8 citations · 22 across the 24 of their papers we have counts for
26 papers
AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?
Zhangchen Xu, Junda Chen, Yue Huang +16
Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifac…
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…
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…
NARRA-Gym for Evaluating Interactive Narrative Agents
Yue Huang, Yuchen Ma, Jiayi Ye +14
Interactive narrative tasks require LLMs to sustain a coherent, evolving story while adapting to a user over multiple turns. However, suitable benchmarks for this setting are limit…
Emergent Risks in Generative Multi-Agent Systems
Yue Huang, Yu Jiang, Wenjie Wang +12
Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jointly plan, negotiate, and allocate sh…
PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory
Bowen Jiang, Yuan Yuan, Maohao Shen +13
Personalization is one of the next milestones in advancing AI capability and alignment. We introduce PersonaMem-v2, the state-of-the-art dataset for LLM personalization that simula…
Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
Yue Huang, Hang Hua, Yujun Zhou +11
While LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm, since certain risks can lead to…
TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
Zhangchen Xu, Adriana Meza Soria, Shawn Tan +4
Large Language Model (LLM) agents are rapidly emerging as powerful systems for automating tasks across domains. Yet progress in the open-source community is constrained by the lack…
Steering Multimodal Large Language Models Decoding for Context-Aware Safety
Zheyuan Liu, Zhangchen Xu, Guangyao Dou +4
Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet their ability to make context-aware safety decisions remains limited. Existing me…
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…
KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding
Zhangchen Xu, Yang Liu, Yueqin Yin +2
We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for tr…
Distributed Consensus Network: A Modularized Communication Framework and Reliability Probabilistic Analysis
Yuetai Li, Zhangchen Xu, Yiqi Wang +3
In this paper, we propose a modularized framework for communication processes applicable to crash and Byzantine fault-tolerant consensus protocols. We abstract basic communication…
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…
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…
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…
CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models
Yuetai Li, Zhangchen Xu, Fengqing Jiang +4
The remarkable performance of large language models (LLMs) in generation tasks has enabled practitioners to leverage publicly available models to power custom applications, such as…
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…
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.…
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
Zhangchen Xu, Fengqing Jiang, Luyao Niu +3
As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to alig…