6 citations · 17 across the 9 of their papers we have counts for
12 papers
The Layer Mystery of VLA: An Information-Theoretical Analysis of VLA Latent Interface
Yuxiang Liu, Lizhi Yang, Fengze Xie +2
Vision-language-action (VLA) policies connect a pretrained vision-language backbone to an action head through a latent interface, but which backbone layers this interface should ex…
TDRM: Smooth Reward Models with Temporal Difference for LLM RL and Inference
Dan Zhang, Min Cai, Jonathan Light +3
Reward models are central to both reinforcement learning (RL) with language models and inference-time verification. However, existing reward models often lack temporal consistency,…
CLEVER: A Curated Benchmark for Formally Verified Code Generation
Amitayush Thakur, Jasper Lee, George Tsoukalas +6
We introduce , a high-quality, curated benchmark of 161 problems for end-to-end verified code generation in Lean. Each problem consists of (1) the task of ge…
Self-Evolving Visual Concept Library using Vision-Language Critics
Atharva Sehgal, Patrick Yuan, Ziniu Hu +3
We study the problem of building a visual concept library for visual recognition. Building effective visual concept libraries is challenging, as manual definition is labor-intensiv…
DataSciBench: An LLM Agent Benchmark for Data Science
Dan Zhang, Sining Zhoubian, Min Cai +7
This paper presents DataSciBench, a comprehensive benchmark for evaluating Large Language Model (LLM) capabilities in data science. Recent related benchmarks have primarily focused…
PIANIST: Learning Partially Observable World Models with LLMs for Multi-Agent Decision Making
Jonathan Light, Sixue Xing, Yuanzhe Liu +7
Effective extraction of the world knowledge in LLMs for complex decision-making tasks remains a challenge. We propose a framework PIANIST for decomposing the world model into seven…
Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search
Jonathan Light, Min Cai, Weiqin Chen +5
Traditional reinforcement learning and planning typically requires vast amounts of data and training to develop effective policies. In contrast, large language models (LLMs) exhibi…
ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
Dan Zhang, Sining Zhoubian, Ziniu Hu +3
Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low…
Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller
Min Cai, Yuchen Zhang, Shichang Zhang +5
We propose SelfControl, an inference-time model control method utilizing gradients to control the behavior of large language models (LLMs) without explicit human annotations. Given…
SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code
Ziniu Hu, Ahmet Iscen, Aashi Jain +5
This paper introduces SceneCraft, a Large Language Model (LLM) Agent converting text descriptions into Blender-executable Python scripts which render complex scenes with up to a hu…
Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion
Yujia Huang, Adishree Ghatare, Yuanzhe Liu +6
We study the problem of symbolic music generation (e.g., generating piano rolls), with a technical focus on non-differentiable rule guidance. Musical rules are often expressed in s…
SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models
Dan Zhang, Ziniu Hu, Sining Zhoubian +6
Large Language Models (LLMs) have shown promise in assisting scientific discovery. However, such applications are currently limited by LLMs' deficiencies in understanding intricate…