Related papers: Speculative Policy Orchestration: A Latency-Resili…
By leveraging differentiable dynamics, Reparameterization Policy Gradient (RPG) achieves high sample efficiency. However, current approaches are hindered by two critical limitations: the under-utilization of computationally expensive…
Training general robotic policies from heterogeneous data for different tasks is a significant challenge. Existing robotic datasets vary in different modalities such as color, depth, tactile, and proprioceptive information, and collected in…
Speculative decoding accelerates LLM inference by having a lightweight draft model propose speculative windows of candidate tokens for parallel verification by a larger target model. In practice, speculative efficiency is often bottlenecked…
In modern distributed cloud environments, efficient resource allocation is required as traditional scaling mechanisms are often subject to cloud thrashing due to network-induced latencies. In this paper, we propose C-SAS (Complex-Stability…
This paper tackles the growing issue of excessive data transmission in networks. With increasing traffic, backhaul links and core networks are under significant traffic, leading to the investigation of caching solutions at edge routers.…
Striking a balance between efficiency and transparent motion is a core challenge in human-robot collaboration, as highly expressive movements often incur unnecessary time and energy costs. In collaborative environments, legibility allows a…
Vision-language-action (VLA) models achieve strong generalization through large-scale pre-training, but real-world deployment requires expert-level task proficiency in addition to broad generality. Existing post-training approaches for VLA…
Resource scheduling in cloud-edge systems is challenging as edge nodes run latency-sensitive workloads under tight resource constraints, while existing centralized schedulers can suffer from performance bottlenecks and user experience…
Mobile edge computing mitigates the shortcomings of cloud computing caused by unpredictable wide-area network latency and serves as a critical enabling technology for the Industrial Internet of Things (IIoT). Unlike cloud computing, mobile…
Automated matching engines execute millions of orders per session, yet systematic asymmetries in latency, order size, and market access compound into persistent execution disparities that erode participant trust. We formulate provably fair…
In this paper we develop a computational offloading strategy with graceful degradation for executing Model Predictive Control using the cloud. Backed up by previous work we simulate the control of a cyber-physical-system at high frequency…
Speculative execution attacks leverage the speculative and out-of-order execution features in modern computer processors to access secret data or execute code that should not be executed. Secret information can then be leaked through a…
Mobile robots can fail before they collide: a velocity that is safe now may commit the robot to a passage that moving obstacles will soon close. We study this predictive near-miss commitment problem and propose Risk-Sensitive Conjectural…
The Internet of Things (IoT) devices are highly reliant on cloud systems to meet their storage and computational demands. However, due to the remote location of cloud servers, IoT devices often suffer from intermittent Wide Area Network…
Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous training and mismatches between training and inference engines. Naive importance sampling gives an…
We study the problem of conservative off-policy evaluation (COPE) where given an offline dataset of environment interactions, collected by other agents, we seek to obtain a (tight) lower bound on a policy's performance. This is crucial when…
Human preference alignment is critical in building powerful and reliable large language models (LLMs). However, current methods either ignore the multi-dimensionality of human preferences (e.g. helpfulness and harmlessness) or struggle with…
Long-term fluid dynamics forecasting is a critically important problem in science and engineering. While neural operators have emerged as a promising paradigm for modeling systems governed by partial differential equations (PDEs), they…
Very recently proximal policy optimization (PPO) algorithms have been proposed as first-order optimization methods for effective reinforcement learning. While PPO is inspired by the same learning theory that justifies trust region policy…
FaaS introduces a lightweight, function-based cloud execution model that finds its relevance in a range of applications like IoT-edge data processing and anomaly detection. While cloud service providers offer a near-infinite function…