17 citations · 45 across the 14 of their papers we have counts for
16 papers
Markov maps and quasi-conformal deformations associated to geometrically finite Kleinian groups
Shengjin Huo, Wanting Shao
It is known that the dynamical properties of Kleinian groups with parabolic elements are much more complex than those without parabolic elements. In this paper, we mainly study the…
Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking
Yuandong Tian
While the phenomenon of grokking, i.e., delayed generalization, has been studied extensively, it remains an open problem whether there is a mathematical framework that characterize…
Language Self-Play For Data-Free Training
Jakub Grudzien Kuba, Mengting Gu, Qi Ma +3
Large language models (LLMs) have advanced rapidly in recent years, driven by scale, abundant high-quality training data, and reinforcement learning. Yet this progress faces a fund…
SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks
Yifei Zhou, Song Jiang, Yuandong Tian +4
Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks. However, existing multi-turn RL algorithms for optimizing LLM agents fail to perform…
NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions
Weizhe Yuan, Jane Yu, Song Jiang +8
Scaling reasoning capabilities beyond traditional domains such as math and coding is hindered by the lack of diverse and high-quality questions. To overcome this limitation, we int…
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
DiJia Su, Hanlin Zhu, Yingchen Xu +3
Large Language Models (LLMs) excel at reasoning and planning when trained on chainof-thought (CoT) data, where the step-by-step thought process is explicitly outlined by text token…
Towards General-Purpose Model-Free Reinforcement Learning
Scott Fujimoto, Pierluca D'Oro, Amy Zhang +2
Reinforcement learning (RL) promises a framework for near-universal problem-solving. In practice however, RL algorithms are often tailored to specific benchmarks, relying on carefu…
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
Yen-Ting Lin, Di Jin, Tengyu Xu +11
Large language models (LLMs) have recently demonstrated remarkable success in mathematical reasoning. Despite progress in methods like chain-of-thought prompting and self-consisten…
Training Large Language Models to Reason in a Continuous Latent Space
Shibo Hao, Sainbayar Sukhbaatar, DiJia Su +4
Large language models (LLMs) are typically constrained to reason in the language space, where they express the reasoning process through a chain-of-thought (CoT) to solve complex p…
Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
DiJia Su, Sainbayar Sukhbaatar, Michael Rabbat +2
In cognition theory, human thinking is governed by two systems: the fast and intuitive System 1 and the slower but more deliberative System 2. Analogously, Large Language Models (L…
Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets
Yuandong Tian
We prove rich algebraic structures of the solution space for 2-layer neural networks with quadratic activation and loss, trained on reasoning tasks in Abelian group (e.g., mo…
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
Tianhao Wu, Weizhe Yuan, Olga Golovneva +5
Large Language Models (LLMs) are rapidly surpassing human knowledge in many domains. While improving these models traditionally relies on costly human data, recent self-rewarding m…
Holding the Line: A Study of Writers' Attitudes on Co-creativity with AI
Morteza Behrooz, Yuandong Tian, William Ngan +3
Generative AI has put many professional writers on the defensive; a major negotiation point of the recent Writers Guild of America's strike concerned use of AI. However, must AI th…
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
Lucas Lehnert, Sainbayar Sukhbaatar, DiJia Su +4
While Transformers have enabled tremendous progress in various application settings, such architectures still trail behind traditional symbolic planners for solving complex decisio…
TravelPlanner: A Benchmark for Real-World Planning with Language Agents
Jian Xie, Kai Zhang, Jiangjie Chen +5
Planning has been part of the core pursuit for artificial intelligence since its conception, but earlier AI agents mostly focused on constrained settings because many of the cognit…
H-GAP: Humanoid Control with a Generalist Planner
Zhengyao Jiang, Yingchen Xu, Nolan Wagener +5
Humanoid control is an important research challenge offering avenues for integration into human-centric infrastructures and enabling physics-driven humanoid animations. The dauntin…