53 citations · 85 across the 32 of their papers we have counts for
36 papers
On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training
Shufan Shen, Zhongni Hou, Junshu Sun +5
The strong generalization performance of on-policy post-training paradigms has motivated studies of their parameter update behaviors. However, these studies treat the observed beha…
Object-Aware Background-Controlled Editing via Weighted Velocity Guidance
Wuji Wang, Yue Wu, Chenhao Yi +1
Training-free image editing steers diffusion or flow-matching generative models at inference time by modifying prompt-conditioned denoising velocities. Existing velocity-based edit…
DyGT: Modeling Object Dynamics with 3D Gaussian Temporal-Spatial Particle Graph Transformer
Yansong Wang, Zhaobo Qi, Xinyan Liu +4
Modeling object dynamics from limited visual observations is a fundamental problem for enabling accurate motion trajectory prediction in embodied interaction scenarios. Existing dy…
When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning
Zhengqi Pei, Qingming Huang, Shuhui Wang
Chain-of-Thought (CoT) improves large language models (LLMs) on difficult reasoning tasks, but it often incurs long natural-language rationales that are poorly aligned with efficie…
ActiveScope: Actively Seeking and Correcting Perception for MLLMs
Yajing Wang, Chao Bi, Junshu Sun +4
Multimodal Large Language Models (MLLMs) have demonstrated impressive vision-language understanding, yet still struggle with fine-grained perception in high-resolution images. Whil…
Adaptive Recurrent Message Passing for Test Time Computing on Graphs
Junshu Sun, Wanxing Chang, Qingming Huang +1
Pre-trained foundation models have demonstrated remarkable success in many domains, enabling a unified backbone to generalize across diverse downstream tasks. However, extending th…
Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation
Junshu Sun, Wanxing Chang, Qingming Huang +1
Graph neural networks (GNNs) tightly couple their input-output parameters to dataset-specific feature spaces and target sets, exhibiting limited transferability across different da…
Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
Tiantian Dang, Chao Bi, Shufan Shen +3
Despite the significant advancements in Large Vision-Language Models (LVLMs), their tendency to generate hallucinations undermines reliability and restricts broader practical deplo…
Enhancing Pre-trained Representation Classifiability can Boost its Interpretability
Shufan Shen, Zhaobo Qi, Junshu Sun +3
The visual representation of a pre-trained model prioritizes the classifiability on downstream tasks, while the widespread applications for pre-trained visual models have posed new…
Kernelized Sparse Fine-Tuning with Bi-level Parameter Competition for Vision Models
Shufan Shen, Junshu Sun, Shuhui Wang +1
Parameter-efficient fine-tuning (PEFT) aims to adapt pre-trained vision models to downstream tasks. Among PEFT paradigms, sparse tuning achieves remarkable performance by adjusting…
Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs
Jinzhe Liu, Junshu Sun, Shufan Shen +2
Lifelong knowledge editing enables continuous, precise updates to outdated knowledge in large language models (LLMs) without computationally expensive full retraining. However, exi…
VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
Shufan Shen, Junshu Sun, Qingming Huang +1
The alignment of vision-language representations endows current Vision-Language Models (VLMs) with strong multi-modal reasoning capabilities. However, the interpretability of the a…
Relieving the Over-Aggregating Effect in Graph Transformers
Junshu Sun, Wanxing Chang, Chenxue Yang +2
Graph attention has demonstrated superior performance in graph learning tasks. However, learning from global interactions can be challenging due to the large number of nodes. In th…
Neuronal Group Communication for Efficient Neural representation
Zhengqi Pei, Qingming Huang, Shuhui Wang
The ever-increasing scale of modern neural networks has brought unprecedented performance alongside daunting challenges in efficiency and interpretability. This paper addresses the…
Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos
Yufan Zhou, Zhaobo Qi, Lingshuai Lin +5
In this paper, we address the challenge of procedure planning in instructional videos, aiming to generate coherent and task-aligned action sequences from start and end visual obser…
Towards Dynamic Message Passing on Graphs
Junshu Sun, Chenxue Yang, Xiangyang Ji +2
Message passing plays a vital role in graph neural networks (GNNs) for effective feature learning. However, the over-reliance on input topology diminishes the efficacy of message p…
Expanding Sparse Tuning for Low Memory Usage
Shufan Shen, Junshu Sun, Xiangyang Ji +2
Parameter-efficient fine-tuning (PEFT) is an effective method for adapting pre-trained vision models to downstream tasks by tuning a small subset of parameters. Among PEFT methods,…
Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering
Ting Yu, Kunhao Fu, Shuhui Wang +2
Video Question Answering (VideoQA) represents a crucial intersection between video understanding and language processing, requiring both discriminative unimodal comprehension and s…
Confusing Pair Correction Based on Category Prototype for Domain Adaptation under Noisy Environments
Churan Zhi, Junbao Zhuo, Shuhui Wang
In this paper, we address unsupervised domain adaptation under noisy environments, which is more challenging and practical than traditional domain adaptation. In this scenario, the…
Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video
Zhaobo Qi, Yibo Yuan, Xiaowen Ruan +3
Temporal Sentence Grounding in Video (TSGV) is troubled by dataset bias issue, which is caused by the uneven temporal distribution of the target moments for samples with similar se…
R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation
Jiayu Xiao, Henglei Lv, Liang Li +2
Recent text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images given text-prompts as input. However, these models fail to convey ap…
Open-Set Knowledge-Based Visual Question Answering with Inference Paths
Jingru Gan, Xinzhe Han, Shuhui Wang +1
Given an image and an associated textual question, the purpose of Knowledge-Based Visual Question Answering (KB-VQA) is to provide a correct answer to the question with the aid of…
Orthogonal Temporal Interpolation for Zero-Shot Video Recognition
Yan Zhu, Junbao Zhuo, Bin Ma +4
Zero-shot video recognition (ZSVR) is a task that aims to recognize video categories that have not been seen during the model training process. Recently, vision-language models (VL…
COMICS: End-to-end Bi-grained Contrastive Learning for Multi-face Forgery Detection
Cong Zhang, Honggang Qi, Shuhui Wang +2
DeepFakes have raised serious societal concerns, leading to a great surge in detection-based forensics methods in recent years. Face forgery recognition is a standard detection met…