Siteng Huang

Venues

Frequent coauthors

Papers

1. Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration
   AAAI 2026 ·

   Yuhang Han

   DBLP profile ↗ORCID search ↗
2. Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
   AAAI 2026 ·

   Xuyang Liu

   DBLP profile ↗ORCID search ↗
3. Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors
   AAAI 2026 ·

   Haoyu Zhao

   DBLP profile ↗ORCID search ↗
4. VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
   AAAI 2026 ·

   Yihao Wang

   DBLP profile ↗ORCID search ↗
5. Accelerating Diffusion Transformers with Token-wise Feature Caching
   ICLR 2025 ·

   Chang Zou

   DBLP profile ↗ORCID search ↗
6. CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction
   ICCV 2025 ·

   Zhefei Gong

   DBLP profile ↗ORCID search ↗
7. Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
   AAAI 2025 ·

   Han Zhao

   DBLP profile ↗ORCID search ↗
8. Quart-Online: Latency-Free Multimodal Large Language Model for Quadruped Robot Learning
   ICRA 2025 ·

   Xinyang Tong

   DBLP profile ↗ORCID search ↗
9. SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning
   NeurIPS 2025 ·

   Yang Liu

   DBLP profile ↗ORCID search ↗
10. Check, Locate, Rectify: A Training-Free Layout Calibration System for Text- to- Image Generation
    CVPR 2024 ·

    Biao Gong

    DBLP profile ↗ORCID search ↗
11. Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation
    CVPR 2024 · Siteng Huang
12. PiTe: Pixel-Temporal Alignment for Large Video-Language Model
    ECCV 2024 ·

    Yang Liu

    DBLP profile ↗ORCID search ↗
13. ProFD: Prompt-Guided Feature Disentangling for Occluded Person Re-Identification
    ACM MM 2024 ·

    Can Cui

    DBLP profile ↗ORCID search ↗
14. Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation
    AAAI 2024 ·

    Shuanghao Bai

    DBLP profile ↗ORCID search ↗
15. QUAR-VLA: Vision-Language-Action Model for Quadruped Robots
    ECCV 2024 ·

    Pengxiang Ding

    DBLP profile ↗ORCID search ↗
16. Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
    CVPR 2024 · Siteng Huang