PPaperPicks

Di Zhang

Kuaishou Technology, Beijing, China

58 papers at tracked venues · 50 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0009-0006-5475-2728 ↗Homepage ↗

Venues

CVPR ×10ICCV ×8NeurIPS ×8ACL ×7ICLR ×7EMNLP ×6AAAI ×4ICML ×3ACM MM ×2NAACL ×2SIGKDD ×1

Frequent coauthors

Junxian Li
DBLP profile ↗ORCID search ↗
×2
Jie Liu
DBLP profile ↗ORCID search ↗
×2
Longrong Yang
DBLP profile ↗ORCID search ↗
×2
Zhicheng Zhang
DBLP profile ↗ORCID search ↗
×2
Jianhong Bai
DBLP profile ↗ORCID search ↗
×2
Jiao Ou
DBLP profile ↗ORCID search ↗
×2
Yang Jin
DBLP profile ↗ORCID search ↗
×2
Liang Hou
DBLP profile ↗ORCID search ↗
×1
Xiangyang Luo
DBLP profile ↗ORCID search ↗
×1
Yunxiao Wang
DBLP profile ↗ORCID search ↗
×1
Xiao Fu
DBLP profile ↗ORCID search ↗
×1
Haonan He
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Boosting Resolution Generalization of Diffusion Transformers with Randomized Positional Encodings
    AAAI 2026 ·
    Liang Hou
    DBLP profile ↗ORCID search ↗
  2. Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs
    ACL 2026 ·
    Junxian Li
    DBLP profile ↗ORCID search ↗
  3. FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion
    AAAI 2026 ·
    Xiangyang Luo
    DBLP profile ↗ORCID search ↗
  4. TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs
    AAAI 2026 ·
    Yunxiao Wang
    DBLP profile ↗ORCID search ↗
  5. 3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
    ICLR 2025 ·
    Xiao Fu
    DBLP profile ↗ORCID search ↗
  6. Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models
    EMNLP 2025 ·
    Haonan He
    DBLP profile ↗ORCID search ↗
  7. Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control
    ICLR 2025 ·
    Hejia Chen
    DBLP profile ↗ORCID search ↗
  8. ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area
    AAAI 2025 ·
    Junxian Li
    DBLP profile ↗ORCID search ↗
  9. Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
    CVPR 2025 · Di Zhang
  10. DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs
    EMNLP 2025 ·
    Minxuan Lv
    DBLP profile ↗ORCID search ↗
  11. Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models
    NeurIPS 2025 ·
    Wei Chen
    DBLP profile ↗ORCID search ↗
  12. Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization
    NeurIPS 2025 ·
    Tao Zhang
    DBLP profile ↗ORCID search ↗
  13. Flow-GRPO: Training Flow Matching Models via Online RL
    NeurIPS 2025 ·
    Jie Liu
    DBLP profile ↗ORCID search ↗
  14. FullDiT: Video Generative Foundation Models with Multimodal Control via Full Attention
    ICCV 2025 ·
    Xuan Ju
    DBLP profile ↗ORCID search ↗
  15. GGTalker: Talking Head Systhesis with Generalizable Gaussian Priors and Identity-Specific Adaptation
    ICCV 2025 ·
    Wentao Hu
    DBLP profile ↗ORCID search ↗
  16. GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections
    CVPR 2025 ·
    Wei-Qi Feng
    DBLP profile ↗ORCID search ↗
  17. GameFactorly: Creating New Games with Generative Interactive Videos
    ICCV 2025 ·
    Jiwen Yu
    DBLP profile ↗ORCID search ↗
  18. HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models
    ACL 2025 ·
    Xiao Wang
    DBLP profile ↗ORCID search ↗
  19. How Far are AI-Generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approach
    ICCV 2025 ·
    Chirui Chang
    DBLP profile ↗ORCID search ↗
  20. Imbalance in Balance: Online Concept Balancing in Generation Models
    ICCV 2025 ·
    Yukai Shi
    DBLP profile ↗ORCID search ↗
  21. Improving Video Generation with Human Feedback
    NeurIPS 2025 ·
    Jie Liu
    DBLP profile ↗ORCID search ↗
  22. Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content
    CVPR 2025 ·
    Qiuheng Wang
    DBLP profile ↗ORCID search ↗
  23. LLaMA-Berry: Pairwise Optimization for Olympiad-level Mathematical Reasoning via O1-like Monte Carlo Tree Search
    NAACL 2025 · Di Zhang
  24. Libra-Merging: Importance-redundancy and Pruning-merging Trade-off for Acceleration Plug-in in Large Vision-Language Model
    CVPR 2025 ·
    Longrong Yang
    DBLP profile ↗ORCID search ↗
  25. MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
    ICML 2025 ·
    Yifan Zhang
    DBLP profile ↗ORCID search ↗
  26. MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding
    ICML 2025 ·
    Zhicheng Zhang
