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