3 citations · 7 across the 13 of their papers we have counts for
21 papers
The Memory Trap: Language Agents Overgeneralize from Benign Interactions
Kaiqu Liang, Jaime Fernández Fisac, Thomas L. Griffiths +1
Language agents increasingly use persistent memory to record user preferences and procedures across sessions. We show that memory from benign interactions can cause unsafe or unrel…
Confidence-Modulated Safety Filtering for End-to-End Policies
Javier Borquez, Jaime F. Fisac
End-to-end policies, from task-specific controllers to robot foundation models, learn complex behavior from raw observations but are not guaranteed to remain safe, so they are ofte…
Training Controllable World Models via Action Influence Maximization
Samuel M. Bateman, Tenny Yin, Chongyi Zheng +5
Action-conditioned video generative models trained on successful, goal-directed demonstrations tend to ignore the commanded action, rendering a plausible expert-like future regardl…
Winning a Won Game: Strict Reach-Avoid-Stay Control Barrier Functions for High-Dimensional Black-Box Systems
Donggeon David Oh, Duy P. Nguyen, Gongkai Yuan +3
Robots must complete their tasks and maintain the achieved outcomes while avoiding safety failures at all times. Strict reach-avoid-stay (sRAS) formalizes this requirement: safely…
Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response
Elle Lazarski, Jaime Fernández Fisac
Assistance games formalize human-robot collaboration under asymmetric information: the human knows the goal, while the robot must infer it from observation and interaction in order…
Human-like autonomy emerges from self-play and a pinch of human data
Daphne Cornelisse, Julian Hunt, Zixu Zhang +4
Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data. It uses cheap, large-scale simulations to substitute expensive, lar…
Synthesis and Deployment of Maximal Robust Control Barrier Functions through Adversarial Reinforcement Learning
Donggeon David Oh, Duy P. Nguyen, Haimin Hu +1
Robust control barrier functions (CBFs) provide a principled mechanism for smooth safety enforcement under worst-case disturbances. However, existing approaches typically rely on e…
Learning Personalized Agents from Human Feedback
Kaiqu Liang, Julia Kruk, Shengyi Qian +9
Modern AI agents are powerful but often fail to align with the idiosyncratic, evolving preferences of individual users. Prior approaches typically rely on static datasets, either t…
Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions
Zhiting Mei, Tenny Yin, Ola Shorinwa +9
Video world models have emerged as promising candidates for high-fidelity world models, offering the potential to synthesize high-quality videos capturing fine-grained interactions…
Viscosity CBFs: Bridging the Control Barrier Function and Hamilton-Jacobi Reachability Frameworks in Safe Control Theory
Dylan Hirsch, Jaime Fernández Fisac, Sylvia Herbert
Control barrier functions (CBFs) and Hamilton-Jacobi reachability (HJR) are central frameworks in safe control. Traditionally, these frameworks have been viewed as distinct, with t…
Provably Optimal Reinforcement Learning under Safety Filtering
Donggeon David Oh, Duy P. Nguyen, Haimin Hu +2
Recent advances in reinforcement learning (RL) enable its use on increasingly complex tasks, but the lack of formal safety guarantees still limits its application in safety-critica…
From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails
Ravi Pandya, Madison Bland, Duy P. Nguyen +3
Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-generation autonomous cars. In th…
Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models
Kaiqu Liang, Haimin Hu, Xuandong Zhao +3
Bullshit, as conceptualized by philosopher Harry Frankfurt, refers to statements made without regard to their truth value. While previous work has explored large language model (LL…
Safety with Agency: Human-Centered Safety Filter with Application to AI-Assisted Motorsports
Donggeon David Oh, Justin Lidard, Haimin Hu +8
We propose a human-centered safety filter (HCSF) for shared autonomy that significantly enhances system safety without compromising human agency. Our HCSF is built on a neural safe…
RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation
Kaiqu Liang, Haimin Hu, Ryan Liu +2
While Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning generative AI, we present empirical evidence that it can also cause severe, systematic misalig…
MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safety
Justin Wang, Haimin Hu, Duy Phuong Nguyen +1
While robust optimal control theory provides a rigorous framework to compute robot control policies that are provably safe, it struggles to scale to high-dimensional problems, lead…
Think Deep and Fast: Learning Neural Nonlinear Opinion Dynamics from Inverse Dynamic Games for Split-Second Interactions
Haimin Hu, Jaime Fernández Fisac, Naomi Ehrich Leonard +3
Non-cooperative interactions commonly occur in multi-agent scenarios such as car racing, where an ego vehicle can choose to overtake the rival, or stay behind it until a safe overt…
Blending Data-Driven Priors in Dynamic Games
Justin Lidard, Haimin Hu, Asher Hancock +9
As intelligent robots like autonomous vehicles become increasingly deployed in the presence of people, the extent to which these systems should leverage model-based game-theoretic…
Who Plays First? Optimizing the Order of Play in Stackelberg Games with Many Robots
Haimin Hu, Gabriele Dragotto, Zixu Zhang +3
We consider the multi-agent spatial navigation problem of computing the socially optimal order of play, i.e., the sequence in which the agents commit to their decisions, and its as…
Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity
Kaiqu Liang, Zixu Zhang, Jaime Fernández Fisac
Large language models (LLMs) exhibit advanced reasoning skills, enabling robots to comprehend natural language instructions and strategically plan high-level actions through proper…
Differentiable Cutting-plane Layers for Mixed-integer Linear Optimization
Gabriele Dragotto, Stefan Clarke, Jaime Fernández Fisac +1
We consider the problem of solving a family of parametric mixed-integer linear optimization problems where some entries in the input data change. We introduce the concept of cuttin…