Lune

Profiles2019-2026

Zhaoxiang Zhang

University of Chinese Academy of Sciences

68Papers
35Last author
137Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers68

  1. DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous DrivingAuthor 13 of 13ICLR 2026 · 134 citations
  2. Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and MethodAuthor 12 of 13ICLR 2026 · 45 citations
  3. Uniform Discrete Diffusion with Metric Path for Video GenerationAuthor 10 of 11ICLR 2026 · 12 citations
  4. DynVLA: Learning World Dynamics for Action Reasoning in Autonomous DrivingAuthor 11 of 12ICML 2026 · 8 citations
  5. DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous DrivingAuthor 5 of 5NeurIPS 2025 · 49 citations
  6. Activation Steering Decoding: Mitigating Hallucination in Large Vision-Language Models through Bidirectional Hidden State InterventionAuthor 6 of 6ACL 2025 · 24 citations
  7. SceneX: Procedural Controllable Large-Scale Scene GenerationAuthor 8 of 8AAAI 2025 · 22 citations
  8. TC-Light: Temporally Coherent Generative Rendering for Realistic World TransferAuthor 9 of 9NeurIPS 2025 · 12 citations
  9. Ross3d: Reconstructive Visual Instruction Tuning With 3D-AwarenessAuthor 6 of 9ICCV 2025 · 7 citations
  10. FIRM: Flexible Interactive Reflection ReMovalAuthor 7 of 7AAAI 2025 · 5 citations
  11. C2KD: Cross-layer and Cross-head Knowledge Distillation for Small Language Model-based RecommendationAuthor 4 of 5ACL Findings 2025 · 3 citations
  12. CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale ScenesAuthor 5 of 5ICLR 2025 · 3 citations
  13. LayerAnimate: Layer-Level Control for AnimationAuthor 5 of 5ICCV 2025 · 3 citations
  14. AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMsAuthor 6 of 6ACL 2025
  15. FreeSim: Toward Free-viewpoint Camera Simulation in Driving ScenesAuthor 5 of 8CVPR 2025
  16. FreeVS: Generative View Synthesis on Free Driving TrajectoryAuthor 5 of 5ICLR 2025
  17. Reconstructive Visual Instruction TuningAuthor 7 of 7ICLR 2025
  18. MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object DetectionAuthor 3 of 3ICLR 2024 · 11 citations
  19. Enhancing Visual Continual Learning with Language-Guided SupervisionAuthor 6 of 7CVPR 2024 · 8 citations
  20. RCL: Reliable Continual Learning for Unified Failure DetectionAuthor 5 of 5CVPR 2024 · 5 citations
  21. MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D AssetsAuthor 10 of 18ACM MM 2024 · 4 citations
  22. VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector QuantizationAuthor 6 of 8NeurIPS 2024 · 3 citations
  23. Continual Forgetting for Pre-Trained Vision ModelsAuthor 7 of 7CVPR 2024
  24. HardMo: A Large-Scale Hardcase Dataset for Motion CaptureAuthor 7 of 8CVPR 2024
  25. SheetCopilot: Bringing Software Productivity to the Next Level through Large Language ModelsAuthor 5 of 5NeurIPS 2023 · 75 citations
  26. FPR: False Positive Rectification for Weakly Supervised Semantic SegmentationAuthor 5 of 6ICCV 2023 · 65 citations
  27. Fairly Adaptive Negative Sampling for RecommendationsAuthor 6 of 7WWW 2023 · 64 citations
  28. Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality FusionAuthor 4 of 4NeurIPS 2023 · 48 citations
  29. DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action LocalizationAuthor 4 of 6ICCV 2023 · 16 citations
  30. Informative Data Mining for One-shot Cross-Domain Semantic SegmentationAuthor 6 of 6ICCV 2023 · 12 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines