papers

Publications (31)

q-bio.BM2025

Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows

Xiangxin Zhou, Yi Xiao, Haowei Lin +7

The dynamic nature of proteins, influenced by ligand interactions, is essential for comprehending protein function and progressing drug discovery. Traditional structure-based drug…

math.CO2026

Settling the Optimal Exponent Relating Sumsets and Difference Sets

Haowei Lin, Shanda Li

The authors construct explicit finite subsets of the integers showing that the exponent 1/2 in the classical sum‑difference inequality cannot be improved, proving it is optimal.

#additive combinatorics#sumsets#difference sets#extremal combinatorics
cs.SE2026

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini +82

AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not…

cs.LG2024

Class Incremental Learning via Likelihood Ratio Based Task Prediction

Haowei Lin, Yijia Shao, Weinan Qian +3

Class incremental learning (CIL) is a challenging setting of continual learning, which learns a series of tasks sequentially. Each task consists of a set of unique classes. The key…

cs.LG2024

Selecting Large Language Model to Fine-tune via Rectified Scaling Law

Haowei Lin, Baizhou Huang, Haotian Ye +7

The ever-growing ecosystem of LLMs has posed a challenge in selecting the most appropriate pre-trained model to fine-tune amidst a sea of options. Given constrained resources, fine…

cs.CL2023

Continual Pre-training of Language Models

Zixuan Ke, Yijia Shao, Haowei Lin +3

Language models (LMs) have been instrumental for the rapid advance of natural language processing. This paper studies continual pre-training of LMs, in particular, continual domain…

cs.CL2025

Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models

Haotian Ye, Himanshu Jain, Chong You +4

In real-world applications of large language models, outputs are often required to be confined: selecting items from predefined product or document sets, generating phrases that co…

cs.AI2024

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents

Shaofei Cai, Bowei Zhang, Zihao Wang +4

Developing agents that can follow multimodal instructions remains a fundamental challenge in robotics and AI. Although large-scale pre-training on unlabeled datasets (no language i…

cs.LG2024

TFG: Unified Training-Free Guidance for Diffusion Models

Haotian Ye, Haowei Lin, Jiaqi Han +6

Given an unconditional diffusion model and a predictor for a target property of interest (e.g., a classifier), the goal of training-free guidance is to generate samples with desira…

cs.LG2023

FLatS: Principled Out-of-Distribution Detection with Feature-Based Likelihood Ratio Score

Haowei Lin, Yuntian Gu

Detecting out-of-distribution (OOD) instances is crucial for NLP models in practical applications. Although numerous OOD detection methods exist, most of them are empirical. Backed…

cs.LG2026

Can Language Models Discover Scaling Laws?

Haowei Lin, Haotian Ye, Wenzheng Feng +8

Discovering scaling laws for predicting model performance at scale is a fundamental and open-ended challenge, mostly reliant on slow, case specific human experimentation. To invest…

cs.CL2025

Generative Evaluation of Complex Reasoning in Large Language Models

Haowei Lin, Xiangyu Wang, Ruilin Yan +7

With powerful large language models (LLMs) demonstrating superhuman reasoning capabilities, a critical question arises: Do LLMs genuinely reason, or do they merely recall answers f…

cs.LG2026

Structured Scaling of AI Discovery Across Diverse Scientific Domains

Haotian Ye, Haowei Lin, Jingyi Tang +30

Scientific discovery often requires many cycles of proposing, testing, and refining candidate solutions. Language models can increasingly participate in these loops, but simply gen…

cs.AI2026

Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies

Guangyu Zhao, Kewei Lian, Haoxuan Ru +8

Goal-conditioned policies enable decision-making models to execute diverse behaviors based on specified goals, yet their downstream performance is often highly sensitive to the cho…

cs.LG2025

TFG-Flow: Training-free Guidance in Multimodal Generative Flow

Haowei Lin, Shanda Li, Haotian Ye +4

Given an unconditional generative model and a predictor for a target property (e.g., a classifier), the goal of training-free guidance is to generate samples with desirable target…

cs.AI2026

SceneActBench: Can Agents Act on the 3D Scenes They See?

