Zhimeng Wang

Zhimeng (知萌) is currently forth-year undergrad at Soochow University, advised by Assoc. Prof. Juntao Li and Prof. Min Zhang (ACL Fellow).

His research focuses on the intersection of MLSys and NLP, including Reasoning(Inference-time Scaling), LLM + RL and Long Context LLM.

In 2025, he plans to focus on the following topics:

Long context capabilities of large models: This includes long-context generation, evaluation, inference acceleration (with a focus on MLSys), and long-video understanding.
Advancing RL for LLMs: He aims to address broader challenges beyond alignment. Current RLHF is not true reinforcement learning; methods like Chain-of-Thought, PRM, or Multi-Agent Workflows cannot fully resolve this issue. His goal is to work on developing genuine reinforcement learning for LLMs.

He is eager to collaborate with talented researchers to explore these areas!

news

Sep 20, 2024	A paper (CTD framework) has been accepted to EMNLP2024 🔥 🔥
Nov 07, 2015	A long announcement with details
Oct 22, 2015	A simple inline announcement.

latest posts

Jan 25, 2025
Oct 02, 2024	a post with tabs
May 14, 2024	Google Gemini updates: Flash 1.5, Gemma 2 and Project Astra

selected publications

PhysRev

Can Quantum-Mechanical Description of Physical Reality Be Considered Complete?

A. Einstein^*†, B. Podolsky^*, and N. Rosen^*

Phys. Rev., New Jersey. More Information can be found here , May 1935

Abs HTML PDF Video

In a complete theory there is an element corresponding to each element of reality. A sufficient condition for the reality of a physical quantity is the possibility of predicting it with certainty, without disturbing the system. In quantum mechanics in the case of two physical quantities described by non-commuting operators, the knowledge of one precludes the knowledge of the other. Then either (1) the description of reality given by the wave function in quantum mechanics is not complete or (2) these two quantities cannot have simultaneous reality. Consideration of the problem of making predictions concerning a system on the basis of measurements made on another system that had previously interacted with it leads to the result that if (1) is false then (2) is also false. One is thus led to conclude that the description of reality as given by a wave function is not complete.