20 citations · 71 across the 35 of their papers we have counts for
23 papers · 1 filter
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…
Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense
Zhanke Zhou, Bo Han, Xuan Li +3
Graph neural networks (GNNs) are widely deployed on relational data, yet they can leak sensitive or proprietary information about the training graph adjacency, e.g., social ties, t…
Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning
Xuan Li, Zhanke Zhou, Zongze Li +4
Large language models (LLMs) benefit substantially from supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) in reasoning tasks. However, these re…
TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification
Haoyun Jiang, Junqi He, Feng Hong +8
Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and respo…
Per-parameter Task Arithmetic for Unlearning in Large Language Models
Chengyi Cai, Zesheng Ye, Jiangchao Yao +5
In large language model (LLM) unlearning, private information is required to be removed. Task arithmetic unlearns by subtracting a specific task vector (TV)--defined as the paramet…
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…
From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
Zhanke Zhou, Xiao Feng, Zhaocheng Zhu +3
While existing benchmarks probe the reasoning abilities of large language models (LLMs) across diverse domains, they predominantly assess passive reasoning, providing models with a…
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…
Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning
Yuhao Wu, Jiangchao Yao, Bo Han +2
While Positive-Unlabeled (PU) learning is vital in many real-world scenarios, its application to graph data still remains under-explored. We unveil that a critical challenge for PU…
Mitigating Label Noise on Graph via Topological Sample Selection
Yuhao Wu, Jiangchao Yao, Xiaobo Xia +4
Despite the success of the carefully-annotated benchmarks, the effectiveness of existing graph neural networks (GNNs) can be considerably impaired in practice when the real-world g…
Combating Bilateral Edge Noise for Robust Link Prediction
Zhanke Zhou, Jiangchao Yao, Jiaxu Liu +6
Although link prediction on graphs has achieved great success with the development of graph neural networks (GNNs), the potential robustness under the edge noise is still less inve…
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…
Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel
Xuan Li, Zhanke Zhou, Jiangchao Yao +3
Graph Neural Networks (GNNs) have been widely adopted for drug discovery with molecular graphs. Nevertheless, current GNNs mainly excel in leveraging short-range interactions (SRI)…
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…
On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation
Zhanke Zhou, Chenyu Zhou, Xuan Li +3
Although powerful graph neural networks (GNNs) have boosted numerous real-world applications, the potential privacy risk is still underexplored. To close this gap, we perform the f…
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…
Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI
Jiangchao Yao, Shengyu Zhang, Yang Yao +15
Influenced by the great success of deep learning via cloud computing and the rapid development of edge chips, research in artificial intelligence (AI) has shifted to both of the co…
Reliable Adversarial Distillation with Unreliable Teachers
Jianing Zhu, Jiangchao Yao, Bo Han +6
In ordinary distillation, student networks are trained with soft labels (SLs) given by pretrained teacher networks, and students are expected to improve upon teachers since SLs are…
Contrastive Attraction and Contrastive Repulsion for Representation Learning
Huangjie Zheng, Xu Chen, Jiangchao Yao +7
Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative sampl…
Device-Cloud Collaborative Learning for Recommendation
Jiangchao Yao, Feng Wang, KunYang Jia +3
With the rapid development of storage and computing power on mobile devices, it becomes critical and popular to deploy models on devices to save onerous communication latencies and…