1 citations · 2 across the 31 of their papers we have counts for
38 papers
VideoTapestry: Query-Adaptive Memory Refinement for Multi-Agent Long-Video Understanding
Yucheng Liu, Yufei Yin, Mingxiao Feng +3
Long-video understanding places substantial demands on memory, as answering questions often requires retrieving information distributed across extended temporal spans. Existing app…
Revisiting On-policy Adversarial Black-Box Distillation: Calibrating Groupwise Reward Geometry for Effective Advantage Construction
Xiao Cui, Mo Zhu, Yulei Qin +3
Black-box distillation is a practical route for transferring capabilities from API-accessible large language models that expose only text outputs into smaller student models. Recen…
WAM-OPD: Sharpening World Action Models via On-Policy Distillation
Panjun Liu, Xiaohan Lei, Shiqi Zhang +8
Pretrained world action models (WAMs) provide generalist capabilities across diverse robotic manipulation tasks, yet improving target-task performance to an expert level without de…
HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question Answering
Rongjian Gu, Wengang Zhou, Junyu Xiong +4
Multi-page document visual question answering requires locating sparse evidence at both the page and region levels. Existing approaches typically emphasize one level over the other…
Hierarchical Evidence-Driven Reasoning for Long Document Understanding
Junyu Xiong, Yonghui Wang, Rongjian Gu +4
Retrieval-Augmented Generation (RAG) streamlines long-document understanding by leveraging retrieval mechanisms to restrict input images to a highly curated subset. However, existi…
Revisiting Shadow Detection from a Vision-Language Perspective
Yonghui Wang, Shaokai Liu, Wengang Zhou +2
Shadow detection is commonly formulated as a vision-driven dense prediction problem, where models rely primarily on pixel-wise visual supervision to distinguish shadows from non-sh…
Geometry-Aware Dataset Condensation for Diffusion Model Training
Xiao Cui, Yulei Qin, Mo Zhu +3
Dataset condensation aims to construct compact datasets from real data via synthesis or selection. However, existing approaches are ill-suited for diffusion model training: synthet…
Self-supervised Hierarchical Visual Reasoning with World Model
Yuanfei Xu, Lin Liu, Wengang Zhou +2
3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning due to their vast state spaces. Effective reasoning representations are ess…
Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing
Shaodong Xu, Zexian Li, Zhendong Wang +5
A fundamental challenge in image editing lies in preserving spatial locality: edits should improve targeted content without inadvertently altering surrounding regions. However, mos…
Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers
Shaodong Xu, Zhendong Wang, Litong Gong +4
Recent advances in Diffusion Transformers (DiTs) demonstrate that aligning noisy latent states with well-trained semantic features-as pioneered by Representation Alignment (REPA)-c…
SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval
Xin Xie, Dongyun Xue, Wuguannan Yao +5
LLM-powered systems require complex multi-step decision-making abilities to solve real-world tasks, yet current planning approaches face a trade-off between the high latency of inf…
Structural Action Transformer for 3D Dexterous Manipulation
Xiaohan Lei, Min Wang, Bohong Weng +2
Achieving human-level dexterity in robots via imitation learning from heterogeneous datasets is hindered by the challenge of cross-embodiment skill transfer, particularly for high-…
StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models
Keli Liu, Zhendong Wang, Wengang Zhou +1
Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high resolutions. We obser…
Primary-Fine Decoupling for Action Generation in Robotic Imitation
Xiaohan Lei, Min Wang, Wengang Zhou +2
Multi-modal distribution in robotic manipulation action sequences poses critical challenges for imitation learning. To this end, existing approaches often model the action space as…
CodeContests-O: Powering LLMs via Feedback-Driven Iterative Test Case Generation
Jianfeng Cai, Jinhua Zhu, Ruopei Sun +5
The rise of reasoning models necessitates large-scale verifiable data, for which programming tasks serve as an ideal source. However, while competitive programming platforms provid…
Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling
Xiao Cui, Yulei Qin, Xinyue Li +3
Dataset distillation creates a small distilled set that enables efficient training by capturing key information from the full dataset. While existing dataset distillation methods p…
Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction
Haolin Song, Hongbo Zhu, Tao Yu +5
For full-size humanoid robots, even with recent advances in reinforcement learning-based control, achieving reliable locomotion on complex terrains, such as long staircases, remain…
Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters
Zhiyang Guo, Ori Zhang, Jax Xiang +4
Posing 3D characters is a fundamental task in computer graphics. However, existing paradigms, ranging from traditional auto-rigging to recent pose-conditioned generative models, fr…
Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation
Xiao Cui, Yulei Qin, Wengang Zhou +2
Dataset distillation seeks to synthesize a compact distilled dataset, enabling models trained on it to achieve performance comparable to models trained on the full dataset. Recent…
Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling
Jiahao Wang, Weiye Xu, Aijun Yang +5
Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs). In the mul…
ScaleWeaver: Weaving Efficient Controllable T2I Generation with Multi-Scale Reference Attention
Keli Liu, Zhendong Wang, Wengang Zhou +3
Text-to-image generation with visual autoregressive~(VAR) models has recently achieved impressive advances in generation fidelity and inference efficiency. While control mechanisms…
Goal Discovery with Causal Capacity for Efficient Reinforcement Learning
Yan Yu, Yaodong Yang, Zhengbo Lu +3
Causal inference is crucial for humans to explore the world, which can be modeled to enable an agent to efficiently explore the environment in reinforcement learning. Existing rese…
SLRTP2025 Sign Language Production Challenge: Methodology, Results, and Future Work
Harry Walsh, Ed Fish, Ozge Mercanoglu Sincan +19
Sign Language Production (SLP) is the task of generating sign language video from spoken language inputs. The field has seen a range of innovations over the last few years, with th…
Search-Based Credit Assignment for Offline Preference-Based Reinforcement Learning
Xiancheng Gao, Yufeng Shi, Wengang Zhou +1
Offline reinforcement learning refers to the process of learning policies from fixed datasets, without requiring additional environment interaction. However, it often relies on wel…