Di Zhang

57 papers · 2023–2026 · 12 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (12) 🐝 Cross-Pollinator (7) 🗺️ Taxonomy Completionist (79) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌈 Renaissance Researcher (7) 🏆 Grand Slam 👑 Triple Crown 🤝 Dynamic Duo (20) 🔬 Deep Specialist (11) ⚡ Prolific Year (16) 🚀 Conference Pioneer 🗃️ Keyword Collector (244) 💎 Century Club (54)

Conferences

CVPR (10) EMNLP (8) ICCV (8) ICLR (7) ACL (6) AAAI (4) ICML (4) COLING (3) NIPS (3) NAACL (2) CORL (1) MICCAI (1)

Top co-authors

Pengfei Wan (22) Kun Gai (14) Fuzheng Zhang (12) Xintao Wang (9) Xin Tao (8) Tingting Gao (8) Fan Yang (6) Dongzhan Zhou (4) Chengru Song (4) Menghan Xia (4)

Keywords

large language model (11) video generation (10) diffusion model (9) instruction tuning (5) text-to-video generation (3) reinforcement learning (3) diffusion transformer (3) image generation (3) text-to-image generation (3) preference optimization (3) video diffusion (2) benchmark evaluation (2) multimodal large language model (2) language model (2) temporal coherence (2) gaussian splatting (2) video captioning (2) instruction following (2) prompt engineering (2) video understanding (2)

Papers

TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs AAAI 2026

FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion AAAI 2026

Boosting Resolution Generalization of Diffusion Transformers with Randomized Positional Encodings AAAI 2026

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment ICML 2025

KineDex: Learning Tactile-Informed Visuomotor Policies via Kinesthetic Teaching for Dexterous Manipulation CORL 2025

ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area AAAI 2025

How Far are AI-generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approach ICCV 2025

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video ICCV 2025

GameFactory: Creating New Games with Generative Interactive Videos ICCV 2025

Imbalance in Balance: Online Concept Balancing in Generation Models ICCV 2025

GGTalker: Talking Head Systhesis with Generalizable Gaussian Priors and Identity-Specific Adaptation ICCV 2025

FullDiT: Video Generative Foundation Models with Multimodal Control via Full Attention ICCV 2025

MUSE: Multi-Subject Unified Synthesis via Explicit Layout Semantic Expansion ICCV 2025

Scene Graph Guided Generation: Enable Accurate Relations Generation in Text-to-Image Models via Textural Rectification ICCV 2025

Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model ICLR 2025

TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types ICLR 2025

Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control ICLR 2025

Stable Segment Anything Model ICLR 2025

SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints ICLR 2025

3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation ICLR 2025

MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding ICML 2025

CERTAIN: Context Uncertainty-aware One-Shot Adaptation for Context-based Offline Meta Reinforcement Learning ICML 2025

LLaMA-Berry: Pairwise Optimization for Olympiad-level Mathematical Reasoning via O1-like Monte Carlo Tree Search NAACL 2025

HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models ACL 2025

VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation ACL 2025

iMOVE : Instance-Motion-Aware Video Understanding ACL 2025

Chain-of-Specificity: Enhancing Task-Specific Constraint Adherence in Large Language Models COLING 2025

Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models COLING 2025

SketchVideo: Sketch-based Video Generation and Editing CVPR 2025

StyleMaster: Stylize Your Video with Artistic Generation and Translation CVPR 2025

Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content CVPR 2025

Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning CVPR 2025

PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution CVPR 2025

GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections CVPR 2025

Libra-Merging: Importance-redundancy and Pruning-merging Trade-off for Acceleration Plug-in in Large Vision-Language Model CVPR 2025

Towards Precise Scaling Laws for Video Diffusion Transformers CVPR 2025

Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulation CVPR 2025

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs EMNLP 2025

SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin EMNLP 2025

Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models EMNLP 2025

Focus On What Matters: Separated Models For Visual-Based RL Generalization NIPS 2024

Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint ACL 2024

Hierarchical multiple instance learning for COPD grading with relatively specific similarity MICCAI 2024

Evaluating Readability and Faithfulness of Concept-based Explanations EMNLP 2024

Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector EMNLP 2024

Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs COLING 2024

Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues EMNLP 2024

Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming EMNLP 2024

Learning Multi-Dimensional Human Preference for Text-to-Image Generation CVPR 2024

ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors EMNLP 2024

DialogBench: Evaluating LLMs as Human-like Dialogue Systems NAACL 2024

VideoTetris: Towards Compositional Text-to-Video Generation NIPS 2024

Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization ICML 2024

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization ICLR 2024

Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models ACL 2024

Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios ACL 2024

How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization NIPS 2023