YU LI

23

Papers

392

Total Citations

Papers (23)

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

NeurIPS 2025arXiv

IRSAM: Advancing Segment Anything Model for Infrared Small Target Detection

SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration

ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning

NeurIPS 2025arXiv

CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction

RoboScape: Physics-informed Embodied World Model

NeurIPS 2025arXiv

MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems

NeurIPS 2025arXiv

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness

NeurIPS 2025arXiv

Divergence-enhanced Knowledge-guided Context Optimization for Visual-Language Prompt Tuning

Text-Anchored Score Composition: Tackling Condition Misalignment in Text-to-Image Diffusion Models

Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning

NeurIPS 2025arXiv

ECHOPulse: ECG Controlled Echocardio-gram Video Generation

Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions

AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees

NeurIPS 2025arXiv

GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization

NeurIPS 2025arXiv

TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration

NeurIPS 2025arXiv

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

NeurIPS 2025arXiv

ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting

NeurIPS 2025arXiv

AmorLIP: Efficient Language-Image Pretraining via Amortization

NeurIPS 2025arXiv

Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data

CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts

Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders

NeurIPS 2025arXiv

Accident Anticipation via Temporal Occurrence Prediction

NeurIPS 2025arXiv