Jing Liu

Venues

Frequent coauthors

Papers

1. OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs
   AAAI 2026 ·

   Feng Chen

   DBLP profile ↗ORCID search ↗
2. Channel Merging: Preserving Specialization for Merged Experts
   AAAI 2025 ·

   Mingyang Zhang

   DBLP profile ↗ORCID search ↗
3. Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher
   ICLR 2025 ·

   Yong Guo

   DBLP profile ↗ORCID search ↗
4. HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration
   ICML 2025 ·

   Yushi Huang

   DBLP profile ↗ORCID search ↗
5. Efficient Stitchable Task Adaptation
   CVPR 2024 ·

   Haoyu He

   DBLP profile ↗ORCID search ↗
6. EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
   ICLR 2024 ·

   Yefei He

   DBLP profile ↗ORCID search ↗
7. MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
   NeurIPS 2024 ·

   Akide Liu

   DBLP profile ↗ORCID search ↗
8. QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
   ICLR 2024 · Jing Liu
9. Stitched ViTs are Flexible Vision Backbones
   ECCV 2024 ·

   Zizheng Pan

   DBLP profile ↗ORCID search ↗
10. TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models
    CVPR 2024 ·

    Yushi Huang

    DBLP profile ↗ORCID search ↗
11. ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
    NeurIPS 2024 ·

    Yefei He

    DBLP profile ↗ORCID search ↗