60 citations · 96 across the 34 of their papers we have counts for
34 papers
TTTIR: Unlocking Instance-Specific State Evolution via Test-Time Training for Image Restoration
Kaihang Zheng, Jun Li, Hang Guo +5
Image restoration is inherently challenging due to the diverse and highly input-dependent nature of real-world degradations. While recent architectures like Transformers and state-…
DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding
Hanshu Yao, Janfeng Zhong, Niu Lian +1
Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, yet existing systems remain limited by static retrieval and fragile cross-…
LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World Models
Jiarui Yang, Jiale Zhange, Jiawei Li +5
World models enable agents to perform forward rollout and planning without real-world interaction. However, their application in open-world embodied intelligence remains limited by…
Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering
Dongxing Mao, Jinpeng Wang, Jiahao Tang +6
Visual Autoregressive (AR) models generate images by predicting discrete tokens that are decoded by a visual tokenizer. Despite demonstrating strong overall image generation abilit…
VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning
Xingyu Lu, Jinpeng Wang, Yi-Fan Zhang +13
Visual captioning requires models to capture visual content faithfully while minimizing both omission and hallucination. As the dominant paradigm for captioning, MLLMs have achieve…
Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval
Jun Li, Peifeng Lai, Xuhang Lou +5
Partially relevant video retrieval aims to retrieve untrimmed videos using text queries that describe only partial content. However, the inherent asymmetry between brief queries an…
From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents
Niu Lian, Yuting Wang, Hanshu Yao +5
While multimodal large language models have demonstrated impressive short-term reasoning, they struggle with long-horizon video understanding due to limited context windows and sta…
Love Me, Love My Label: Rethinking the Role of Labels in Prompt Retrieval for Visual In-Context Learning
Tianci Luo, Haohao Pan, Jinpeng Wang +5
Visual in-context learning (VICL) enables visual foundation models to handle multiple tasks by steering them with demonstrative prompts. The choice of such prompts largely influenc…
Imagine Before Concentration: Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval
Jun Li, Xuhang Lou, Jinpeng Wang +4
Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos based on text queries that describe only partial events. Existing methods suffer from incomplete global…
PromptHub: Enhancing Multi-Prompt Visual In-Context Learning with Locality-Aware Fusion, Concentration and Alignment
Tianci Luo, Jinpeng Wang, Shiyu Qin +5
Visual In-Context Learning (VICL) aims to complete vision tasks by imitating pixel demonstrations. Recent work pioneered prompt fusion that combines the advantages of various demon…
Heterogeneous Uncertainty-Guided Composed Image Retrieval with Fine-Grained Probabilistic Learning
Haomiao Tang, Jinpeng Wang, Minyi Zhao +4
Composed Image Retrieval (CIR) enables image search by combining a reference image with modification text. Intrinsic noise in CIR triplets incurs intrinsic uncertainty and threaten…
Towards Efficient Low-rate Image Compression with Frequency-aware Diffusion Prior Refinement
Yichong Xia, Yimin Zhou, Jinpeng Wang +1
Recent advancements in diffusion-based generative priors have enabled visually plausible image compression at extremely low bit rates. However, existing approaches suffer from slow…
CoPRS: Learning Positional Prior from Chain-of-Thought for Reasoning Segmentation
Zhenyu Lu, Liupeng Li, Jinpeng Wang +4
Existing works on reasoning segmentation either connect hidden features from a language model directly to a mask decoder or represent positions in text, which limits interpretabili…
MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds
Junxi Wu, Jinpeng Wang, Zheng Liu +4
The rapid advancement of large language models has intensified public concerns about the potential misuse. Therefore, it is important to build trustworthy AI-generated text detecti…
HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning
Jun Li, Jinpeng Wang, Chaolei Tan +6
Partially Relevant Video Retrieval (PRVR) addresses the critical challenge of matching untrimmed videos with text queries describing only partial content. Existing methods suffer f…
PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter
Yaohua Zha, Yanzi Wang, Hang Guo +7
Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightfor…
EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models
GuangHao Meng, Sunan He, Jinpeng Wang +7
Vision-language retrieval (VLR) has attracted significant attention in both academia and industry, which involves using text (or images) as queries to retrieve corresponding images…
Embracing Collaboration Over Competition: Condensing Multiple Prompts for Visual In-Context Learning
Jinpeng Wang, Tianci Luo, Yaohua Zha +7
Visual In-Context Learning (VICL) enables adaptively solving vision tasks by leveraging pixel demonstrations, mimicking human-like task completion through analogy. Prompt selection…
AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video Hashing
Niu Lian, Jun Li, Jinpeng Wang +4
Self-Supervised Video Hashing (SSVH) compresses videos into hash codes for efficient indexing and retrieval using unlabeled training videos. Existing approaches rely on random fram…
Efficient Self-Supervised Video Hashing with Selective State Spaces
Jinpeng Wang, Niu Lian, Jun Li +5
Self-supervised video hashing (SSVH) is a practical task in video indexing and retrieval. Although Transformers are predominant in SSVH for their impressive temporal modeling capab…
BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping
Taolin Zhang, Jinpeng Wang, Hang Guo +3
Adaptation of pretrained vision-language models such as CLIP to various downstream tasks have raised great interest in recent researches. Previous works have proposed a variety of…
Towards Scalable Semantic Representation for Recommendation
Taolin Zhang, Junwei Pan, Jinpeng Wang +9
With recent advances in large language models (LLMs), there has been emerging numbers of research in developing Semantic IDs based on LLMs to enhance the performance of recommendat…
MambaVC: Learned Visual Compression with Selective State Spaces
Shiyu Qin, Jinpeng Wang, Yimin Zhou +6
Learned visual compression is an important and active task in multimedia. Existing approaches have explored various CNN- and Transformer-based designs to model content distribution…
GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval
Yuting Wang, Jinpeng Wang, Bin Chen +3
Given a text query, partially relevant video retrieval (PRVR) aims to retrieve untrimmed videos containing relevant moments. Due to the lack of moment annotations, the uncertainty…