8 papers
Trajectory-Relative Hindsight Distillation for Agentic Reinforcement Learning
Haoyu Zheng, Yun Zhu, Qing Wang +1
Recent agentic reinforcement learning methods use hindsight to complement sparse outcome rewards. However, a completed rollout can yield many such signals, leaving their appropriat…
Unified Personalized Understanding, Generating and Editing
Yu Zhong, Tianwei Lin, Ruike Zhu +9
Unified large multimodal models (LMMs) have achieved remarkable progress in general-purpose multimodal understanding and generation. However, they still operate under a ``one-size-…
PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models
Haoyu Zheng, Yun Zhu, Yuqian Yuan +4
Strategic planning is critical for multi-step reasoning, yet compact Large Language Models (LLMs) often lack the capacity to formulate global strategies, leading to error propagati…
Fast Thinking for Large Language Models
Haoyu Zheng, Zhuonan Wang, Yuqian Yuan +7
Reasoning-oriented Large Language Models (LLMs) often rely on generating explicit tokens step by step, and their effectiveness typically hinges on large-scale supervised fine-tunin…
Retrieval Augmented Comic Image Generation
Yunhao Shui, Xuekuan Wang, Feng Qiu +8
We present RaCig, a novel system for generating comic-style image sequences with consistent characters and expressive gestures. RaCig addresses two key challenges: (1) maintaining…
SOYO: A Tuning-Free Approach for Video Style Morphing via Style-Adaptive Interpolation in Diffusion Models
Haoyu Zheng, Qifan Yu, Binghe Yu +5
Diffusion models have achieved remarkable progress in image and video stylization. However, most existing methods focus on single-style transfer, while video stylization involving…