14 citations · 72 across the 41 of their papers we have counts for
48 papers
RAC: A Relational Agent Contract for Constraint-Governed Engineering Tasks
Kaiyuan Zheng, Fengqing Jiang, Yichen Feng +6
Engineering agents must produce artifacts that satisfy exact, coupled constraints. Existing solutions often require agents to make semantic decisions and also derive consequences s…
TAPDreamer: Transferable Adversarial Patches for World Action Models
Xuanyu Lu, Fengqing Jiang, Kaiyuan Zheng +8
World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world action models depend on camera i…
JobBench: Aligning Agent Work With Human Will
Yuetai Li, Yichen Feng, Zhangchen Xu +21
Current benchmarks for occupational AI agents are scoped primarily by economic values, telling a replacement story. We introduce JobBench, which evaluates AI agents on the workflow…
Polyhedral Instability Governs Regret in Online Learning
Yuetai Li, Fengqing Jiang, Yichen Feng +6
Many online decision problems over combinatorial actions are addressed via convex relaxations, leading to online convex optimization with piecewise linear objectives and induced po…
The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks
Fengqing Jiang, Yuetai Li, Yichen Feng +6
Hypergraphs provide a natural framework to model higher-order interactions in scientific, social, and biological systems. Hypergraph neural networks (HGNNs) aim to learn from such…
Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?
Yichen Feng, Yuetai Li, Chunjiang Liu +14
Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of these applications require an expl…
Distributed Safety-Critical Control of Multi-Agent Systems with Time-Varying Communication Topologies
Shiyu Cheng, Luyao Niu, Bhaskar Ramasubramanian +2
Coordinating multiple autonomous agents to reach a target region while avoiding collisions and maintaining communication connectivity is a core problem in multi-agent systems. In p…
BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?
Fengqing Jiang, Yichen Feng, Yuetai Li +3
The convergence of LLM-powered research assistants and AI-based peer review systems creates a critical vulnerability: fully automated publication loops where AI-generated research…
Swarm-STL: A Framework for Motion Planning in Large-Scale, Multi-Swarm Systems
Shiyu Cheng, Luyao Niu, Bhaskar Ramasubramanian +2
In multi-agent systems, signal temporal logic (STL) is widely used for path planning to accomplish complex objectives with formal safety guarantees. However, as the number of agent…
VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL
Yichen Feng, Zhangchen Xu, Fengqing Jiang +5
Vision language models (VLMs) are expected to perform effective multimodal reasoning and make logically coherent decisions, which is critical to tasks such as diagram understanding…
Temporal Sampling for Forgotten Reasoning in LLMs
Yuetai Li, Zhangchen Xu, Fengqing Jiang +5
Fine-tuning large language models (LLMs) is intended to improve their reasoning capabilities, yet we uncover a counterintuitive effect: models often forget how to solve problems th…
TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
Zhangchen Xu, Yuetai Li, Fengqing Jiang +4
Reinforcement Learning (RL) has become a powerful tool for enhancing the reasoning abilities of large language models (LLMs) by optimizing their policies with reward signals. Yet,…
SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
Fengqing Jiang, Fengbo Ma, Zhangchen Xu +8
Large language models (LLMs) exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particul…
SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
Fengqing Jiang, Zhangchen Xu, Yuetai Li +5
Emerging large reasoning models (LRMs), such as DeepSeek-R1 models, leverage long chain-of-thought (CoT) reasoning to generate structured intermediate steps, enhancing their reason…
Small Models Struggle to Learn from Strong Reasoners
Yuetai Li, Xiang Yue, Zhangchen Xu +5
Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting…
Modeling and Designing Non-Pharmaceutical Interventions in Epidemics: A Submodular Approach
Shiyu Cheng, Luyao Niu, Bhaskar Ramasubramanian +2
This paper considers the problem of designing non-pharmaceutical intervention (NPI) strategies, such as masking and social distancing, to slow the spread of a viral epidemic. We fo…
Stronger Models are NOT Stronger Teachers for Instruction Tuning
Zhangchen Xu, Fengqing Jiang, Luyao Niu +2
Instruction tuning has been widely adopted to ensure large language models (LLMs) follow user instructions effectively. The resulting instruction-following capabilities of LLMs hea…
Who is Responsible? Explaining Safety Violations in Multi-Agent Cyber-Physical Systems
Luyao Niu, Hongchao Zhang, Dinuka Sahabandu +3
Multi-agent cyber-physical systems are present in a variety of applications. Agent decision-making can be affected due to errors induced by uncertain, dynamic operating environment…
ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning
Zhangchen Xu, Fengqing Jiang, Luyao Niu +3
In Federated Learning (FL), a set of clients collaboratively train a machine learning model (called global model) without sharing their local training data. The local training data…
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates
Fengqing Jiang, Zhangchen Xu, Luyao Niu +2
Large language models (LLMs) are expected to follow instructions from users and engage in conversations. Techniques to enhance LLMs' instruction-following capabilities typically fi…
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
Zhangchen Xu, Fengqing Jiang, Luyao Niu +4
High-quality instruction data is critical for aligning large language models (LLMs). Although some models, such as Llama-3-Instruct, have open weights, their alignment data remain…
Fault Tolerant Neural Control Barrier Functions for Robotic Systems under Sensor Faults and Attacks
Hongchao Zhang, Luyao Niu, Andrew Clark +1
Safety is a fundamental requirement of many robotic systems. Control barrier function (CBF)-based approaches have been proposed to guarantee the safety of robotic systems. However,…
Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors
Dinuka Sahabandu, Xiaojun Xu, Arezoo Rajabi +4
We propose and analyze an adaptive adversary that can retrain a Trojaned DNN and is also aware of SOTA output-based Trojaned model detectors. We show that such an adversary can ens…
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
Fengqing Jiang, Zhangchen Xu, Luyao Niu +4
Safety is critical to the usage of large language models (LLMs). Multiple techniques such as data filtering and supervised fine-tuning have been developed to strengthen LLM safety.…