Yu Wang

49

Papers

563

Total Citations

1

Affiliations

Affiliations

University of California, San Diego

Papers (49)

Knowledge Graph Prompting for Multi-Document Question Answering

Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector

ParCo: Part-Coordinating Text-to-Motion Synthesis

MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization

V2Meow: Meowing to the Visual Beat via Video-to-Music Generation

FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models

PrPSeg: Universal Proposition Learning for Panoramic Renal Pathology Segmentation

Exploring Diverse Representations for Open Set Recognition

KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling

Every Node Is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering

ASIGN: An Anatomy-aware Spatial Imputation Graphic Network for 3D Spatial Transcriptomics

Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning

MBQ: Modality-Balanced Quantization for Large Vision-Language Models

ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning

NeurIPS 2025arXiv

DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers

Towards Trustworthy Knowledge Graph Reasoning: An Uncertainty Aware Perspective

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

NeurIPS 2025arXiv

When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach

Holistic Semantic Representation for Navigational Trajectory Generation

AnyTalk: Multi-modal Driven Multi-domain Talking Head Generation

Take the Bull by the Horns: Learning to Segment Hard Samples

PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction

DLFR-Gen: Diffusion-based Video Generation with Dynamic Latent Frame Rate

Probabilistic Prompt Distribution Learning for Animal Pose Estimation

DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image

SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion

Reducing Class-wise Confusion for Incremental Learning with Disentangled Manifolds

Continual SFT Matches Multimodal RLHF with Negative Supervision

Rethinking the Upsampling Process in Light Field Super-Resolution with Spatial-Epipolar Implicit Image Function

Long-Tailed Classification with Multi-Granularity Semantics

HoliTracer: Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery

Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models

Zero-Sum vs. Positive-Sum: Effects of Inter-team Competition Modes and Haptic Feedback on Team Flow in Multi-team VR

SuperJunction: Learning-Based Junction Detection for Retinal Image Registration

Semi-supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach

Self-Updatable Large Language Models by Integrating Context into Model Parameters

Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning

FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models

H2GFormer: Horizontal-to-Global Voxel Transformer for 3D Semantic Scene Completion

Enhancing Contrastive Learning Inspired by the Philosophy of “The Blind Men and the Elephant”

Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding

Interaction-based Retrieval-augmented Diffusion Models for Protein-specific 3D Molecule Generation

MEMORYLLM: Towards Self-Updatable Large Language Models

Position: Towards Implicit Prompt For Text-To-Image Models

Socialized Learning: Making Each Other Better Through Multi-Agent Collaboration

Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game

Evaluating Quantized Large Language Models

Open-Set Graph Domain Adaptation via Separate Domain Alignment

High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data Sampling