2 citations · 7 across the 19 of their papers we have counts for
20 papers
CrashGym: Measuring the Decision Value of Experimentation for LLM Agents in Counterfactual Market Crashes
Haocheng Lu, Haoxuan Cheng, Mingyang Chen +1
Language-model agents are increasingly asked to run experiments, yet benchmarks rarely measure whether those experiments improve the decisions they are meant to inform. We introduc…
DeepInstructor: An Agentic AI Instructor for Experience-Driven Idea Evaluation
Rongcan Pei, Fang Guo, Qinglin Qi +7
As automated scientific discovery advances, Large Language Models (LLMs) can now generate research ideas at an unprecedented scale, shifting the bottleneck from idea generation to…
SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts
Yuan Xin, Yixuan Weng, Minjun Zhu +5
As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial hidden prompts, i.e., adversarial instructions embedded in…
SafeAgent: A Runtime Protection Architecture for Agentic Systems
Hailin Liu, Eugene Ilyushin, Jie Ni +1
Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-ou…
DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Review
Yixuan Weng, Minjun Zhu, Qiujie Xie +7
Automated peer review is often framed as generating fluent critique, yet reviewers and area chairs need judgments they can \emph{audit}: where a concern applies, what evidence supp…
AutoFigure-Edit: Generating Editable Scientific Illustration
Zhen Lin, Qiujie Xie, Minjun Zhu +10
High-quality scientific illustrations are essential for communicating complex scientific and technical concepts, yet existing automated systems remain limited in editability, styli…
AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations
Minjun Zhu, Zhen Lin, Yixuan Weng +6
High-quality scientific illustrations are crucial for effectively communicating complex scientific and technical concepts, yet their manual creation remains a well-recognized bottl…
Hard Negative Sample-Augmented DPO Post-Training for Small Language Models
Haocheng Lu, Minjun Zhu, Henry Yu
Large language models (LLMs) continue to struggle with mathematical reasoning, and common post-training pipelines often reduce each generated solution to a binary outcome: correct…
Deep Research: A Systematic Survey
Zhengliang Shi, Yiqun Chen, Haitao Li +23
Large language models (LLMs) have rapidly evolved from text generators into powerful problem solvers. Yet, many open tasks demand critical thinking, multi-source, and verifiable ou…
DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively
Yixuan Weng, Minjun Zhu, Qiujie Xie +4
While previous AI Scientist systems can generate novel findings, they often lack the focus to produce scientifically valuable contributions that address pressing human-defined chal…
Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systems
Alva West, Yixuan Weng, Minjun Zhu +3
Failure attribution in multi-agent systems -- pinpointing the exact step where a decisive error occurs -- is a critical yet unsolved challenge. Current methods treat this as a patt…
AI-Generated Text is Non-Stationary: Detection via Temporal Tomography
Alva West, Yixuan Weng, Minjun Zhu +4
The field of AI-generated text detection has evolved from supervised classification to zero-shot statistical analysis. However, current approaches share a fundamental limitation: t…
How Far Are AI Scientists from Changing the World?
Qiujie Xie, Yixuan Weng, Minjun Zhu +9
The emergence of large language models (LLMs) is propelling automated scientific discovery to the next level, with LLM-based Artificial Intelligence (AI) Scientist systems now taki…
T-Detect: Tail-Aware Statistical Normalization for Robust Detection of Adversarial Machine-Generated Text
Alva West, Luodan Zhang, Liuliu Zhang +3
Large language models (LLMs) have shown the capability to generate fluent and logical content, presenting significant challenges to machine-generated text detection, particularly t…
AI Scientists Fail Without Strong Implementation Capability
Minjun Zhu, Qiujie Xie, Yixuan Weng +4
The emergence of Artificial Intelligence (AI) Scientist represents a paradigm shift in scientific discovery, with large language models (LLMs) taking the lead as the primary execut…
DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process
Minjun Zhu, Yixuan Weng, Linyi Yang +1
Large Language Models (LLMs) are increasingly utilized in scientific research assessment, particularly in automated paper review. However, existing LLM-based review systems face si…
Constrain Alignment with Sparse Autoencoders
Qingyu Yin, Chak Tou Leong, Minjun Zhu +7
The alignment of large language models (LLMs) with human preferences remains a key challenge. While post-training techniques like Reinforcement Learning from Human Feedback (RLHF)…
CycleResearcher: Improving Automated Research via Automated Review
Yixuan Weng, Minjun Zhu, Guangsheng Bao +4
The automation of scientific discovery has been a long-standing goal within the research community, driven by the potential to accelerate knowledge creation. While significant prog…
Locking Down the Finetuned LLMs Safety
Minjun Zhu, Linyi Yang, Yifan Wei +2
Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, whic…
Personality Alignment of Large Language Models
Minjun Zhu, Yixuan Weng, Linyi Yang +1
Aligning large language models (LLMs) typically aim to reflect general human values and behaviors, but they often fail to capture the unique characteristics and preferences of indi…