Wei Ye
- Papers
- 22
Cite
Notes
Only stored in your browser.
Authored papers
22ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
arXiv 2026
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
arXiv 2026
A Comprehensive Survey on Long Context Language Modeling
arXiv 2025
Reverse-Engineered Reasoning for Open-Ended Generation
arXiv 2025
TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them
arXiv 2025
RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors
ICCV 2025
RewardAnything: Generalizable Principle-Following Reward Models
arXiv 2025
CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians
arXiv 2024
CoderUJB: An Executable and Unified Java Benchmark for Practical Programming Scenarios
arXiv 2024
Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation
arXiv 2024
AutoSurvey: Large Language Models Can Automatically Write Surveys
arXiv 2024
RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
arXiv 2024
SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization
CVPR 2025 1
FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models
arXiv 2024
MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models
arXiv 2023
A Survey on Evaluation of Large Language Models
arXiv 2023
TiMix: Text-aware Image Mixing for Effective Vision-Language Pre-training
arXiv 2023
PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
arXiv 2023
Supervised Knowledge Makes Large Language Models Better In-context Learners
arXiv 2023
Consistent Direct Time-of-Flight Video Depth Super-Resolution
CVPR 2023 1
USB: A Unified Semi-supervised Learning Benchmark for Classification
arXiv 2022
SongMASS: Automatic Song Writing with Pre-training and Alignment Constraint
arXiv 2020
Affiliations
Frequent co-authors
10from 22 papers