Yu

25

Papers

396

Total Citations

Papers (25)

VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?

MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

NeurIPS 2025arXiv

RRM: Robust Reward Model Training Mitigates Reward Hacking

Can LLMs Understand Time Series Anomalies?

KGGen: Extracting Knowledge Graphs from Plain Text with Language Models

NeurIPS 2025arXiv

MoonCast: High-Quality Zero-Shot Podcast Generation

NeurIPS 2025arXiv

SimulPL: Aligning Human Preferences in Simultaneous Machine Translation

Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection

CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching

NeurIPS 2025arXiv

Pose-Aware Self-Supervised Learning with Viewpoint Trajectory Regularization

Discovering Influential Neuron Path in Vision Transformers

Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control

NeurIPS 2025arXiv

Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics

NeurIPS 2025arXiv

OAT: Object-Level Attention Transformer for Gaze Scanpath Prediction

Rethinking Residual Distribution in Locate-then-Edit Model Editing

NeurIPS 2025arXiv

PolyhedronNet: Representation Learning for Polyhedra with Surface-attributed Graph

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression

NeurIPS 2025arXiv

ViewCraft3D: High-fidelity and View-Consistent 3D Vector Graphics Synthesis

NeurIPS 2025arXiv

Unifying Proportional Fairness in Centroid and Non-Centroid Clustering

NeurIPS 2025arXiv

Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance

Revealing Multimodal Causality with Large Language Models

NeurIPS 2025arXiv

Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery

NeurIPS 2025arXiv

Simulating Society Requires Simulating Thought

NeurIPS 2025arXiv

Resolution Attack: Exploiting Image Compression to Deceive Deep Neural Networks