18 citations · 36 across the 21 of their papers we have counts for
21 papers
MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning
Guanglong Sun, Kanglei Zhou, Liyuan Wang +6
General continual learning (GCL) aims to learn from evolving data streams without task identities, explicit boundaries, or repeated access to previous data, making it a realistic y…
ComMem: Complementary Memory Systems for Test-Time Adaptation of Vision-Language Models
Guanglong Sun, Shuang Cui, Bo Lei +6
Test-time adaptation (TTA) of vision-language models (VLMs) is essential for their robust deployment in dynamic, real-world environments. However, existing TTA methods often adapt…
Dummy-Aware Weighted Attack (DAWA): Breaking the Safe Sink in Dummy Class Defenses
Yunrui Yu, Xuxiang Feng, Pengda Qin +5
Adversarial robustness evaluation faces a critical challenge as new defense paradigms emerge that can exploit limitations in existing assessment methods. This paper reveals that Du…
Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness
Yunrui Yu, Hang Su, Jun Zhu
This work investigates the critical role of activation function curvature -- quantified by the maximum second derivative -- in adversarial robustness. Using the Recursi…
Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving
Chang Su, Zhongkai Hao, Zhizhou Zhang +4
Large language models (LLMs) with reasoning abilities have demonstrated growing promise for tackling complex scientific problems. Yet such tasks are inherently domain-specific, unb…
MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning
Guanglong Sun, Hongwei Yan, Liyuan Wang +5
To cope with uncertain changes of the external world, intelligent systems must continually learn from complex, evolving environments and respond in real time. This ability, collect…
Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
Guanglong Sun, Siyuan Zhang, Liyuan Wang +3
Safety post-training can improve the harmfulness and policy compliance of Large Language Models (LLMs), but it may also reduce general utility, a phenomenon often described as the…
Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environments
Xiao Yang, Lingxuan Wu, Lizhong Wang +3
Adversarial attacks in 3D environments have emerged as a critical threat to the reliability of visual perception systems, particularly in safety-sensitive applications such as iden…
AnyPos: Automated Task-Agnostic Actions for Bimanual Manipulation
Hengkai Tan, Yao Feng, Xinyi Mao +5
Learning generalizable manipulation policies hinges on data, yet robot manipulation data is scarce and often entangled with specific embodiments, making both cross-task and cross-p…
Self-Consistent Model-based Adaptation for Visual Reinforcement Learning
Xinning Zhou, Chengyang Ying, Yao Feng +2
Visual reinforcement learning agents typically face serious performance declines in real-world applications caused by visual distractions. Existing methods rely on fine-tuning the…
Exploratory Diffusion Model for Unsupervised Reinforcement Learning
Chengyang Ying, Huayu Chen, Xinning Zhou +3
Unsupervised reinforcement learning (URL) aims to pre-train agents by exploring diverse states or skills in reward-free environments, facilitating efficient adaptation to downstrea…
MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue
Fengxiang Wang, Ranjie Duan, Peng Xiao +9
Large Language Models (LLMs) demonstrate outstanding performance in their reservoir of knowledge and understanding capabilities, but they have also been shown to be prone to illega…
ManiBox: Enhancing Embodied Spatial Generalization via Scalable Simulation Data Generations
Hengkai Tan, Xuezhou Xu, Chengyang Ying +7
Embodied agents require robust spatial intelligence to execute precise real-world manipulations. However, this remains a significant challenge, as current methods often struggle to…
HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning
Liyuan Wang, Jingyi Xie, Xingxing Zhang +2
The deployment of pre-trained models (PTMs) has greatly advanced the field of continual learning (CL), enabling positive knowledge transfer and resilience to catastrophic forgettin…
Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning
Hengkai Tan, Songming Liu, Kai Ma +4
Transformer has shown promise in reinforcement learning to model time-varying features for obtaining generalized low-level robot policies on diverse robotics datasets in embodied l…
PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
Chengyang Ying, Zhongkai Hao, Xinning Zhou +4
Designing generalizable agents capable of adapting to diverse embodiments has achieved significant attention in Reinforcement Learning (RL), which is critical for deploying RL agen…
LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents
Shilong Liu, Hao Cheng, Haotian Liu +10
LLaVA-Plus is a general-purpose multimodal assistant that expands the capabilities of large multimodal models. It maintains a skill repository of pre-trained vision and vision-lang…
Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation
Yilin Lyu, Liyuan Wang, Xingxing Zhang +4
Continual learning entails learning a sequence of tasks and balancing their knowledge appropriately. With limited access to old training samples, much of the current work in deep n…
Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality
Liyuan Wang, Jingyi Xie, Xingxing Zhang +3
Prompt-based continual learning is an emerging direction in leveraging pre-trained knowledge for downstream continual learning, and has almost reached the performance pinnacle unde…
Towards a General Framework for Continual Learning with Pre-training
Liyuan Wang, Jingyi Xie, Xingxing Zhang +2
In this work, we present a general framework for continual learning of sequentially arrived tasks with the use of pre-training, which has emerged as a promising direction for artif…
Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk
Chengyang Ying, Xinning Zhou, Hang Su +3
Though deep reinforcement learning (DRL) has obtained substantial success, it may encounter catastrophic failures due to the intrinsic uncertainty of both transition and observatio…