Ji Liu

21

Papers

381

Total Citations

Papers (21)

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

NeurIPS 2025arXiv

FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-Aware Model Update

MindSearch: Mimicking Human Minds Elicits Deep AI Searcher

Training-Free Activation Sparsity in Large Language Models

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites

NeurIPS 2025arXiv

InstructGIE: Towards Generalizable Image Editing

Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Prompts

Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization

Reprojection Errors as Prompts for Efficient Scene Coordinate Regression

Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling

NeurIPS 2025arXiv

On the Convergence of Projected Policy Gradient for Any Constant Step Sizes

NeurIPS 2025arXiv

Stitched ViTs are Flexible Vision Backbones

$\phi$-Update: A Class of Policy Update Methods with Policy Convergence Guarantee

MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs

NeurIPS 2025arXiv

Capability Localization: Capabilities Can be Localized rather than Individual Knowledge

SD-KDE: Score-Debiased Kernel Density Estimation

NeurIPS 2025arXiv

A Generalized Binary Tree Mechanism for Private Approximation of All-Pair Shortest Distances

Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems

NeurIPS 2025arXiv

EGSRAL:An Enhanced 3D Gaussian Splatting Based Renderer with Automated Labeling for Large-Scale Driving Scene

Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation

NeurIPS 2025arXiv