Related papers: Stress Testing Deliberative Alignment for Anti-Sch…
Autonomous inspection in hazardous environments requires AI agents that can interpret high-level goals and execute precise control. A key capability for such agents is spatial grounding, for example when a drone must center a detected…
AI support of collaborative interactions entails mediating potential misalignment between interlocutor beliefs. Common preference alignment methods like DPO excel in static settings, but struggle in dynamic collaborative tasks where the…
Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed human behavior. We compare 120 base-aligned model pairs on more than 10,000 real human decisions…
Increasing interest in integrating advanced robotics within manufacturing has spurred a renewed concentration in developing real-time scheduling solutions to coordinate human-robot collaboration in this environment. Traditionally, the…
Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…
The ability to accurately predict human behavior is central to the safety and efficiency of robot autonomy in interactive settings. Unfortunately, robots often lack access to key information on which these predictions may hinge, such as…
Autonomous robots operating in open and changing environments cannot always rely on predefined inputs, outputs, and action routines. Although existing learning methods enable robots to improve their performance through environmental…
Learned dynamics models combined with both planning and policy learning algorithms have shown promise in enabling artificial agents to learn to perform many diverse tasks with limited supervision. However, one of the fundamental challenges…
AI systems in high-consequence domains such as defense, intelligence, and disaster response must detect rare, high-impact events while operating under tight resource constraints. Traditional annotation strategies that prioritize label…
If AI systems match or exceed human capabilities on a wide range of tasks, it may become difficult for humans to efficiently judge their actions -- making it hard to use human feedback to steer them towards desirable traits. One proposed…
The search for reliable indicators of consciousness has fragmented into competing theoretical camps (Global Workspace Theory (GWT), Integrated Information Theory (IIT), and Higher-Order Theories (HOT)), each proposing distinct neural…
Adversarial training, as one of the most effective defense methods against adversarial attacks, tends to learn an inclusive decision boundary to increase the robustness of deep learning models. However, due to the large and unnecessary…
As AI systems become more capable and widely deployed as agents, ensuring their safe operation becomes critical. AI control offers one approach to mitigating the risk from untrusted AI agents by monitoring their actions and intervening or…
Strategic classification studies learning in settings where self-interested users can strategically modify their features to obtain favorable predictive outcomes. A key working assumption, however, is that "favorable" always means…
Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step…
A long-standing goal in AI is to develop agents capable of solving diverse tasks across a range of environments, including those never seen during training. Two dominant paradigms address this challenge: (i) reinforcement learning (RL),…
AI Agents can perform complex operations at great speed, but just like all the humans we have ever hired, their intelligence remains fallible. Miscommunications aren't noticed, systemic biases have no counter-action, and inner monologues…
Large Language Models (LLMs) are being adopted across a wide range of tasks, including decision-making processes in industries where bias in AI systems is a significant concern. Recent research indicates that LLMs can harbor implicit biases…
This is the second in a series of short reports that seek to help business, education, and policy leaders understand the technical details of working with AI through rigorous testing. In this report, we investigate Chain-of-Thought (CoT)…
Word alignment which aims to extract lexicon translation equivalents between source and target sentences, serves as a fundamental tool for natural language processing. Recent studies in this area have yielded substantial improvements by…