PPaperPicks

Jun Zhang

Hong Kong University of Science and Technology, Department of Electronic and Computer Engineering, Hong Kong

19 papers at tracked venues · 14 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing
  2. GaussianImage++: Boosted Image Representation and Compression with 2D Gaussian Splatting
  3. VIL2C: Value-of-Information Aware Low-Latency Communication for Multi-Agent Reinforcement Learning
  4. C2IQL: Constraint-Conditioned Implicit Q-learning for Safe Offline Reinforcement Learning
  5. CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression
  6. Dimensionx: Create Any 3D and 4D Scenes From a Single Image With Decoupled Video Diffusion
  7. EVA-Gaussian: 3D Gaussian-Based Real-Time Human Novel View Synthesis Under Diverse Multi-View Camera Settings
  8. Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning
  9. GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering
  10. Graph Neural Network Enhanced Retrieval for Question Answering of Large Language Models
  11. HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration
  12. MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes
  13. Reinforcement Learning with Intrinsically Motivated Feedback Graph for Lost-sales Inventory Control
  14. Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model
  15. Boosting Neural Representations for Videos with a Conditional Decoder
  16. Context-aware Communication for Multi-agent Reinforcement Learning
  17. GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting
  18. Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning
  19. Task-Aware Encoder Control for Deep Video Compression