8 citations · 22 across the 13 of their papers we have counts for
15 papers
RoboTalk: Learning Multi-Robot Communication and Coordination from Multimodal Demonstrations
Dorian Benhamou Goldfajn, Mason Nakamura, Saaduddin Mahmud +3
Multi-robot collaboration could enable more efficient and scalable solutions to complex robotic tasks, but collaboration under partial observability remains challenging. Natural-la…
FrankenReport: Early Exiting in Long-Form Generation Using Expected Value of Computation
Zhengping Jiang, Gonzalo Ramos, Jina Suh +6
While deep research systems address interactive information-seeking needs impressively, their real-world deployments face latency and resource-consumption challenges. We present Fr…
RHO: Your Coding Agent is Secretly a Roboticist
Karim Elmaaroufi, Justin Svegliato, Sarunas Kalade +3
Code-as-Policies (CaP) has shown that large language models (LLMs) can write code to solve robotics tasks by composing perception, planning, and control primitives. Recent CaP syst…
Fine-Tuning LLMs with Fine-Grained Human Feedback on Text Spans
Sky CH-Wang, Justin Svegliato, Helen Appel +1
We present a method and dataset for fine-tuning language models with preference supervision using feedback-driven improvement chains. Given a model response, an annotator provides…
GRAID: Enhancing Spatial Reasoning of VLMs Through High-Fidelity Data Generation
Karim Elmaaroufi, Liheng Lai, Justin Svegliato +3
Vision Language Models (VLMs) achieve strong performance on many vision-language tasks but often struggle with spatial reasoning$\unicode{x2014}$a prerequisite for many application…
MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools
Nishant Subramani, Jason Eisner, Justin Svegliato +3
Tool-using agents that act in the world need to be both useful and safe. Well-calibrated model confidences can be used to weigh the risk versus reward of potential actions, but pri…
AssistanceZero: Scalably Solving Assistance Games
Cassidy Laidlaw, Eli Bronstein, Timothy Guo +5
Assistance games are a promising alternative to reinforcement learning from human feedback (RLHF) for training AI assistants. Assistance games resolve key drawbacks of RLHF, such a…
A StrongREJECT for Empty Jailbreaks
Alexandra Souly, Qingyuan Lu, Dillon Bowen +8
Most jailbreak papers claim the jailbreaks they propose are highly effective, often boasting near-100% attack success rates. However, it is perhaps more common than not for jailbre…
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
Sam Toyer, Olivia Watkins, Ethan Adrian Mendes +9
While Large Language Models (LLMs) are increasingly being used in real-world applications, they remain vulnerable to prompt injection attacks: malicious third party prompts that su…
Active teacher selection for reward learning
Rachel Freedman, Justin Svegliato, Kyle Wray +1
Reward learning techniques enable machine learning systems to learn objectives from human feedback. A core limitation of these systems is their assumption that all feedback comes f…
Active Reward Learning from Multiple Teachers
Peter Barnett, Rachel Freedman, Justin Svegliato +1
Reward learning algorithms utilize human feedback to infer a reward function, which is then used to train an AI system. This human feedback is often a preference comparison, in whi…
Fairness and Sequential Decision Making: Limits, Lessons, and Opportunities
Samer B. Nashed, Justin Svegliato, Su Lin Blodgett
As automated decision making and decision assistance systems become common in everyday life, research on the prevention or mitigation of potential harms that arise from decisions m…
Agent-aware State Estimation in Autonomous Vehicles
Shane Parr, Ishan Khatri, Justin Svegliato +1
Autonomous systems often operate in environments where the behavior of multiple agents is coordinated by a shared global state. Reliable estimation of the global state is thus crit…
Improving Competence for Reliable Autonomy
Connor Basich, Justin Svegliato, Kyle Hollins Wray +2
Given the complexity of real-world, unstructured domains, it is often impossible or impractical to design models that include every feature needed to handle all possible scenarios…
Learning to Optimize Autonomy in Competence-Aware Systems
Connor Basich, Justin Svegliato, Kyle Hollins Wray +3
Interest in semi-autonomous systems (SAS) is growing rapidly as a paradigm to deploy autonomous systems in domains that require occasional reliance on humans. This paradigm allows…