English
Related papers

Related papers: ASA: Training-Free Representation Engineering for …

200 papers

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal…

Cryptography and Security · Computer Science 2025-09-22 Weixiang Zhao , Jiahe Guo , Yulin Hu , Yang Deng , An Zhang , Xingyu Sui , Xinyang Han , Yanyan Zhao , Bing Qin , Tat-Seng Chua , Ting Liu

As LLMs are increasingly deployed in real-world applications, ensuring their ability to refuse malicious prompts, especially jailbreak attacks, is essential for safe and reliable use. Recently, activation steering has emerged as an…

Machine Learning · Computer Science 2026-02-10 Leheng Sheng , Changshuo Shen , Weixiang Zhao , Junfeng Fang , Xiaohao Liu , Zhenkai Liang , Xiang Wang , An Zhang , Tat-Seng Chua

This paper rethinks steady-hand robotic manipulation by using a weakly supervised framework that fuses calibration-aware perception with admittance control. Unlike conventional automation that relies on labor-intensive 2D labeling, our…

LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test…

Computation and Language · Computer Science 2026-05-19 Nivya Talokar , Ayush K Tarun , Murari Mandal , Maksym Andriushchenko , Antoine Bosselut

Large language models (LLMs) are becoming the foundation for autonomous agents that can use tools to solve complex tasks. Reinforcement learning (RL) has emerged as a common approach for injecting such agentic capabilities, but typically…

Machine Learning · Computer Science 2026-02-26 Emre Can Acikgoz , Cheng Qian , Jonas Hübotter , Heng Ji , Dilek Hakkani-Tür , Gokhan Tur

Reinforcement learning (RL) is a promising, upcoming topic in automatic control applications. Where classical control approaches require a priori system knowledge, data-driven control approaches like RL allow a model-free controller design…

Systems and Control · Electrical Eng. & Systems 2022-02-01 Daniel Weber , Maximilian Schenke , Oliver Wallscheid

A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior…

Machine Learning · Computer Science 2025-03-04 Reza Bayat , Ali Rahimi-Kalahroudi , Mohammad Pezeshki , Sarath Chandar , Pascal Vincent

LLM-powered agents are emerging as a dominant paradigm for autonomous task solving. Unlike standard inference workloads, agents operate in a strictly serial "LLM-tool" loop, where the LLM must wait for external tool execution at every step.…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-20 Yifan Sui , Han Zhao , Rui Ma , Zhiyuan He , Hao Wang , Jianxun Li , Yuqing Yang

Intermediate training of pre-trained transformer-based language models on domain-specific data leads to substantial gains for downstream tasks. To increase efficiency and prevent catastrophic forgetting alleviated from full domain-adaptive…

Computation and Language · Computer Science 2023-05-23 Chia-Chien Hung , Lukas Lange , Jannik Strötgen

Current AI agent frameworks commit early to a single interaction protocol, a fixed tool integration strategy, and static user models, limiting their deployment across diverse interaction paradigms. To address these constraints, we introduce…

Artificial Intelligence · Computer Science 2026-03-25 Alfred Shen , Aaron Shen

Iterative industrial design-simulation optimization is bottlenecked by the CAD-CAE semantic gap: translating simulation feedback into valid geometric edits under diverse, coupled constraints. To fill this gap, we propose COSMO-Agent…

Artificial Intelligence · Computer Science 2026-05-21 Liyuan Deng , Shujian Deng , Yongkang Chen , Yongkang Dai , Zhihang Zhong , Linyang Li , Xiao Sun , Yilei Shi , Huaxi Huang

Vision-Language Models (VLMs) excel at zero-shot inference but often degrade under test-time domain shifts. For this reason, episodic test-time adaptation strategies have recently emerged as powerful techniques for adapting VLMs to a single…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Konstantinos M. Dafnis , Dimitris N. Metaxas

Low-precision training has become a popular approach to reduce compute requirements, memory footprint, and energy consumption in supervised learning. In contrast, this promising approach has not yet enjoyed similarly widespread adoption…

Machine Learning · Computer Science 2021-06-07 Johan Bjorck , Xiangyu Chen , Christopher De Sa , Carla P. Gomes , Kilian Q. Weinberger

In the realm of embodied intelligence, the evolution of large language models (LLMs) has markedly enhanced agent decision making. Consequently, researchers have begun exploring agent performance in dynamically changing high-risk scenarios,…

Artificial Intelligence · Computer Science 2025-06-10 Yangqing Zheng , Shunqi Mao , Dingxin Zhang , Weidong Cai

Prompt engineering and finetuning aim to maximize language model performance on a given metric (like toxicity reduction). However, these methods do not fully elicit a model's capabilities. To reduce this gap, we introduce activation…

Computation and Language · Computer Science 2024-10-11 Alexander Matt Turner , Lisa Thiergart , Gavin Leech , David Udell , Juan J. Vazquez , Ulisse Mini , Monte MacDiarmid

Large language models (LLMs) have achieved remarkable performance across many tasks, yet aligning them with desired behaviors remains challenging. Activation intervention has emerged as an effective and economical method to modify the…

Computation and Language · Computer Science 2025-02-26 Weixuan Wang , Jingyuan Yang , Wei Peng

Reinforcement learning (RL) offers a promising approach for adaptive wind farm flow control, yet its practical deployment is hindered by slow training convergence and poor initial performance, factors that could translate to years of…

Systems and Control · Electrical Eng. & Systems 2026-04-28 Marcus Binder Nilsen , Julian Quick , Tuhfe Göçmen , Nikolay Dimitrov , Pierre-Elouan Réthoré

Tool-Integrated Reasoning (TIR) has significantly enhanced the capabilities of Large Language Models (LLMs), yet current agents tend to exhibit cognitive offloading, redundantly invoking external tools even for simple tasks. In this paper,…

Computation and Language · Computer Science 2026-01-22 Zhaiyu Fang , Ruipeng Sun

Despite the recent success of deep reinforcement learning (RL), domain adaptation remains an open problem. Although the generalization ability of RL agents is critical for the real-world applicability of Deep RL, zero-shot policy transfer…

Machine Learning · Computer Science 2021-09-06 Jinwei Xing , Takashi Nagata , Kexin Chen , Xinyun Zou , Emre Neftci , Jeffrey L. Krichmar

Large Language Models (LLMs) can extend their parameter knowledge limits by adopting the Tool-Integrated Reasoning (TIR) paradigm. However, existing LLM-based agent training framework often focuses on answers' accuracy, overlooking specific…

Artificial Intelligence · Computer Science 2026-01-21 Yifei Chen , Guanting Dong , Zhicheng Dou