English
Related papers

Related papers: Activation Space Interventions Can Be Transferred …

200 papers

Embodied AI requires agents that perceive, act, and anticipate how actions reshape future world states. World models serve as internal simulators that capture environment dynamics, enabling forward and counterfactual rollouts to support…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Xinqing Li , Xin He , Le Zhang , Min Wu , Xiaoli Li , Yun Liu

General Purpose AI - such as Large Language Models (LLMs) - have seen rapid deployment in a wide range of use cases. Most surprisingly, they have have made their way from plain language models, to chat-bots, all the way to an almost…

Cryptography and Security · Computer Science 2025-01-06 Mario Fritz

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…

Computation and Language · Computer Science 2021-11-02 Lujia Shen , Shouling Ji , Xuhong Zhang , Jinfeng Li , Jing Chen , Jie Shi , Chengfang Fang , Jianwei Yin , Ting Wang

Artificial Intelligence (AI) has demonstrated unprecedented performance across various domains, and its application to communication systems is an active area of research. While current methods focus on task-specific solutions, the broader…

Artificial Intelligence · Computer Science 2025-05-21 Davide Buffelli , Sowmen Das , Yu-Wei Lin , Sattar Vakili , Chien-Yi Wang , Masoud Attarifar , Pritthijit Nath , Da-shan Shiu

Open-weight advanced AI models -- systems whose parameters are freely available for download and adaptation -- are reshaping the global AI landscape. As these models rapidly close the performance gap with closed alternatives, they enable…

Computers and Society · Computer Science 2026-02-24 Bengüsu Özcan , Alex Petropoulos , Max Reddel

Recent end-to-end robotic manipulation research increasingly adopts architectures inspired by large language models to enable robust manipulation. However, a critical challenge arises from severe distribution shifts between robotic action…

Robotics · Computer Science 2025-12-10 Yuchi Zhang , Churui Sun , Shiqi Liang , Diyuan Liu , Chao Ji , Wei-Nan Zhang , Ting Liu

Deep learning has seen a movement away from representing examples with a monolithic hidden state towards a richly structured state. For example, Transformers segment by position, and object-centric architectures decompose images into…

To improve reliability and the understanding of AI systems, there is increasing interest in the use of formal methods, e.g. model checking. Model checking tools produce a counterexample when a model does not satisfy a property.…

Formal Languages and Automata Theory · Computer Science 2024-02-05 Christel Baier , Roxane van den Bossche , Sascha Klüppelholz , Johannes Lehmann , Jakob Piribauer

How can agents learn internal models that veridically represent interactions with the real world is a largely open question. As machine learning is moving towards representations containing not just observational but also interventional…

Machine Learning · Computer Science 2024-07-03 Hamza Keurti , Hsiao-Ru Pan , Michel Besserve , Benjamin F. Grewe , Bernhard Schölkopf

The paradigm of pretrained deep learning models has recently emerged in artificial intelligence practice, allowing deployment in numerous societal settings with limited computational resources, but also embedding biases and enabling…

Computers and Society · Computer Science 2019-09-10 Lav R. Varshney , Nitish Shirish Keskar , Richard Socher

Adversarial machine learning has exposed several security hazards of neural models and has become an important research topic in recent times. Thus far, the concept of an "adversarial perturbation" has exclusively been used with reference…

Machine Learning · Computer Science 2020-09-22 Siddhant Garg , Adarsh Kumar , Vibhor Goel , Yingyu Liang

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Cryptography and Security · Computer Science 2025-11-24 Yige Li , Zhe Li , Wei Zhao , Nay Myat Min , Hanxun Huang , Xingjun Ma , Jun Sun

As Artificial Intelligence (AI) systems increasingly underpin critical applications, from autonomous vehicles to biometric authentication, their vulnerability to transferable attacks presents a growing concern. These attacks, designed to…

Cryptography and Security · Computer Science 2025-05-13 Guangjing Wang , Ce Zhou , Yuanda Wang , Bocheng Chen , Hanqing Guo , Qiben Yan

Aligned representations across languages is a desired property in multilingual large language models (mLLMs), as alignment can improve performance in cross-lingual tasks. Typically alignment requires fine-tuning a model, which is…

Computation and Language · Computer Science 2025-07-22 Anirudh Sundar , Sinead Williamson , Katherine Metcalf , Barry-John Theobald , Skyler Seto , Masha Fedzechkina

Transformers are crucial across many AI fields, such as large language models, computer vision, and reinforcement learning. This prominence stems from the architecture's perceived universality and scalability compared to alternatives. This…

Machine Learning · Computer Science 2025-12-23 Amirreza Abbasi , Mohsen Hooshmand

Since training a large-scale backdoored model from scratch requires a large training dataset, several recent attacks have considered to inject backdoors into a trained clean model without altering model behaviors on the clean data. Previous…

Machine Learning · Computer Science 2022-03-03 Zhiyuan Zhang , Lingjuan Lyu , Weiqiang Wang , Lichao Sun , Xu Sun

We conduct the first empirical study on using knowledge transfer to improve the generalization ability of large language models (LLMs) in software engineering tasks, which often require LLMs to generalize beyond their training data. Our…

Software Engineering · Computer Science 2023-08-10 Qing Huang , Yishun Wu , Zhenchang Xing , He Jiang , Yu Cheng , Huan Jin

The development of AI agents based on large, open-domain language models (LLMs) has paved the way for the development of general-purpose AI assistants that can support human in tasks such as writing, coding, graphic design, and scientific…

Artificial Intelligence · Computer Science 2025-06-03 Mustafa Mert Çelikok , Saptarashmi Bandyopadhyay , Robert Loftin

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-training stage,…

Computation and Language · Computer Science 2022-04-12 Lei Xu , Yangyi Chen , Ganqu Cui , Hongcheng Gao , Zhiyuan Liu

We analyze the ability of pre-trained language models to transfer knowledge among datasets annotated with different type systems and to generalize beyond the domain and dataset they were trained on. We create a meta task, over multiple…

Computation and Language · Computer Science 2021-12-16 Jaromir Savelka , Hannes Westermann , Karim Benyekhlef