activity
20242026
collaborators

6 papers

cs.LG2026

FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics

Qiran Zou, Hou Hei Lam, Wenhao Zhao +11

AI research agents accelerate ML research by automating hypothesis generation, experimentation, and empirical refinement. Existing agent strategies range from greedy hill-climbing…

cs.LG2026

Mitigating Premature Discretization with Progressive Quantization for Robust Vector Tokenization

Wenhao Zhao, Qiran Zou, Zhouhan Lin +1

Vector Quantization (VQ) has become the cornerstone of tokenization for many multimodal Large Language Models and diffusion synthesis. However, existing VQ paradigms suffer from a…

cs.LG2026

Early Quantization Shrinks Codebook: A Simple Fix for Diversity-Preserving Tokenization

Wenhao Zhao, Qiran Zou, Rushi Shah +3

Vector quantization is a technique in machine learning that discretizes continuous representations into a set of discrete vectors. It is widely employed in tokenizing data represen…

cs.CL2026

FML-bench: Benchmarking Machine Learning Agents for Scientific Research

Qiran Zou, Hou Hei Lam, Wenhao Zhao +7

Large language models (LLMs) have sparked growing interest in machine learning research agents that can autonomously propose ideas and conduct experiments. However, existing benchm…

cs.LG2025

Deconstructing Generative Diversity: An Information Bottleneck Analysis of Discrete Latent Generative Models

Yudi Wu, Wenhao Zhao, Dianbo Liu

Generative diversity varies significantly across discrete latent generative models such as AR, MIM, and Diffusion. We propose a diagnostic framework, grounded in Information Bottle…

cs.LG2024

Representation Collapsing Problems in Vector Quantization

Wenhao Zhao, Qiran Zou, Rushi Shah +1

Vector quantization is a technique in machine learning that discretizes continuous representations into a set of discrete vectors. It is widely employed in tokenizing data represen…