Related papers: StreamRL: Scalable, Heterogeneous, and Elastic RL …

Large Language Models (LLMs) increasingly rely on reinforcement learning with verifiable rewards (RLVR) to elicit reliable chain-of-thought reasoning. However, the training process remains bottlenecked by the computationally expensive…

Reinforcement Learning (RL) has achieved significant success in application domains such as robotics, games and health care. However, training RL agents is very time consuming. Current implementations exhibit poor performance due to…

Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks. Within this…

Reinforcement learning (RL) has proven effective in incentivizing the reasoning abilities of large language models (LLMs), but suffers from severe efficiency challenges due to its trial-and-error nature. While the common practice employs…

Reinforcement learning (RL) for large-scale Vision-Language-Action (VLA) models faces significant challenges in computational efficiency and data acquisition. We propose AcceRL, a fully asynchronous and decoupled RL framework designed to…

We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, and is applicable across different architectures. Equipped…

Long-horizon robotic manipulation requires bridging the gap between high-level planning (System 2) and low-level control (System 1). Current Vision-Language-Action (VLA) models often entangle these processes, performing redundant multimodal…

Large language models (LLMs) commonly struggle with specialized or emerging topics which are rarely seen in the training corpus. Graph-based retrieval-augmented generation (GraphRAG) addresses this by structuring domain knowledge as a graph…

Disaggregating the prefill and decoding phases represents an effective new paradigm for generative inference of large language models (LLM), which eliminates prefill-decoding interference and optimizes resource allocation. However, it is…

Efficient data transfers over high-speed, long-distance shared networks require proper utilization of available network bandwidth. Using parallel TCP streams enables an application to utilize network parallelism and can improve transfer…

Reinforcement Learning (RL) is crucial for unlocking the complex reasoning capabilities of Diffusion-based Large Language Models (dLLMs). However, applying RL to dLLMs faces unique challenges in efficiency and stability. To address these…

LLM post-training with reinforcement learning (RL) requires frequent synchronization of large model parameters between the trainer and distributed rollout actors. High-throughput RL post-training therefore relies on dedicated RDMA HPC…

The escalating scale of Large Language Models (LLMs) necessitates efficient adaptation techniques. Model merging has gained prominence for its efficiency and controllability. However, existing merging techniques typically serve as post-hoc…

Reinforcement learning (RL) has demonstrated immense potential in advancing artificial general intelligence, agentic intelligence, and embodied intelligence. However, the inherent heterogeneity and dynamicity of RL workflows often lead to…

Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks. Despite the substantial empirical gains demonstrated by RL-based training methods like GRPO, a…

Large-batch Contrastive Learning (CL), the foundation of modern representation learning, is fundamentally incompatible with the volatile resource constraints of edge devices. This conflict creates a dilemma: small on-device batches degrade…

Extending the context length (i.e., the maximum supported sequence length) of LLMs is of paramount significance. To facilitate long context training of LLMs, sequence parallelism has emerged as an essential technique, which scatters each…

Text-to-SQL has recently achieved impressive progress, yet remains difficult to apply effectively in real-world scenarios. This gap stems from the reliance on single static workflows, fundamentally limiting scalability to…

We introduce a reinforcement learning (RL) environment to design and benchmark control strategies aimed at reducing drag in turbulent fluid flows enclosed in a channel. The environment provides a framework for computationally-efficient,…

Continual Reinforcement Learning (CRL) aims to develop lifelong learning agents to continuously acquire knowledge across diverse tasks while mitigating catastrophic forgetting. This requires efficiently managing the stability-plasticity…