Tang

30

Papers

814

Total Citations

Papers (30)

JudgeBench: A Benchmark for Evaluating LLM-Based Judges

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

WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

Catastrophic Failure of LLM Unlearning via Quantization

CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning

Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

EAS-SNN: End-to-End Adaptive Sampling and Representation for Event-based Detection with Recurrent Spiking Neural Networks

How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension

PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration

Systematic Outliers in Large Language Models

ColorMNet: A Memory-based Deep Spatial-Temporal Feature Propagation Network for Video Colorization

RoboScape: Physics-informed Embodied World Model

NeurIPS 2025arXiv

UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface

NeurIPS 2025arXiv

InstructGIE: Towards Generalizable Image Editing

Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning

ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning

Hessian-Free Online Certified Unlearning

Dataset Growth

LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents

NeurIPS 2025arXiv

TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine

NeurIPS 2025arXiv

MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning

NeurIPS 2025arXiv

LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding

NeurIPS 2025arXiv

Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs

NeurIPS 2025arXiv

EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval

NeurIPS 2025arXiv

Simulating Society Requires Simulating Thought

NeurIPS 2025arXiv

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

NeurIPS 2025arXiv

Robustifying Learning-Augmented Caching Efficiently without Compromising 1-Consistency

NeurIPS 2025arXiv