    DBLP profile ↗ORCID search ↗
  27. MUSE: Multi-Subject Unified Synthesis Via Explicit Layout Semantic Expansion
    ICCV 2025 ·
    Fei Peng
    DBLP profile ↗ORCID search ↗
  28. Mavors: Multi-granularity Video Representation for Multimodal Large Language Model
    ACM MM 2025 ·
    Yang Shi
    DBLP profile ↗ORCID search ↗
  29. OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers
    NeurIPS 2025 ·
    Ziqiao Peng
    DBLP profile ↗ORCID search ↗
  30. PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution
    CVPR 2025 ·
    Shian Du
    DBLP profile ↗ORCID search ↗
  31. Recammaster: Camera-Controlled Generative Rendering From a Single Video
    ICCV 2025 ·
    Jianhong Bai
    DBLP profile ↗ORCID search ↗
  32. Retrieval is Not Enough: Enhancing RAG through Test-Time Critique and Optimization
    NeurIPS 2025 ·
    Jiaqi Wei
    DBLP profile ↗ORCID search ↗
  33. SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin
    EMNLP 2025 ·
    Hao Yi
    DBLP profile ↗ORCID search ↗
  34. Scene Graph Guided Generation: Enable Accurate Relations Generation in Text-to-Image Models via Textural Rectification
    ICCV 2025 ·
    Guibao Shen
    DBLP profile ↗ORCID search ↗
  35. SketchVideo: Sketch-based Video Generation and Editing
    CVPR 2025 ·
    Feng-Lin Liu
    DBLP profile ↗ORCID search ↗
  36. Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model
    ICLR 2025 ·
    Longrong Yang
    DBLP profile ↗ORCID search ↗
  37. Stable Segment Anything Model
    ICLR 2025 ·
    Qi Fan
    DBLP profile ↗ORCID search ↗
  38. StyleMaster: Stylize Your Video with Artistic Generation and Translation
    CVPR 2025 ·
    Zixuan Ye
    DBLP profile ↗ORCID search ↗
  39. SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
    ICLR 2025 ·
    Jianhong Bai
    DBLP profile ↗ORCID search ↗
  40. TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types
    ICLR 2025 ·
    Jiankang Chen
    DBLP profile ↗ORCID search ↗
  41. Towards Precise Scaling Laws for Video Diffusion Transformers
    CVPR 2025 ·
    Yuanyang Yin
    DBLP profile ↗ORCID search ↗
  42. Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulation
    CVPR 2025 ·
    Zhuoman Liu
    DBLP profile ↗ORCID search ↗
  43. VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform
    SIGKDD 2025 ·
    Xingyu Lu
    DBLP profile ↗ORCID search ↗
  44. VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation
    ACL 2025 ·
    Xinlong Chen
    DBLP profile ↗ORCID search ↗
  45. VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models
    NeurIPS 2025 ·
    Zhicheng Zhang
    DBLP profile ↗ORCID search ↗
  46. iMOVE : Instance-Motion-Aware Video Understanding
    ACL 2025 ·
    Jiaze Li
    DBLP profile ↗ORCID search ↗
  47. DialogBench: Evaluating LLMs as Human-like Dialogue Systems
    NAACL 2024 ·
    Jiao Ou
    DBLP profile ↗ORCID search ↗
  48. Evaluating Readability and Faithfulness of Concept-based Explanations
    EMNLP 2024 ·
    Meng Li
    DBLP profile ↗ORCID search ↗
  49. Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint
    ACL 2024 ·
    Zhipeng Chen
    DBLP profile ↗ORCID search ↗
  50. Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues
    EMNLP 2024 ·
    Jiao Ou
    DBLP profile ↗ORCID search ↗
  51. Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios
    ACL 2024 ·
    Lei Lin
    DBLP profile ↗ORCID search ↗
  52. Learning Multi-Dimensional Human Preference for Text-to-Image Generation
    CVPR 2024 ·
    Sixian Zhang
    DBLP profile ↗ORCID search ↗
  53. Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models
    ACL 2024 ·
    Yuchong Sun
    DBLP profile ↗ORCID search ↗
  54. PlacidDreamer: Advancing Harmony in Text-to-3D Generation
    ACM MM 2024 ·
    Shuo Huang
    DBLP profile ↗ORCID search ↗
  55. Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector
    EMNLP 2024 ·
    Xiaoxue Cheng
    DBLP profile ↗ORCID search ↗
  56. Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
    ICLR 2024 ·
    Yang Jin
    DBLP profile ↗ORCID search ↗
  57. Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
    ICML 2024 ·
    Yang Jin
    DBLP profile ↗ORCID search ↗
  58. VideoTetris: Towards Compositional Text-to-Video Generation
    NeurIPS 2024 ·
    Ye Tian
    DBLP profile ↗ORCID search ↗