Related papers: ROSE: Rollout On Serving GPUs via Cooperative Elas…

Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in complex reasoning and multi-turn interactions but struggle to continuously improve and adapt when deployed in new environments. One promising approach is…

Equipping large language models with explicit skills has emerged as a promising paradigm for enabling autonomous agents to solve complex tasks. Agent skills can be inherently divided into general skills for broad cognitive transfer and…

Scalability is a major challenge in modern recommender systems. In sequential recommendations, full Cross-Entropy (CE) loss achieves state-of-the-art recommendation quality but consumes excessive GPU memory with large item catalogs,…

With the increasing computational capability of mobile devices, deploying agentic retrieval-augmented generation (RAG) locally on heterogeneous System-on-Chips (SoCs) has become a promising way to enhance LLM-based applications. However,…

Simulation-based design space exploration (DSE) aims to efficiently optimize high-dimensional structured designs under complex constraints and expensive evaluation costs. Existing approaches, including heuristic and multi-step reinforcement…

Since the introduction of the GRPO algorithm, reinforcement learning (RL) has attracted increasing attention for LLM post-training, yet training efficiency remains a critical challenge. In mainstream RL frameworks, inference and training…

Autonomous racing presents unique challenges due to its non-linear dynamics, the high speed involved, and the critical need for real-time decision-making under dynamic and unpredictable conditions. Most traditional Reinforcement Learning…

Shared-use autonomous mobility services (SAMS) present new opportunities for improving accessible and demand-responsive mobility. A fundamental challenge that SAMS face is appropriate positioning of idle fleet vehicles to meet future demand…

Reinforcement learning (RL) is widely used for post-training large language models (LLMs) in code editing, where group-relative methods, such as GRPO, are popular due to their critic-free and normalized advantage estimation. However, in…

As single-center computing approaches power constraints, decentralized training becomes essential. However, traditional Reinforcement Learning (RL) methods, crucial for enhancing large model post-training, cannot adapt to decentralized…

Maximizing training throughput and cost-efficiency of RL for LLMs is essential to democratize this advanced technique. One promising but challenging approach is to deploy such a computational workflow over heterogeneous GPUs. Unlike…

Reinforcement learning (RL) suffers from low sample efficiency, particularly in high-dimensional continuous state-action spaces of complex robotic manipulation tasks. RL performance can improve by leveraging prior knowledge, even when…

Reinforcement learning (RL) has demonstrated the ability to maintain the plasticity of the policy throughout short-term training in aerial robot control. However, these policies have been shown to loss of plasticity when extended to…

The promotion of large-scale applications of reinforcement learning (RL) requires efficient training computation. While existing parallel RL frameworks encompass a variety of RL algorithms and parallelization techniques, the excessively…

With recent advancements in Connected Autonomous Vehicles (CAVs), Green Light Optimal Speed Advisory (GLOSA) emerges as a promising eco-driving strategy to reduce the number of stops and idle time at intersections, thereby reducing energy…

We propose a novel multi-agent reinforcement learning (RL) approach for inter-cell interference mitigation, in which agents selectively share their experiences with other agents. Each base station is equipped with an agent, which receives…

The deployment of reconfigurable intelligent surfaces (RISs) introduces new challenges for resource allocation in multi-cell wireless networks, particularly when user loads are uneven across base stations. In this work, we consider RISs as…

As predictive models are increasingly being deployed in high-stakes decision making (e.g., loan approvals), there has been growing interest in post hoc techniques which provide recourse to affected individuals. These techniques generate…

Robots and autonomous agents often complete goal-based tasks with limited resources, relying on imperfect models and sensor measurements. In particular, reinforcement learning (RL) and feedback control can be used to help a robot achieve a…

Large language model (LLM) serving is fundamentally limited by inefficient hardware utilization. Autoregressive (AR) decoding underutilizes GPUs due to its strictly sequential execution, while diffusion LLMs (DLLMs) improve throughput by…