4 papers
Rapid co-design of Buoyancy-assisted robots for Challenging Locomotion using Gaussian Evolutionary Specialists
Ankit Sinha, Nitish Sontakke, Dennis Hong +2
Designing high-performance legged robots requires jointly optimizing morphology and control. Model-free Reinforcement Learning (RL) offers an alternative to model-predictive contro…
Adapting World Models with Latent-State Dynamics Residuals
JB Lanier, Kyungmin Kim, Armin Karamzade +5
Simulation-to-reality reinforcement learning (RL) faces the critical challenge of reconciling discrepancies between simulated and real-world dynamics, which can severely degrade ag…
Learning to Search Effective Example Sequences for In-Context Learning
Xiang Gao, Ankita Sinha, Kamalika Das
Large language models (LLMs) demonstrate impressive few-shot learning capabilities, but their performance varies widely based on the sequence of in-context examples. Key factors in…
Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution
Ankita Sinha, Wendi Cui, Kamalika Das +1
Large language models (LLMs) have demonstrated remarkable capabilities; however, the optimization of their prompts has historically prioritized performance metrics at the expense o…