Yuan

33

Papers

629

Total Citations

Papers (33)

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

NeurIPS 2025arXiv

MoBA: Mixture of Block Attention for Long-Context LLMs

NeurIPS 2025arXiv

ImgEdit: A Unified Image Editing Dataset and Benchmark

NeurIPS 2025arXiv

MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences

GVGEN: Text-to-3D Generation with Volumetric Representation

HiFi-123: Towards High-fidelity One Image to 3D Content Generation

GTP-4o: Modality-prompted Heterogeneous Graph Learning for Omni-modal Biomedical Representation

Boosting Neural Combinatorial Optimization for Large-Scale Vehicle Routing Problems

Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation

CLIFF: Continual Latent Diffusion for Open-Vocabulary Object Detection

InstantSplamp: Fast and Generalizable Stenography Framework for Generative Gaussian Splatting

DreamDiffusion: High-Quality EEG-to-Image Generation with Temporal Masked Signal Modeling and CLIP Alignment

IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation

Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs

VideoMAR: Autoregressive Video Generation with Continuous Tokens

LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory

NeurIPS 2025arXiv

IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt Learning

IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning

The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition

NeurIPS 2025arXiv

Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model

The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training

NeurIPS 2025arXiv

LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models

NeurIPS 2025arXiv

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks

Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning

NeurIPS 2025arXiv

RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills

NeurIPS 2025arXiv

SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought

NeurIPS 2025arXiv

Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images

MoORE: SVD-based Model MoE-ization for Conflict- and Oblivion-Resistant Multi-Task Adaptation

NeurIPS 2025arXiv

Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling

NeurIPS 2025arXiv

Multi-Granularity Sparse Relationship Matrix Prediction Network for End-to-End Scene Graph Generation

Forecasting Future Videos from Novel Views via Disentangled 3D Scene Representation

MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization

NeurIPS 2025arXiv

FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning

NeurIPS 2025arXiv