0

Yasheng Wang

Papers
20

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
20papers

Authored papers

20

Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents

arXiv 2026

2026

ACEBench: Who Wins the Match Point in Tool Learning?

arXiv 2025

2025

Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?

arXiv 2025

2025

Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering

arXiv 2025

2025

Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification

arXiv 2025

2025

Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving

arXiv 2025

2025

Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge

arXiv 2025

2025

QFFT, Question-Free Fine-Tuning for Adaptive Reasoning

arXiv 2025

2025

Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction

arXiv 2025

2025

SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation

arXiv 2024

2024

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance

arXiv 2024

2024

CoIR: A Comprehensive Benchmark for Code Information Retrieval Models

arXiv 2024

2024

Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios

arXiv 2024

2024

PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models

arXiv 2024

2024

Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization

arXiv 2024

2024

Learning Evolving Tools for Large Language Models

arXiv 2024

2024

PanGu-Coder: Program Synthesis with Function-Level Language Modeling

arXiv 2022

2022

MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions

arXiv 2022

2022

Sub-Character Tokenization for Chinese Pretrained Language Models

arXiv 2021

2021

Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger

ACL 2021 5

2021

Affiliations

No known affiliations.

Frequent co-authors

10

from 20 papers