pith. sign in

Wenjun Zeng

Identifiers

  • name variant Wenjun Zeng 0.60 · backfill

Papers (40)

  1. DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning cs.RO · 2026 · author #12
  2. Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs cs.CV · 2026 · author #5
  3. ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? cs.CV · 2026 · author #9
  4. Proprioceptive-visual correspondence enables self-other distinction in humanoid robots cs.RO · 2026 · author #7
  5. Can VLA Models Learn from Real-World Data Continually without Forgetting? cs.RO · 2026 · author #7
  6. Generation Navigator: A State-Aware Agentic Framework for Image Generation cs.CV · 2026 · author #4
  7. An Efficient Streaming Video Understanding Framework with Agentic Control cs.CV · 2026 · author #8
  8. From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation cs.CV · 2026 · author #11
  9. ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation cs.LG · 2026 · author #2
  10. SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations cs.CV · 2026 · author #9
  11. Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining cs.RO · 2026 · author #4
  12. Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning cs.LG · 2025 · author #10
  13. Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method cs.CV · 2025 · author #12
  14. OmniNWM: Omniscient Driving Navigation World Models cs.CV · 2025 · author #13
  15. Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends cs.CR · 2025 · author #8
  16. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities cs.CL · 2025 · author #1356
  17. DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge cs.CV · 2025 · author #13
  18. Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning cs.CV · 2025 · author #9
  19. Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion cs.CV · 2024 · author #7
  20. ShieldGemma: Generative AI Content Moderation Based on Gemma cs.CL · 2024 · author #1
  21. SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking cs.CV · 2019 · author #4
  22. View Invariant 3D Human Pose Estimation cs.CV · 2019 · author #3
  23. Densely Semantically Aligned Person Re-Identification cs.CV · 2018 · author #3
  24. Content-Aware Personalised Rate Adaptation for Adaptive Streaming via Deep Video Analysis cs.MM · 2018 · author #5
  25. Detect or Track: Towards Cost-Effective Video Object Detection/Tracking cs.CV · 2018 · author #4
  26. Temporal-Spatial Mapping for Action Recognition cs.CV · 2018 · author #3
  27. Towards a Better Match in Siamese Network Based Visual Object Tracker cs.CV · 2018 · author #4
  28. Adding Attentiveness to the Neurons in Recurrent Neural Networks cs.CV · 2018 · author #4
  29. Learning to Update for Object Tracking with Recurrent Meta-learner cs.CV · 2018 · author #3
  30. A Twofold Siamese Network for Real-Time Object Tracking cs.CV · 2018 · author #4
  31. Object Detection in Videos by High Quality Object Linking cs.CV · 2018 · author #5
  32. Benchmarking Single Image Dehazing and Beyond cs.CV · 2017 · author #6
  33. Human Pose Estimation using Global and Local Normalization cs.CV · 2017 · author #4
  34. View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data cs.CV · 2017 · author #4
  35. Deep Convolutional Neural Networks with Merge-and-Run Mappings cs.CV · 2016 · author #5
  36. An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data cs.CV · 2016 · author #4
  37. Photo Stylistic Brush: Robust Style Transfer via Superpixel-Based Bipartite Graph cs.CV · 2016 · author #4
  38. Deeply-Fused Nets cs.CV · 2016 · author #4
  39. Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks cs.CV · 2016 · author #4
  40. Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks cs.CV · 2016 · author #4

Mentions

  • 2606.25939 #12 · arxiv_oai · confidence 0.70 Wenjun Zeng
  • 2606.25758 #5 · arxiv_oai · confidence 0.70 Wenjun Zeng
  • 2510.18313 #13 · arxiv_oai · confidence 0.70 Wenjun Zeng
  • 2606.19531 #9 · arxiv_oai · confidence 0.70 Wenjun Zeng
  • 2606.13222 #7 · arxiv_oai · confidence 0.70 Wenjun Zeng
  • 2604.23099 #2 · arxiv_oai · confidence 0.70 Wenjun Zeng
  • 2605.26820 #7 · arxiv_oai · confidence 0.70 Wenjun Zeng
  • 2510.22973 #12 · arxiv_oai · confidence 0.70 Wenjun Zeng
  • 2407.21772 #1 · arxiv_oai · confidence 0.70 Wenjun Zeng
  • 2605.17969 #4 · arxiv_oai · confidence 0.70 Wenjun Zeng
  • 2605.17921 #8 · arxiv_oai · confidence 0.70 Wenjun Zeng
  • 2412.18158 #7 · arxiv_oai · confidence 0.70 Wenjun Zeng
  • 2507.04447 #13 · arxiv_oai · confidence 0.70 Wenjun Zeng

Frequent Coauthors