Zhihang Yuan

Venues

Frequent coauthors

Papers

1. OTARo: Once Tuning for All Precisions Toward Robust On-Device LLMs
   AAAI 2026 ·

   Shaoyuan Chen

   DBLP profile ↗ORCID search ↗
2. VocabTailor: Dynamic Vocabulary Selection for Downstream Tasks in Small Language Models
   ACL 2026 ·

   Hanling Zhang

   DBLP profile ↗ORCID search ↗
3. A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
   CVPR 2025 ·

   Kai Wang

   DBLP profile ↗ORCID search ↗
4. DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation
   ACM MM 2025 · Zhihang Yuan
5. DiTFastAttnV2: Head-Wise Attention Compression for Multi-Modality Diffusion Transformers
   ICCV 2025 ·

   Hanling Zhang

   DBLP profile ↗ORCID search ↗
6. Dlfr-Gen: Diffusion-Based Video Generation With Dynamic Latent Frame Rate
   ICCV 2025 · Zhihang Yuan
7. EA-Vit: Efficient Adaptation for Elastic Vision Transformer
   ICCV 2025 ·

   Chen Zhu

   DBLP profile ↗ORCID search ↗
8. GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning
   ACL 2025 ·

   Sifan Zhou

   DBLP profile ↗ORCID search ↗
9. MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Static Quantization
   ACM MM 2025 ·

   Jiangyong Yu

   DBLP profile ↗ORCID search ↗
10. MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues
    ICRA 2025 ·

    Zhaofeng Hu

    DBLP profile ↗ORCID search ↗
11. MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods
    ICLR 2025 ·

    Zukang Xu

    DBLP profile ↗ORCID search ↗
12. MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance
    ICML 2025 ·

    Zhixuan Chen

    DBLP profile ↗ORCID search ↗
13. MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design
    ICML 2025 ·

    Haojie Duanmu

    DBLP profile ↗ORCID search ↗
14. OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
    ICLR 2025 ·

    Xing Hu

    DBLP profile ↗ORCID search ↗
15. PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram
    CVPR 2025 ·

    Sifan Zhou

    DBLP profile ↗ORCID search ↗
16. QuEST: Low-Bit Diffusion Model Quantization via Efficient Selective Finetuning
    ICCV 2025 ·

    Haoxuan Wang

    DBLP profile ↗ORCID search ↗
17. R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
    NeurIPS 2025 ·

    Tianyu Fu

    DBLP profile ↗ORCID search ↗
18. RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
    ICML 2025 ·

    Chen Xu

    DBLP profile ↗ORCID search ↗
19. SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
    NeurIPS 2025 ·

    Zhenglin Lai

    DBLP profile ↗ORCID search ↗
20. Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance
    EMNLP 2025 ·

    Songsheng Wang

    DBLP profile ↗ORCID search ↗
21. DiTFastAttn: Attention Compression for Diffusion Transformer Models
    NeurIPS 2024 · Zhihang Yuan
22. Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding
    ICML 2024 ·

    Chuanhao Sun

    DBLP profile ↗ORCID search ↗
23. PB-LLM: Partially Binarized Large Language Models
    ICLR 2024 · Zhihang Yuan