Searcharxiv⌕ Search

arXiv subjects

Yuhong Guo

Publications and source records attributed to Yuhong Guo.

At least 19 recordsLinked to original sources
arXiv2026

AInfer-PD: Communication-Safe In-Place Prefill-Decode Multiplexing for Distributed MoE Rollouts

Rollout inference often dominates the wall-clock time of large-scale reinforcement learning (RL). In agentic RL, each trajectory alternates between model generation and environment interaction over multiple turns. Asynchronous trajectories consequently introduce new prefill (P) work while other trajectories remain in decode (D), making P/D coexistence a persistent property of the rollout rather than a one-time prompt-ingestion event. On shared accelerators, persistent P/D coexistence can make prefill interfere with latency-sensitive decode and prolong rollout completion. P/D disaggregation avoids this co-location but requires separate device pools and KV-cache transfers. In-place multiplexing retains shared devices and KV state, but existing designs lack the communication isolation needed for large MoE deployments that combine attention TP/DP with distributed expert execution. In practical implementations, P and D can issue intersecting collectives in inconsistent cross-rank orders; DeepEP's P and D paths also share mutable protocol state. We present AInfer-PD, which extends in-place P/D multiplexing to distributed MoE rollouts. AInfer-PD coordinates P/D collective order across ranks and gives the two DeepEP paths independent communication state, making crossed ADP/ATP and DeepEP paths safe for concurrent P/D execution. The design retains shared model weights and KV storage while coordinating P and D on the same devices. Across repeated single-node prefill-intensive workloads, AInfer-PD reduces fixed-workload rollout completion time by 7.1-22.5% relative to the same AInfer engine with P/D multiplexing disabled and by 24.8-32.9% relative to SGLang. On two nodes, the reductions are 18.0-35.3% and 18.3-31.8%, respectively. In a same-engine ablation, fine-grained boundaries reduce completion time by a further 8.6-19.8% over whole-epoch asynchronous enqueue.

cs.DC↗
arXiv2026

Quality-Aware Modulation for Diffusion Transformers

Modern text-to-image diffusion models, such as diffusion transformers (DiT), rely on timestep or prompt embeddings to modulate the strength of the denoising process in each timestep. While this modulation communicates the current noise level, it does not provide any quality-aware information, which can lead to generated images that are unaligned, visually inconsistent, and lacking in fidelity. In this paper, we propose the Quality Representation Module (QRM), a lightweight transformer module that learns a quality-aware representation based on existing model inputs, and produces a set of vectors $M_{qrm}$. These vectors adjust the adaptive LayerNorm modulation within the DiT transformer blocks, thereby injecting a quality-sensitive signal into the denoising parameters. The QRM introduces no significant changes to the sampling schedule or diffusion backbone. Experiments include ablations on QRM training losses and architectures, as well as empirical results demonstrating consistent image quality improvements over baseline DiT-based models.

cs.LG↗
arXiv2026

Select-to-Act: Hierarchical Reinforcement Learning via Adaptive Language Guidance

Reinforcement Learning (RL) has been widely applied to sequential decision-making, yet it often suffers from poor sample efficiency due to costly interactions with the environment. A limited line of recent work has started exploring improving RL efficiency by leveraging external knowledge expressed in natural-language instructions. However, the few existing approaches typically treat the entire instruction as a single conditioning input, failing to account for the stage-dependent nature of language guidance, especially in complex environments. In this paper, we propose \emph{Hierarchical Reinforcement Learning with Language Instructions (HRLLI)}, a hierarchical RL framework that explicitly models natural-language instructions as dynamically selectable semantic guidance during decision-making. HRLLI decomposes instructions into a set of piecewise guidance elements, where each instruction piece may become relevant at different stages of interaction with the environment. A novel hierarchical RL policy structure is then formulated in a \emph{Select-to-Act} paradigm: a high-level semantic policy acts as a guidance selector that selects the most relevant instruction piece to the current state to guide the low-level agent's decision, while a low-level policy executes environment actions conditioned on the selected guidance. The two-level policies are learned simultaneously to maximize augmented expected returns from interactions with the environment. This design enables the agent to adaptively ground language instructions into stage-specific decisions during interaction. Experiments on the instruction-intensive RTFM benchmark show that HRLLI consistently outperforms strong instruction-conditioned RL baselines, demonstrating that explicitly modeling adaptive instruction selection significantly improves the effectiveness of RL.

cs.LG↗
arXiv2026

Reliability-Guided Adaptive Ensembling for Robust Test-Time Adaptation

Test-time adaptation (TTA) can mitigate domain shift without source data, but it is highly brittle under adversarially contaminated test streams, where corrupted inputs also destabilize online updates. We study robust test-time adaptation (RTTA) in the adversarial-stream setting, which remains comparatively underexplored relative to standard TTA, and propose SAFER (Stochastic Augmentation Framework for Enhanced Robustness), a training-free reliability-guided augmentation wrapper for RTTA. SAFER preserves the wrapped TTA objective while replacing brittle single-view predictions with a reliability-guided pooled predictor. For each test sample, SAFER generates stochastic augmentations and aggregates their predictions through correlation-weighted pooling with outlier detection. We further study an adaptive-mixing extension that improves clean-performance retention by adjusting original-versus-augmentation weighting using feature disagreement signals. We evaluate on PACS, VLCS, and OfficeHome under PGD attacks at various attack rates. Across benchmarks, SAFER improves resilience of TTA methods to adversarial attacks while maintaining competitive clean performance.

