Related papers: PRISM: Performer RS-IMLE for Single-pass Multisens…

Offline Reinforcement Learning (RL) learns optimal policies from fixed datasets, training a policy once and deploying it at inference time without further refinement. Inspired by model predictive control (MPC), we introduce an inference…

Processing-in-memory (PIM) seeks to eliminate computation/memory data transfer using devices that support both storage and logic. Stateful logic techniques such as IMPLY, MAGIC and FELIX can perform logic gates within memristive crossbar…

Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel…

The ability to learn multi-modal action distributions is indispensable for robotic manipulation policies to perform precise and robust control. Flow-based generative models have recently emerged as a promising solution to learning…

Simulation of atomic resolution image formation in scanning transmission electron microscopy can require significant computation times using traditional methods. A recently developed method, termed plane-wave reciprocal-space interpolated…

In recent years, reinforcement learning and imitation learning have shown great potential for controlling humanoid robots' motion. However, these methods typically create simulation environments and rewards for specific tasks, resulting in…

Robotic manipulation tasks often rely on static cameras for perception, which can limit flexibility, particularly in scenarios like robotic surgery and cluttered environments where mounting static cameras is impractical. Ideally, robots…

Accurately forecasting GPU workloads is essential for AI infrastructure, enabling efficient scheduling, resource allocation, and power management. Modern workloads are highly volatile, multiple periodicity, and heterogeneous, making them…

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

Diffusion Policies have become widely used in Imitation Learning, offering several appealing properties, such as generating multimodal and discontinuous behavior. As models are becoming larger to capture more complex capabilities, their…

This work demonstrates a front-flip on bicycle robots via reinforcement learning, particularly by imitating reference motions that are infeasible and imperfect. To address this, we propose Iterative Motion Imitation(IMI), a method that…

Model-based reinforcement learning promises strong sample efficiency but often underperforms in practice due to compounding model error, unimodal world models that average over multi-modal dynamics, and overconfident predictions that bias…

Acquiring complex behaviors is essential for artificially intelligent agents, yet learning these behaviors in high-dimensional settings poses a significant challenge due to the vast search space. Traditional reinforcement learning (RL)…

Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-frequency variations. Flow Matching (FM) offers an efficient…

Compared to traditional image retrieval tasks, product retrieval in retail settings is even more challenging. Products of the same type from different brands may have highly similar visual appearances, and the query image may be taken from…

Room impulse responses (RIRs) are fundamental to audio data augmentation, acoustic signal processing, and immersive audio rendering. While geometric simulators such as the image source method (ISM) can efficiently generate early…

Prompt learning has demonstrated promising results in fine-tuning pre-trained multimodal models. However, the performance improvement is limited when applied to more complex and fine-grained tasks. The reason is that most existing methods…

Foundation models, a cornerstone of recent advancements in machine learning, have predominantly thrived on complete and well-structured data. Wearable sensor data frequently suffers from significant missingness, posing a substantial…

Model-based planning in robotic domains is challenged by the hybrid nature of physical dynamics, where continuous motion is punctuated by discrete events such as contacts and impacts. Conventional latent world models typically employ…

Robot learning has proven to be a general and effective technique for programming manipulators. Imitation learning is able to teach robots solely from human demonstrations but is bottlenecked by the capabilities of the demonstrations.…