31 citations · 95 across the 27 of their papers we have counts for
28 papers
Dream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems
Boxuan Zhang, Jianing Zhu, jianing Zhu +2
Reliable deployment of LLM-based multi-agent systems calls for runtime auditors that predict terminal outcomes from observed execution prefixes. These auditors typically learn from…
Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement
Xutao Mao, Jianing Zhu, Jinman Zhao +4
Reinforcement learning (RL) has substantially improved the reasoning capabilities of vision-language models (VLMs), yet it can induce chain-of-thought (CoT) obfuscation, an operati…
Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling
Xinmu Ge, Zizhuo Zhang, Yu Huang +9
On-policy distillation (OPD) has emerged as a promising post-training technique for enhancing LLM reasoning. Under the reverse KL objective, the idealized optimum of OPD aligns the…
POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking
Zhangheng LI, Jianing Zhu, Junyuan Hong +4
Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on cross-modal tasks by jointly training on large-scale textual and visual data, where privacy-sen…
Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
Jianing Zhu, Yeonju Ro, John Robertson +5
Long-lived AI agents are increasingly deployed as persistent operational systems, yet they are still evaluated like freshly initialized models. Day-one benchmarks miss a basic syst…
AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
Jingwei Sun, Jianing Zhu, Yuanyi Li +3
Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-w…
When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search
John T. Robertson, Jianing Zhu, Haris Vikalo +1
Activation steering offers a lightweight way to control LLMs without retraining, but its effectiveness varies sharply across concepts. Prior work often reads this variability as ev…
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
Jingwei Sun, Jianing Zhu, Jiangchao Yao +2
To enable reliable long-term interaction, LLM agents require a memory system that can faithfully store, efficiently retrieve, and deeply reason over accumulated dialogue history. M…
AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
Boxuan Zhang, Jianing Zhu, Zeru Shi +2
LLM-based multi-agent systems are increasingly deployed on long-horizon tasks, but a single decisive error is often accepted by downstream agents and cascades into trajectory-level…
Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts
Boxuan Zhang, Jianing Zhu, Qifan Wang +2
Recent generative models can produce images that appear highly realistic, raising challenges in distinguishing real and AI-generated images. Yet existing detectors based on pre-tra…
Belief Memory: Agent Memory Under Partial Observability
Junfeng Liao, Qizhou Wang, Jianing Zhu +3
LLM agents that operate over long context depend on external memory to accumulate knowledge over time. However, existing methods typically store each observation as a single determ…
Towards Understanding Valuable Preference Data for Large Language Model Alignment
Zizhuo Zhang, Qizhou Wang, Shanshan Ye +4
Large language model (LLM) alignment is typically achieved through learning from human preference comparisons, making the quality of preference data critical to its success. Existi…
Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models
Zizhuo Zhang, Jianing Zhu, Xinmu Ge +6
While reinforcement learning with verifiable rewards (RLVR) is effective to improve the reasoning ability of large language models (LLMs), its reliance on human-annotated labels le…
Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
Geng Yu, Jianing Zhu, Jiangchao Yao +1
Out-of-distribution (OOD) detection is crucial for deploying reliable machine learning models in open-world applications. Recent advances in CLIP-based OOD detection have shown pro…
Model Inversion Attacks: A Survey of Approaches and Countermeasures
Zhanke Zhou, Jianing Zhu, Fengfei Yu +4
Deep neural networks have enabled numerous studies and applications on both Euclidean data, such as images and text, and non-Euclidean data, such as graphs. Because these networks…
Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?
Zhanke Zhou, Rong Tao, Jianing Zhu +3
This paper investigates an under-explored challenge in large language models (LLMs): chain-of-thought prompting with noisy rationales, which include irrelevant or inaccurate reason…
What If the Input is Expanded in OOD Detection?
Boxuan Zhang, Jianing Zhu, Zengmao Wang +3
Out-of-distribution (OOD) detection aims to identify OOD inputs from unknown classes, which is important for the reliable deployment of machine learning models in the open world. V…
Decoupling the Class Label and the Target Concept in Machine Unlearning
Jianing Zhu, Bo Han, Jiangchao Yao +3
Machine unlearning as an emerging research topic for data regulations, aims to adjust a trained model to approximate a retrained one that excludes a portion of training data. Previ…
Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
Qizhou Wang, Bo Han, Puning Yang +3
The imperative to eliminate undesirable data memorization underscores the significance of machine unlearning for large language models (LLMs). Recent research has introduced a seri…
DeepInception: Hypnotize Large Language Model to Be Jailbreaker
Xuan Li, Zhanke Zhou, Jianing Zhu +3
Large language models (LLMs) have succeeded significantly in various applications but remain susceptible to adversarial jailbreaks that void their safety guardrails. Previous attem…
Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation
Jianing Zhu, Geng Yu, Jiangchao Yao +4
Out-of-distribution (OOD) detection is important for deploying reliable machine learning models on real-world applications. Recent advances in outlier exposure have shown promising…
Exploring Model Dynamics for Accumulative Poisoning Discovery
Jianing Zhu, Xiawei Guo, Jiangchao Yao +6
Adversarial poisoning attacks pose huge threats to various machine learning applications. Especially, the recent accumulative poisoning attacks show that it is possible to achieve…
Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability
Jianing Zhu, Hengzhuang Li, Jiangchao Yao +3
Out-of-distribution (OOD) detection is an indispensable aspect of secure AI when deploying machine learning models in real-world applications. Previous paradigms either explore bet…
Combating Exacerbated Heterogeneity for Robust Models in Federated Learning
Jianing Zhu, Jiangchao Yao, Tongliang Liu +3
Privacy and security concerns in real-world applications have led to the development of adversarially robust federated models. However, the straightforward combination between adve…