1 citations · 4 across the 29 of their papers we have counts for
36 papers
OmniEdit-Bench: A Comprehensive Benchmark for Instruction-based Video Editing
Chenxuan Miao, Yutong Feng, Yi Lu +6
Instruction-based video editing (IVE) is an emerging field with broad applications, yet evaluating editing models remains challenging. Existing benchmarks suffer from two major lim…
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
Senqiao Yang, Chengyao Wang, Yuxin Chen +13
Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models, yet robot trajectories are harder to scale than web-scale image-text data because embodie…
PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
Kaixin Ding, Xi Chen, Minghong Cai +9
Video world models simulate future states conditioned on current observations and user actions. Recent systems have demonstrated impressive video consistency and action controllabi…
SURF: Signature-Retained Fast Video Generation
Kaixin Ding, Xi Chen, Sihui Ji +4
The demand for high-resolution video generation is growing rapidly. However, the generation resolution is severely constrained by slow inference speeds. For instance, Wan2.1 requir…
CoDance: An Unbind-Rebind Paradigm for Robust Multi-Subject Animation
Shuai Tan, Biao Gong, Ke Ma +5
Character image animation is gaining significant importance across various domains, driven by the demand for robust and flexible multi-subject rendering. While existing methods exc…
GDRO: Group-level Reward Post-training Suitable for Diffusion Models
Yiyang Wang, Xi Chen, Xiaogang Xu +2
Recent advancements adopt online reinforcement learning (RL) from LLMs to text-to-image rectified flow diffusion models for reward alignment. The use of group-level rewards success…
Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection
Kaixin Ding, Yang Zhou, Xi Chen +5
Recent advances in Text-to-Image (T2I) generative models, such as Imagen, Stable Diffusion, and FLUX, have led to remarkable improvements in visual quality. However, their performa…
MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
Sihui Ji, Xi Chen, Shuai Yang +3
The core challenge for streaming video generation is maintaining the content consistency in long context, which poses high requirement for the memory design. Most existing solution…
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
Ruihang Chu, Yefei He, Zhekai Chen +10
We present Wan-Move, a simple and scalable framework that brings motion control to video generative models. Existing motion-controllable methods typically suffer from coarse contro…
Seg-VAR: Image Segmentation with Visual Autoregressive Modeling
Rongkun Zheng, Lu Qi, Xi Chen +3
While visual autoregressive modeling (VAR) strategies have shed light on image generation with the autoregressive models, their potential for segmentation, a task that requires pre…
PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning
Sihui Ji, Xi Chen, Xin Tao +2
Video generation models nowadays are capable of generating visually realistic videos, but often fail to adhere to physical laws, limiting their ability to generate physically plaus…
Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents
Mingkang Zhu, Xi Chen, Bei Yu +2
Large language model (LLM) agents increasingly rely on external tools such as search engines to solve complex, multi-step problems, and reinforcement learning (RL) has become a key…
From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models
Mingkang Zhu, Xi Chen, Bei Yu +2
Large reasoning models (LRMs) generate intermediate reasoning traces before producing final answers, yielding strong gains on multi-step and mathematical tasks. Yet aligning LRMs w…
DiffCamera: Arbitrary Refocusing on Images
Yiyang Wang, Xi Chen, Xiaogang Xu +2
The depth-of-field (DoF) effect, which introduces aesthetically pleasing blur, enhances photographic quality but is fixed and difficult to modify once the image has been created. T…
ROSE: Remove Objects with Side Effects in Videos
Chenxuan Miao, Yutong Feng, Jianshu Zeng +7
Video object removal has achieved advanced performance due to the recent success of video generative models. However, when addressing the side effects of objects, e.g., their shado…
Animate-X++: Universal Character Image Animation with Dynamic Backgrounds
Shuai Tan, Biao Gong, Zhuoxin Liu +4
Character image animation, which generates high-quality videos from a reference image and target pose sequence, has seen significant progress in recent years. However, most existin…
DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs
Jiahe Zhao, Rongkun Zheng, Yi Wang +2
In video Multimodal Large Language Models (video MLLMs), the visual encapsulation process plays a pivotal role in converting video contents into representative tokens for LLM input…
MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
Xi Chen, Mingkang Zhu, Shaoteng Liu +5
This work explores enabling Chain-of-Thought (CoT) reasoning to link visual cues across multiple images. A straightforward solution is to adapt rule-based reinforcement learning fo…
FocalClick-XL: Towards Unified and High-quality Interactive Segmentation
Xi Chen, Hengshuang Zhao
Interactive segmentation enables users to extract binary masks of target objects through simple interactions such as clicks, scribbles, and boxes. However, existing methods often s…
TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
Mingkang Zhu, Xi Chen, Zhongdao Wang +3
Recent advancements in reinforcement learning from human feedback have shown that utilizing fine-grained token-level reward models can substantially enhance the performance of Prox…
LayerFlow: A Unified Model for Layer-aware Video Generation
Sihui Ji, Hao Luo, Xi Chen +3
We present LayerFlow, a unified solution for layer-aware video generation. Given per-layer prompts, LayerFlow generates videos for the transparent foreground, clean background, and…
PlayerOne: Egocentric World Simulator
Yuanpeng Tu, Hao Luo, Xi Chen +3
We introduce PlayerOne, the first egocentric realistic world simulator, facilitating immersive and unrestricted exploration within vividly dynamic environments. Given an egocentric…
Modular Customization of Diffusion Models via Blockwise-Parameterized Low-Rank Adaptation
Mingkang Zhu, Xi Chen, Zhongdao Wang +3
Recent diffusion model customization has shown impressive results in incorporating subject or style concepts with a handful of images. However, the modular composition of multiple…
Enhancing LLM Knowledge Learning through Generalization
Mingkang Zhu, Xi Chen, Zhongdao Wang +3
As Large language models (LLMs) are increasingly deployed in diverse applications, faithfully integrating evolving factual knowledge into these models remains a critical challenge.…