← Search

Zhenyu Hou

12 accepted papers

2025

A Survey of Post-Training Scaling in Large Language Models

ACL 2025long

Large language models (LLMs) have achieved remarkable proficiency in understanding and generating human natural languages, mainly owing to the “scaling law” that optimizes relationships among language modeling loss, model parameters, and pre-trained tokens. However, with the exhaustion of high-quali…

Cited by 0SourcePDFScholar
2025

Controlling Large Language Model with Latent Action

ICML 2025poster

Adapting Large Language Models (LLMs) to downstream tasks using Reinforcement Learning (RL) has proven to be an effective approach. However, LLMs do not inherently define the structure of an agent for RL training, particularly in terms of specifying the action space. This paper studies learning a co…

Cited by 0SourcePDFScholar
2025

LongReward: Improving Long-context Large Language Models with AI Feedback

ACL 2025long

Though significant advancements have been achieved in developing long-context large language models (LLMs), the compromised quality of LLM-synthesized data for supervised fine-tuning (SFT) often affects the long-context performance of SFT models and leads to inherent limitations. In principle, reinf…

2025

Multimodal Neural Machine Translation: A Survey of the State of the Art

EMNLP 2025

Multimodal neural machine translation (MNMT) has received increasing attention due to its widespread applications in various fields such as cross-border e-commerce and cross-border social media platforms. The task aims to integrate other modalities, such as the visual modality, with textual data to

Cited by 0SourcePDFScholar
2025

Real-time Spatial-temporal Traversability Assessment via Feature-based Sparse Gaussian Process

IROS 2025

Terrain analysis is critical for the practical application of ground mobile robots in real-world tasks, especially in outdoor unstructured environments. In this paper, we propose a novel spatial-temporal traversability assessment method, which aims to enable autonomous robots to effectively navigate

Cited by 4SourcecodeScholar
2025

SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling

ACL 2025finding

Large language models (LLMs) have advanced rapidly from conversational problem solving to addressing real-world tasks involving tool use, such as software engineering (SWE). Recent LLM-powered toolkits, such as OpenAI Codex and Cursor, have offered end-to-end automation of the software development p…

2025

SceneGenAgent: Precise Industrial Scene Generation with Coding Agent

ACL 2025long

The modeling of industrial scenes is essential for simulations in industrial manufacturing. While large language models (LLMs) have shown significant progress in generating general 3D scenes from textual descriptions, generating industrial scenes with LLMs poses a unique challenge due to their deman…

2025

T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

ICML 2025poster

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, existing approaches mainly rely on imitation learning and struggle to achieve effective test-time scaling. While reinforcement learning (RL) holds promise for enabling self-exploration, recent…

2025

TreeRL: LLM Reinforcement Learning with On-Policy Tree Search

ACL 2025long

Reinforcement learning (RL) with tree search has demonstrated superior performance in traditional reasoning tasks. Compared to conventional independent chain sampling strategies with outcome supervision, tree search enables better exploration of the reasoning space and provides dense, on-policy proc…

2024

ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline

EMNLP 2024finding

Large language models (LLMs) have shown excellent mastering of human language but still struggle in real-world applications that require mathematical problem-solving. While many strategies and datasets to enhance LLMs’ mathematics are developed, it remains a challenge to simultaneously maintain and…

2023

MTDiag: An Effective Multi-Task Framework for Automatic Diagnosis

AAAI 2023technical

Automatic diagnosis systems aim to probe for symptoms (i.e., symptom checking) and diagnose disease through multi-turn conversations with patients. Most previous works formulate it as a sequential decision process and use reinforcement learning (RL) to decide whether to inquire about symptoms or mak…

Cited by 8SourcePDFScholar