Yifei Zhao, Xiangxin Zhou, Wenhao Yang +11

Vision-language model (VLM) agents increasingly use tools to act on 3D scenes rather than only describe them. Existing 3D benchmarks score textual responses or single-object operat…

cs.LG2025

Unified Cross-Scale 3D Generation and Understanding via Autoregressive Modeling

Shuqi Lu, Haowei Lin, Lin Yao +6

3D structure modeling is essential across scales, enabling applications from fluid simulation and 3D reconstruction to protein folding and molecular docking. Yet, despite shared 3D…

cs.AI2026

Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft

Zhou Ziheng, Huacong Tang, Jinyuan Zhang +9

Discovering causal regularities and applying them to build functional systems--the discovery-to-application loop--is a hallmark of general intelligence, yet evaluating this capacit…

cs.CL2024

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation

Zihao Wang, Anji Liu, Haowei Lin +3

We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-…

cs.LG2025

Peptide2Mol: A Diffusion Model for Generating Small Molecules as Peptide Mimics for Targeted Protein Binding

Xinheng He, Yijia Zhang, Haowei Lin +4

Structure-based drug design has seen significant advancements with the integration of artificial intelligence (AI), particularly in the generation of hit and lead compounds. Howeve…

cs.LG2025

Inference-time Scaling of Diffusion Models through Classical Search

Xiangcheng Zhang, Haowei Lin, Haotian Ye +4

Classical search algorithms have long underpinned modern artificial intelligence. In this work, we tackle the challenge of inference-time control in diffusion models -- adapting ge…

cs.LG2024

CLoG: Benchmarking Continual Learning of Image Generation Models

Haotian Zhang, Junting Zhou, Haowei Lin +6

Continual Learning (CL) poses a significant challenge in Artificial Intelligence, aiming to mirror the human ability to incrementally acquire knowledge and skills. While extensive…

cs.AI2023

JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models

Zihao Wang, Shaofei Cai, Anji Liu +9

Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents. Existing approaches can handle cer…

cs.AI2025

MCU: An Evaluation Framework for Open-Ended Game Agents

Xinyue Zheng, Haowei Lin, Kaichen He +3

Developing AI agents capable of interacting with open-world environments to solve diverse tasks is a compelling challenge. However, evaluating such open-ended agents remains diffic…

math.DG2026

Sub-Finslerian Interpolation Inequalities

Haowei Lin

In this paper, we prove that forward ideal sub-Finslerian manifolds support interpolation inequalities for optimal transport, extending the results of Barilari and Rizzi, arXiv:170…

astro-ph.SR2025

A Neural Symbolic Model for Space Physics

Jie Ying, Haowei Lin, Chao Yue +7

In this study, we unveil a new AI model, termed PhyE2E, to discover physical formulas through symbolic regression. PhyE2E simplifies symbolic regression by decomposing it into sub-…

cs.SE2026

UniCode: Augmenting Evaluation for Code Reasoning

Xinyue Zheng, Haowei Lin, Shaofei Cai +3

The paper presents UniCode, a generative evaluation framework that augments seed coding problems and automatically generates tests to more rigorously assess large language models'…

#code reasoning#large language model evaluation#problem augmentation#automated test generation
cs.CL2023

Adapting a Language Model While Preserving its General Knowledge

Zixuan Ke, Yijia Shao, Haowei Lin +3

Domain-adaptive pre-training (or DA-training for short), also known as post-training, aims to train a pre-trained general-purpose language model (LM) using an unlabeled corpus of a…

cs.CL2022

Continual Training of Language Models for Few-Shot Learning

Zixuan Ke, Haowei Lin, Yijia Shao +3

Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications. Adapting or posttraining an LM using an unlabeled domain corpus can pr…

cs.LG2024

OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents

Zihao Wang, Shaofei Cai, Zhancun Mu +7

This paper presents OmniJARVIS, a novel Vision-Language-Action (VLA) model for open-world instruction-following agents in Minecraft. Compared to prior works that either emit textua…

cs.LG2026

Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection

Sijie Li, Shanda Li, Haowei Lin +3

Scaling laws are used to plan multi-million-dollar training runs, but fitting those laws can itself cost millions. In modern large-scale workflows, assembling a sufficiently inform…