PPaperPicks

Wenjun Zeng

Eastern Institute of Technology, Ningbo, China

22 papers at tracked venues · 15 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning
  2. DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
  3. Hybrid-Grained Feature Aggregation with Coarse-to-Fine Language Guidance for Self-Supervised Monocular Depth Estimation
  4. Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution Detection
  5. MultiConIR: Towards Multi-Condition Information Retrieval
  6. Open-World Reinforcement Learning over Long Short-Term Imagination
  7. Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions
  8. RLLTE: Long-Term Evolution Project of Reinforcement Learning
  9. ULTHO: Ultra-Lightweight Yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning
  10. UniScene: Unified Occupancy-centric Driving Scene Generation
  11. Architecture-Agnostic Unsupervised Gradient Regularization for Parameter-Efficient Transfer Learning
  12. Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion
  13. Closed-Loop Unsupervised Representation Disentanglement with β-VAE Distillation and Diffusion Probabilistic Feedback
  14. Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models
  15. HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects
  16. Hierarchical Temporal Context Learning for Camera-Based Semantic Scene Completion
  17. Inter-X: Towards Versatile Human-Human Interaction Analysis
  18. Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
  19. One at a Time: Progressive Multi-Step Volumetric Probability Learning for Reliable 3D Scene Perception
  20. Rate-Distortion-Cognition Controllable Versatile Neural Image Compression
  21. ReGenNet: Towards Human Action-Reaction Synthesis
  22. Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation