Yi Yang

Uncertainty-Aware 3D Reconstruction for Dynamic Underwater Scenes

LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization

Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World

Structured Reasoning for LLMs: A Unified Framework for Efficiency and Explainability

Open-Set Semantic Gaussian Splatting SLAM with Expandable Representation

Frequency-aware Dynamic Gaussian Splatting

CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving

Uncertainty-Aware Gaussian Map for Vision-Language Navigation

ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation

MoDE: Weight Denoising Towards Better LLM Performance through a Mixture of Domain Experts

Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective

SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization

Translution: Unifying Self-attention and Convolution for Adaptive and Relative Modeling

Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration

OSCAgent: Closing the Loop in Organic Solar Cell Discovery with LLM Agents

Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models

BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment

Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction

Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data

Dynamic Experts Search: Enhancing Reasoning in Mixture-of-Experts LLMs at Test Time

RegionDoc-R1: Reinforcing Semantic Layout-Aware Learning for Document Understanding

CoMo: Compositional Motion Customization for Text-to-Video Generation

Improving Protein Sequence Design through Designability Preference Optimization

PRICIN: Principle-Centered Inorganic Retrosynthesis

Diffusion-Model Layers May Exhibit Diffusive Behavior at Each Step for Noise Estimation

Hierarchical Speculative Decoding through Training-Free Slim-Verifier

StrucBooth: Structural Gradient Supervised Tuning for Enhanced Portrait Animation

Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer

SparseDiT: Token Sparsification for Efficient Diffusion Transformer

3DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization

DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization

DeltaPhi: Physical States Residual Learning for Neural Operators in Data-Limited PDE Solving

Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration

FlexSelect: Flexible Token Selection for Efficient Long Video Understanding

Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation

Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space

Origin Identification for Text-Guided Image-to-Image Diffusion Models

Reaction Graph: Toward Modeling Chemical Reactions with 3D Molecular Structures

Point-Calibrated Spectral Neural Operators

Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D Structures

Collaborative Hybrid Propagator for Temporal Misalignment in Audio-Visual Segmentation

HYBRID MODEL COLLABORATION FOR SIGN LANGUAGE TRANSLATION WITH VQ-VAE AND RAG ENHANCED LLMS

Generalizable Origin Identification for Text-Guided Image-to-Image Diffusion Models

Open-Ended 3D Metric-Semantic Representation Learning via Semantic-Embedded Gaussian Splatting

Towards Human-like Virtual Beings: Simulating Human Behavior in 3D Scenes

Protecting Copyrighted Material with Unique Identifiers in Large Language Model Training

ProteinAdapter: Adapting Pre-trained Large Protein Models for Efficient Protein Representation Learning