24 papers
EgoAlign: Situated 3D Understanding without Situation Descriptions
Yiyang Li, Tianyi Ma, Zehong Wang +1
Situated 3D Question Answering requires models to interpret a 3D scene relative to an agent's pose. Existing methods commonly convey that pose through a natural-language situation…
The Collaboration Tax: How Much LLM Multi-Agent Systems Pay to Coordinate
Weixiang Sun, Zehong Wang, Hong Huang +3
Multi-agent systems built from large language models are deployed widely, yet how much performance is lost when two LLMs must coordinate rather than act alone remains unclear. We f…
Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning
Zheyuan Zhang, Manqing Mao, Hong Wang +8
Critic-free group-based reinforcement learning has become a scalable approach for post-training large language models. However, most existing methods allocate the same number of ro…
HoosierHelp: Benchmarking LLM Agents for Social Service Navigation
Yiyang Li, Weixiang Sun, Tianyi Ma +3
Social service navigation requires connecting help-seeking individuals to resources that satisfy their needs and specific constraints. Although LLM agents offer a promising interfa…
Object-Centric Environment Modeling for Agentic Tasks
Yiyang Li, Tianyi Ma, Zehong Wang +2
Large language model (LLM) agents can improve through accumulated experience, but free-form textual memories become difficult to maintain, validate, and reuse as interactions grow.…
SupraBench: A Benchmark for Supramolecular Chemistry
Tianyi Ma, Yijun Ma, Zehong Wang +6
Supramolecular chemistry, which includes the study of non-covalent host-guest assemblies, has advanced various applications. However, designing host-guest systems remains time-cons…
MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback
Zehong Wang, Yijun Ma, Connor R. Schmidt +7
Molecular dynamics (MD) is the canonical in-silico method for atomistic molecular science, simulating molecular behavior from first-principle physics. Designing an MD pipeline for…
ProPlay: Procedural World Models for Self-Evolving LLM Agents
Yijun Ma, Zehong Wang, Yiyang Li +5
Self-evolving agents are expected to improve through interaction without external supervision, but this remains difficult in partially observable environments where agents must exp…
SAGE: Answer-Conditioned Uncertainty Targets for Verbal Uncertainty Alignment
Kaiwen Shi, Zheyuan Zhang, Yanfang Ye
Large language models increasingly express uncertainty through natural-language statements, yet these expressions often fail to reflect the model's sampled behavior. We study verba…
Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization
Zheyuan Zhang, Kaiwen Shi, Han Bao +3
Post-training has become central to improving reasoning and alignment in large language models, where critic-free models enable scalable learning from model-generated outputs but l…
GRID: Graph Representation of Intelligence Data for Security Text Knowledge Graph Construction
Liangyi Huang, Zichen Liu, Fei Shao +5
Security knowledge graphs can provide computable external memory for security agents, but constructing them from long-form cyber threat intelligence (CTI) remains difficult: LLMs o…
Hypergraph Pattern Machine: Compositional Tokenization for Higher-Order Interactions
Kyrie Zhao, Zehong Wang, Tianyi Ma +5
Hypergraphs model higher-order relations that drive real-world decisions, from drug prescriptions to recommendations. A central structural signal in such data, beyond what pairwise…
PreScam: A Benchmark for Predicting Scam Progression from Early Conversations
Weixiang Sun, Shang Ma, Yiyang Li +5
Conversational scams, such as romance and investment scams, are emerging as a major form of online fraud. Unlike one-shot scam lures such as fake lottery or unpaid toll messages, t…
EvoTaxo: Building and Evolving Taxonomy from Social Media Streams
Yiyang Li, Tianyi Ma, Yanfang Ye
Constructing taxonomies from social media corpora is challenging because posts are short, noisy, semantically entangled, and temporally dynamic. Existing taxonomy induction methods…
A Survey of Weight Space Learning: Understanding, Representation, and Generation
Xiaolong Han, Zehong Wang, Bo Zhao +8
Neural network weights are typically viewed as the end product of training, while most deep learning research focuses on data, features, and architectures. However, recent advances…
BHyGNN+: Unsupervised Representation Learning for Heterophilic Hypergraphs
Tianyi Ma, Yiyue Qian, Zehong Wang +3
Hypergraph Neural Networks (HyGNNs) have demonstrated remarkable success in modeling higher-order relationships among entities. However, their performance often degrades on heterop…
OPBench: A Graph Benchmark to Combat the Opioid Crisis
Tianyi Ma, Yiyang Li, Yiyue Qian +4
The opioid epidemic continues to ravage communities worldwide, straining healthcare systems, disrupting families, and demanding urgent computational solutions. To combat this letha…
AI Alignment Breaks at the Edge
Han Bao, Yue Huang, Xiaoda Wang +5
General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that mode…
Policy4OOD: A Knowledge-Guided World Model for Policy Intervention Simulation against the Opioid Overdose Crisis
Yijun Ma, Zehong Wang, Weixiang Sun +4
The opioid epidemic remains one of the most severe public health crises in the United States, yet evaluating policy interventions before implementation is difficult: multiple polic…
Molecular Representations in Implicit Functional Space via Hyper-Networks
Zehong Wang, Xiaolong Han, Qi Yang +10
Molecular representations fundamentally shape how machine learning systems reason about molecular structure and physical properties. Most existing approaches adopt a discrete pipel…
Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents
Zehong Wang, Fang Wu, Hongru Wang +8
Large language model (LLM)-based agents exhibit strong step-by-step reasoning capabilities over short horizons, yet often fail to sustain coherent behavior over long planning horiz…
Temporal Graph Pattern Machine
Yijun Ma, Zehong Wang, Weixiang Sun +1
Temporal graph learning is pivotal for deciphering dynamic systems, where the core challenge lies in explicitly modeling the underlying evolving patterns that govern network transf…
Graph is a Substrate Across Data Modalities
Ziming Li, Xiaoming Wu, Zehong Wang +6
Graphs provide a natural representation of relational structure that arises across diverse domains. Despite this ubiquity, graph structure is typically learned in a modality- and t…
LLMs4All: A Review of Large Language Models Across Academic Disciplines
Yanfang Ye, Zheyuan Zhang, Tianyi Ma +26
Cutting-edge Artificial Intelligence (AI) techniques keep reshaping our view of the world. For example, Large Language Models (LLMs) based applications such as ChatGPT have shown t…