13 papers
The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
Martin J. Wainwright
We study masking diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the \emph{unmasking growth complexity} ({\textsf{UGC}\xspace}). Its l…
Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers
Tianyi Li, Zhiqiang Shen
Linear mode connectivity (LMC) provides a promising foundation for understanding and merging independently trained neural networks, but existing methods typically optimize the inte…
A Survey on Diffusion Language Models
Tianyi Li, Mingda Chen, Bowei Guo +1
Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through…
CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency
Jiacheng Guo, Suozhi Huang, Zixin Yao +16
This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorously evaluate the real-world capabilities of Large Language Model (LLM) agents in t…
Dataset-Level Metrics Attenuate Non-Determinism: A Fine-Grained Non-Determinism Evaluation in Diffusion Language Models
Zhengyu Fang, Zhimeng Jiang, Huiyuan Chen +5
Diffusion language models (DLMs) have emerged as a promising paradigm for large language models (LLMs), yet the non-deterministic behavior of DLMs remains poorly understood. The ex…
Tracing Prompt-Level Trajectories to Understand Student Learning with AI in Programming Education
Tianyu Shao, Miguel Feijóo-GarcÃa, Yi Zhang +4
As AI tools such as ChatGPT enter programming classrooms, students encounter differing rules across courses and instructors, which shape how they use AI and leave them with unequal…