Jiaqi Wang

Beyond Fixed: Training-Free Variable-Length Denoising for Diffusion Large Language Models

STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence

Visual Self-Refine: A Pixel-Guided Paradigm for Accurate Chart Parsing

SIM-CoT: Supervised Implicit Chain-of-Thought

DiCache: Let Diffusion Model Determine Its Own Cache

Advancing Complex Video Object Segmentation via Progressive Concept Construction

Diffusion Fine-Tuning: Iterative Refinement for Advanced Grounding with Diffusion Large Language Models

GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models

DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies

ScaleCap: Scalable Image Captioning via Dual-Modality Debiasing

CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

GeometryZero: Advancing LLM Geometry Solving via Group Contrastive Policy Optimization

CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization

Unified Reward Model for Multimodal Understanding and Generation

RLFR: Extending Reinforcement Learning for LLMs with Flow Environment

$\text{G}^2$RPO: Granular GRPO for Precise Reward in Flow Models

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better

Edit-then-Consolidate for Reliable Knowledge Editing

SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience

SPARK: Synergistic Policy And Reward Co-Evolving Framework

Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition

Tri-Factor Saliency: A Low-Dimensional Representation for Efficient and Diversity-Aware Video Token Pruning

BoostStep: Boosting Mathematical Capability of Large Language Models via Step-aligned In Context Learning

Adaptive Fast-and-Slow Visual Program Reasoning for Long-Form VideoQA

VideoRoPE: What Makes for Good Video Rotary Position Embedding?

HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance

IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations

Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning

MotionClone: Training-Free Motion Cloning for Controllable Video Generation

RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition

SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate

SAM2Long: Enhancing SAM2 for Long Video Segmentation with a Training-Free Memory Tree

Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images

DualFocus: Integrating Macro and Micro Perspectives in Multi-modal Large Language Models

SongComposer: A Large Language Model for Lyric and Melody Composition in Song Generation

BroadWay: Boost Your Text-to-Video Generation Model in a Training-free Way

Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data

PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction