Yasheng Wang

Huawei Technologies (China) — China

Computer Science · Physical Sciences

20h-index1.3kcitations139works0.42yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(76), Natural Language Processing Techniques(52), Speech and dialogue systems(24), Software Engineering Research(13), Adversarial Robustness in Machine Learning(10)

Publications139 total

ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction
ArXiv.org·2025Open Access
Fast, Slow, and Tool-augmented Thinking for LLMs: A Review
arXiv (Cornell University)·2025Open Access
Dynamic data selection with normalized gradient-based influence approximation for targeted fine-tuning of LLMs
Knowledge-Based Systems·2025
ReliableMath: Benchmark of Reliable Mathematical Reasoning on Large Language Models
arXiv (Cornell University)·2025Open Access
QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
arXiv (Cornell University)·2025Open Access
Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?
arXiv (Cornell University)·2025Open Access
Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
arXiv (Cornell University)·2025Open Access
EssayBench: Evaluating Large Language Models in Multi-Genre Chinese Essay Writing
arXiv (Cornell University)·2025Open Access
KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs
arXiv (Cornell University)·2025Open Access
Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering
ArXiv.org·2025Open Access
ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution
arXiv (Cornell University)·2025Open Access
Advancing and Benchmarking Personalized Tool Invocation for LLMs
arXiv (Cornell University)·2025Open Access
DAST: Difficulty-Aware Self-Training on Large Language Models
arXiv (Cornell University)·2025Open Access
DocPuzzle: A Process-Aware Benchmark for Evaluating Realistic Long-Context Reasoning Capabilities
arXiv (Cornell University)·2025Open Access
Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger
arXiv (Cornell University)·2025Open Access
Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge
arXiv (Cornell University)·2025Open Access
Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving
arXiv (Cornell University)·2025Open Access
ACEBench: Who Wins the Match Point in Tool Usage?
arXiv (Cornell University)·2025Open Access
Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger
2025· 1 citedOpen Access
page 1 of 7Next →

Frequent Co-authors

Qun Liu(24), Fei Mi(17), Xin Jiang(13), Xin Jiang(11), Fanchao Qi(10), Zhiyuan Liu(10), Maosong Sun(10), Yitong Li(10), Zhengyan Zhang(8), Pingyi Zhou(5), Minlie Huang(4), Qun Liu(3), Ruifen Hu(3), Zhiyuan Luo(3), Chenglei Si(3), Xin Wang(3), Jin Liu(3), Hao Wu(3), Zhengkun Zhang(3), Zhenglu Yang(3)