Laruso blog features productivity, tips, inspiration and strategies for massive profits. Find out how to set up a successful blog or how to make yours even better!
DOPPLER is a new framework that combines diffusion models and hierarchical reinforcement learning to let robots plan and replan complex, long-horizon tasks from offline data with robustness in the real world.
We propose optimal likelihood ratio-based selective classification methods based on the Neyman-Pearson lemma and evaluate them under vision and language covariate shifts tasks.
We introduce KOAP for imitation learning with limited actions.
We design an LLM-driven social-scenario simulation pipeline (SocRATES) to enable more holistic evaluation of social navigation algorithms. SocRATES generates context- and location-appropriate scenarios from simple text and image-based inputs, thus reducing the labor-intensive task of scenario proposal and synthesis that is typically required for scenario-based testing.
We show that a single unconditional diffusion model performs competitively in out-of-distribution detection tasks by measuring the rate-of-change and curvature of diffusion paths connecting data samples to the standard normal distribution.
We address a problem where an agent assigns users to arms in a stochastic multi-armed bandit setting to maximize the minimum expected cumulative reward for all users. It presents a UCB-based policy with upper bounds on cumulative regret and an impossibility result for policy-independent approaches.
We develop a safe planning method for trajectory generation by sampling from diffusion model under different LTLf constraints.
