PPaperPicks

Dong Li

AMD Inc., Advanced Micro Devices Inc., Beijing, China

17 papers at tracked venues · 14 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-7369-1445 ↗Google Scholar ↗Homepage ↗

Venues

AAAI ×5ICML ×3NeurIPS ×3ACL ×2BMVC ×1CVPR ×1EMNLP ×1NAACL ×1

Frequent coauthors

Yixing Xu
DBLP profile ↗ORCID search ↗
×2
Jiajun Jiao
DBLP profile ↗ORCID search ↗
×1
Zekai Li
DBLP profile ↗ORCID search ↗
×1
Hui Wu
DBLP profile ↗ORCID search ↗
×1
Huanxuan Liao
DBLP profile ↗ORCID search ↗
×1
Xiusheng Huang
DBLP profile ↗ORCID search ↗
×1
Zeping Li
DBLP profile ↗ORCID search ↗
×1
Lian Liu
DBLP profile ↗ORCID search ↗
×1
Yixiong Huo
DBLP profile ↗ORCID search ↗
×1
Jinze Li
DBLP profile ↗ORCID search ↗
×1
Xiaomin Li
DBLP profile ↗ORCID search ↗
×1
Guanchen Li
DBLP profile ↗ORCID search ↗
×1

Papers

  1. DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation
    AAAI 2026 ·
    Jiajun Jiao
    DBLP profile ↗ORCID search ↗
  2. Learnable Permutation for Structured Sparsity on Transformer Models
    AAAI 2026 ·
    Zekai Li
    DBLP profile ↗ORCID search ↗
  3. MoEC: A Memory-Routed Mixture-of-Experts Controller for Adaptive Minecraft Control
    ACL 2026 ·
    Hui Wu
    DBLP profile ↗ORCID search ↗
  4. SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
    AAAI 2026 ·
    Huanxuan Liao
    DBLP profile ↗ORCID search ↗
  5. Theory-optimal Quantization Based on Flatness
    ACL 2026 ·
    Xiusheng Huang
    DBLP profile ↗ORCID search ↗
  6. Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference
    NAACL 2025 ·
    Zeping Li
    DBLP profile ↗ORCID search ↗
  7. BaWA: Automatic Optimizing Pruning Metric for Large Language Models with Balanced Weight and Activation
    ICML 2025 ·
    Lian Liu
    DBLP profile ↗ORCID search ↗
  8. EGSRAL: An Enhanced 3D Gaussian Splatting Based Renderer with Automated Labeling for Large-Scale Driving Scene
    AAAI 2025 ·
    Yixiong Huo
    DBLP profile ↗ORCID search ↗
  9. Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
    ICML 2025 ·
    Jinze Li
    DBLP profile ↗ORCID search ↗
  10. ReNeg: Learning Negative Embedding with Reward Guidance
    CVPR 2025 ·
    Xiaomin Li
    DBLP profile ↗ORCID search ↗
  11. Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization
    NeurIPS 2025 ·
    Guanchen Li
    DBLP profile ↗ORCID search ↗
  12. DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models
    EMNLP 2024 ·
    Wenjing Ke
    DBLP profile ↗ORCID search ↗
  13. DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization
    NeurIPS 2024 ·
    Haowei Zhu
    DBLP profile ↗ORCID search ↗
  14. Enhancing Vision Transformer: Amplifying Non-Linearity in Feedforward Network Module
    ICML 2024 ·
    Yixing Xu
    DBLP profile ↗ORCID search ↗
  15. MonoGS++: Fast and Accurate Monocular RGB Gaussian SLAM
    BMVC 2024 ·
    Renwu Li
    DBLP profile ↗ORCID search ↗
  16. QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion
    NeurIPS 2024 ·
    Yixing Xu
    DBLP profile ↗ORCID search ↗
  17. UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer
    AAAI 2024 ·
    Ji Liu
    DBLP profile ↗ORCID search ↗