activity
20242026
collaborators

9 papers

cs.LG2026

KV-Skill: Forging Expertise in the Model's Native Language

Zhaowei Han, Xiang Zhang, Bing Han +3

Task knowledge is commonly stored either as text in the prompt or as an update to model weights. Text is modular but must be interpreted on every use, while weight adaptation makes…

cs.CV2026

UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation

Jie Liu, Zilyu Ye, Linxiao Yuan +8

Unified models capable of interleaved generation have emerged as a promising paradigm, with the community increasingly converging on autoregressive modeling for text and flow match…

cs.AI2026

ConsRoute:Consistency-Aware Adaptive Query Routing for Cloud-Edge-Device Large Language Models

Haoyu Qiao, Hao Zhang, Shanwen Mao +2

Large language models (LLMs) deliver impressive capabilities but incur substantial inference latency and cost, which hinders their deployment in latency-sensitive and resource-cons…

cs.CV2026

VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning

Qunzhong Wang, Jie Liu, Jiajun Liang +7

Recent advancements in multimodal reward models (RMs) have substantially improved post-training for visual generative models. However, current RMs face inherent limitations: (1) vi…

cs.CV2025

Flow-GRPO: Training Flow Matching Models via Online RL

Jie Liu, Gongye Liu, Jiajun Liang +6

We propose Flow-GRPO, the first method to integrate online policy gradient reinforcement learning (RL) into flow matching models. Our approach uses two key strategies: (1) an ODE-t…

cs.CV2025

Improving Video Generation with Human Feedback

Jie Liu, Gongye Liu, Jiajun Liang +14

Video generation has achieved significant advances through rectified flow techniques, but issues like unsmooth motion and misalignment between videos and prompts persist. In this w…