3 citations · 3 across the 9 of their papers we have counts for
10 papers
Agentic Transformers Provably Learn to Search via Reinforcement Learning
Tong Yang, Yu Huang, Yingbin Liang +1
Tree search is a central abstraction behind many language-agent reasoning and decision-making tasks: agents must explore actions, remember failures, and backtrack toward promising…
ConvexBench: Can LLMs Recognize Convex Functions?
Yepeng Liu, Yu Huang, Yu-Xiang Wang +2
Convex analysis is a modern branch of mathematics with many applications. As Large Language Models (LLMs) start to automate research-level math and sciences, it is important for LL…
On the Emergence of Implicit Curriculum in RLVR Learning Dynamics
Yu Huang, Zixin Wen, Yuejie Chi +4
Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mystery how rewards based solely on…
Transformers Provably Learn Directed Acyclic Graphs via Kernel-Guided Mutual Information
Yuan Cheng, Yu Huang, Zhe Xiong +2
Uncovering hidden graph structures underlying real-world data is a critical challenge with broad applications across scientific domains. Recently, transformer-based models leveragi…
Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
Tong Yang, Yu Huang, Yingbin Liang +1
Transformers have demonstrated remarkable capabilities in multi-step reasoning tasks. However, understandings of the underlying mechanisms by which they acquire these abilities thr…
In-Context Learning with Representations: Contextual Generalization of Trained Transformers
Tong Yang, Yu Huang, Yingbin Liang +1
In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoreti…
A Theoretical Analysis of Self-Supervised Learning for Vision Transformers
Yu Huang, Zixin Wen, Yuejie Chi +1
Self-supervised learning has become a cornerstone in computer vision, primarily divided into reconstruction-based methods like masked autoencoders (MAE) and discriminative methods…
Sample Complexity Characterization for Linear Contextual MDPs
Junze Deng, Yuan Cheng, Shaofeng Zou +1
Contextual Markov decision processes (CMDPs) describe a class of reinforcement learning problems in which the transition kernels and reward functions can change over time with diff…
Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes
Ruiquan Huang, Yuan Cheng, Jing Yang +2
In multi-task reinforcement learning (RL) under Markov decision processes (MDPs), the presence of shared latent structures among multiple MDPs has been shown to yield significant b…
In-Context Convergence of Transformers
Yu Huang, Yuan Cheng, Yingbin Liang
Transformers have recently revolutionized many domains in modern machine learning and one salient discovery is their remarkable in-context learning capability, where models can sol…