Siyu Ren +11
Speech-driven Talking Human (TH) generation, commonly known as "Talker," currently faces limitations in multi-subject driving capabilities. Extending this paradigm to "Multi-Talker…