Zhenting Wang
Scholar

Zhenting Wang

Google Scholar ID: QSYVbj8AAAAJ
Accenture; Rutgers University
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,364
 
H-index
20
 
i10-index
28
 
Publications
20
 
Co-authors
0
 
Contact
Emailzt.wang1999@gmail.comTwitterOpen ↗GitHubOpen ↗
Publications
42 items
Beyond Solo and Consistency: Vindicating Multi-Agent Debate via Conditional Progressive Pruning
2026
Cited
0
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
2026
Cited
0
HIVE: Understanding Post-Hallucination Reasoning in Vision Language Models
2026
Cited
0
SLIM-RL: Risk-Budgeted Random-Masking RL for Diffusion LLMs Without Trajectory Slicing
2026
Cited
0
UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation
2026
Cited
0
MemGym: a Long-Horizon Memory Environment for LLM Agents
2026
Cited
0
Evidence Over Plans: Online Trajectory Verification for Skill Distillation
2026
Cited
0
A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models
2026
Cited
0
Resume
Academic Achievements
  • Published multiple papers in 2025, including NeurIPS 2025, ACL 2025, ICML 2025, CVPR 2025, ICLR 2025, and NAACL 2025. Co-organized the Data for Generative Models workshop at ICML 2025.
Research Experience
  • Research scientist intern at GenAI@Meta, and a research intern at Sony AI.
Education
  • Ph.D. in Computer Science Department, Rutgers University, advised by Prof. Shiqing Ma and Prof. Dimitris N. Metaxas.
Background
  • Research Interests: Agentic LLM, Agent Training, LLM Reasoning, and LLM Post-training. Brief Introduction: Currently a senior manager researcher at Accenture, Center for Advanced AI.