Chenliang Xu

Venues

Frequent coauthors

Papers

1. Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting
   AAAI 2026 ·

   Yolo Yunlong Tang

   DBLP profile ↗ORCID search ↗
2. DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning
   ACL 2026 ·

   Chao Huang

   DBLP profile ↗ORCID search ↗
3. Tuning the Face: Modulating Facial Expressions for Realistic Self-Avatars in Virtual Reality
   DIS 2026 ·

   Yang Lu

   DBLP profile ↗ORCID search ↗
4. $\pi$-AVAS: Can Physics-Integrated Audio-Visual Modeling Boost Neural Acoustic Synthesis?
   ICCV 2025 ·

   Susan Liang

   DBLP profile ↗ORCID search ↗
5. BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models
   ICML 2025 ·

   Susan Liang

   DBLP profile ↗ORCID search ↗
6. CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion
   AAAI 2025 ·

   Yunlong Tang

   DBLP profile ↗ORCID search ↗
7. Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts
   ACL 2025 ·

   Zeliang Zhang

   DBLP profile ↗ORCID search ↗
8. Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding
   AAAI 2025 ·

   Yunlong Tang

   DBLP profile ↗ORCID search ↗
9. Generative AI for Cel-Animation: A Survey
   ICCV 2025 ·

   Yunlong Tang

   DBLP profile ↗ORCID search ↗
10. GestureLSM: Latent Shortcut Based Co-Speech Gesture Generation with Spatial-Temporal Modeling
    ICCV 2025 ·

    Pinxin Liu

    DBLP profile ↗ORCID search ↗
11. Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
    NeurIPS 2025 ·

    Jiani Liu

    DBLP profile ↗ORCID search ↗
12. Learning to Highlight Audio by Watching Movies
    CVPR 2025 ·

    Chao Huang

    DBLP profile ↗ORCID search ↗
13. MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness
    NeurIPS 2025 ·

    Yunlong Tang

    DBLP profile ↗ORCID search ↗
14. Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives
    ICLR 2025 ·

    Zeliang Zhang

    DBLP profile ↗ORCID search ↗
15. Targeted Forgetting of Image Subgroups in CLIP Models
    CVPR 2025 ·

    Zeliang Zhang

    DBLP profile ↗ORCID search ↗
16. Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach
    CVPR 2025 ·

    Jing Bi

    DBLP profile ↗ORCID search ↗
17. V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning
    AAAI 2025 ·

    Hang Hua

    DBLP profile ↗ORCID search ↗
18. VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
    CVPR 2025 ·

    Yunlong Tang

    DBLP profile ↗ORCID search ↗
19. ZeroSep: Separate Anything in Audio with Zero Training
    NeurIPS 2025 ·

    Chao Huang

    DBLP profile ↗ORCID search ↗
20. Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP
    EMNLP 2024 ·

    Zeliang Zhang

    DBLP profile ↗ORCID search ↗
21. Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
    CVPR 2024 ·

    Zeliang Zhang

    DBLP profile ↗ORCID search ↗
22. EAGLE: Egocentric AGgregated Language-video Engine
    ACM MM 2024 ·

    Jing Bi

    DBLP profile ↗ORCID search ↗
23. Learning to Transform Dynamically for Better Adversarial Transferability
    CVPR 2024 ·

    Rongyi Zhu

    DBLP profile ↗ORCID search ↗
24. Modeling and Driving Human Body Soundfields Through Acoustic Primitives
    ECCV 2024 ·

    Chao Huang

    DBLP profile ↗ORCID search ↗
25. OSCaR: Object State Captioning and State Change Representation
    NAACL 2024 ·

    Nguyen Nguyen

    DBLP profile ↗ORCID search ↗
26. One Forward is Enough for Neural Network Training via Likelihood Ratio Method
    ICLR 2024 ·

    Jinyang Jiang

    DBLP profile ↗ORCID search ↗
27. Tri2-plane: Thinking Head Avatar via Feature Pyramid
    ECCV 2024 ·

    Luchuan Song

    DBLP profile ↗ORCID search ↗