cs.LG↗
arXiv2026

Bi-Level Optimization for Single Domain Generalization

Generalizing from a single labeled source domain to unseen target domains, without access to any target data during training, remains a fundamental challenge in robust machine learning. We address this underexplored setting, known as Single Domain Generalization (SDG), by proposing BiSDG, a bi-level optimization framework that explicitly decouples task learning from domain modeling. BiSDG simulates distribution shifts through surrogate domains constructed via label-preserving transformations of the source data. To capture domain-specific context, we propose a domain prompt encoder that generates lightweight modulation signals to produce augmenting features via feature-wise linear modulation. The learning process is formulated as a bi-level optimization problem: the inner objective optimizes task performance under fixed prompts, while the outer objective maximizes generalization across the surrogate domains by updating the domain prompt encoder. We further develop a practical gradient approximation scheme that enables efficient bi-level training without second-order derivatives. Extensive experiments on various SGD benchmarks demonstrate that BiSDG consistently outperforms prior methods, setting new state-of-the-art performance in the SDG setting.

cs.LG↗
arXiv2026

Bridging Dynamics Gaps via Diffusion Schrödinger Bridge for Cross-Domain Reinforcement Learning

Cross-domain reinforcement learning (RL) aims to learn transferable policies under dynamics shifts between source and target domains. A key challenge lies in the lack of target-domain environment interaction and reward supervision, which prevents direct policy learning. To address this challenge, we propose Bridging Dynamics Gaps for Cross-Domain Reinforcement Learning (BDGxRL), a novel framework that leverages Diffusion Schrödinger Bridge (DSB) to align source transitions with target-domain dynamics encoded in offline demonstrations. Moreover, we introduce a reward modulation mechanism that estimates rewards based on state transitions, applying to DSB-aligned samples to ensure consistency between rewards and target-domain dynamics. BDGxRL performs target-oriented policy learning entirely within the source domain, without access to the target environment or its rewards. Experiments on MuJoCo cross-domain benchmarks demonstrate that BDGxRL outperforms state-of-the-art baselines and shows strong adaptability under transition dynamics shifts.

cs.LG↗
arXiv2026

Diffusion Modulation via Environment Mechanism Modeling for Planning

Diffusion models have shown promising capabilities in trajectory generation for planning in offline reinforcement learning (RL). However, conventional diffusion-based planning methods often fail to account for the fact that generating trajectories in RL requires unique consistency between transitions to ensure coherence in real environments. This oversight can result in considerable discrepancies between the generated trajectories and the underlying mechanisms of a real environment. To address this problem, we propose a novel diffusion-based planning method, termed as Diffusion Modulation via Environment Mechanism Modeling (DMEMM). DMEMM modulates diffusion model training by incorporating key RL environment mechanisms, particularly transition dynamics and reward functions. Experimental results demonstrate that DMEMM achieves state-of-the-art performance for planning with offline reinforcement learning.

cs.AI↗
arXiv2025

Learning to Clean: Reinforcement Learning for Noisy Label Correction

The challenge of learning with noisy labels is significant in machine learning, as it can severely degrade the performance of prediction models if not addressed properly. This paper introduces a novel framework that conceptualizes noisy label correction as a reinforcement learning (RL) problem. The proposed approach, Reinforcement Learning for Noisy Label Correction (RLNLC), defines a comprehensive state space representing data and their associated labels, an action space that indicates possible label corrections, and a reward mechanism that evaluates the efficacy of label corrections. RLNLC learns a deep feature representation based policy network to perform label correction through reinforcement learning, utilizing an actor-critic method. The learned policy is subsequently deployed to iteratively correct noisy training labels and facilitate the training of the prediction model. The effectiveness of RLNLC is demonstrated through extensive experiments on multiple benchmark datasets, where it consistently outperforms existing state-of-the-art techniques for learning with noisy labels.

cs.LG↗
arXiv2025

Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model

We present Ring-1T, the first open-source, state-of-the-art thinking model with a trillion-scale parameter. It features 1 trillion total parameters and activates approximately 50 billion per token. Training such models at a trillion-parameter scale introduces unprecedented challenges, including train-inference misalignment, inefficiencies in rollout processing, and bottlenecks in the RL system. To address these, we pioneer three interconnected innovations: (1) IcePop stabilizes RL training via token-level discrepancy masking and clipping, resolving instability from training-inference mismatches; (2) C3PO++ improves resource utilization for long rollouts under a token budget by dynamically partitioning them, thereby obtaining high time efficiency; and (3) ASystem, a high-performance RL framework designed to overcome the systemic bottlenecks that impede trillion-parameter model training. Ring-1T delivers breakthrough results across critical benchmarks: 93.4 on AIME-2025, 86.72 on HMMT-2025, 2088 on CodeForces, and 55.94 on ARC-AGI-1. Notably, it attains a silver medal-level result on the IMO-2025, underscoring its exceptional reasoning capabilities. By releasing the complete 1T parameter MoE model to the community, we provide the research community with direct access to cutting-edge reasoning capabilities. This contribution marks a significant milestone in democratizing large-scale reasoning intelligence and establishes a new baseline for open-source model performance.

cs.CL↗
arXiv2025

Skill-Enhanced Reinforcement Learning Acceleration from Heterogeneous Demonstrations

Learning from Demonstration (LfD) is a well-established problem in Reinforcement Learning (RL), which aims to facilitate rapid RL by leveraging expert demonstrations to pre-train the RL agent. However, the limited availability of expert demonstration data often hinders its ability to effectively aid downstream RL learning. To address this problem, we propose a novel two-stage method dubbed as Skill-enhanced Reinforcement Learning Acceleration (SeRLA). SeRLA introduces a skill-level adversarial Positive-Unlabeled (PU) learning model that extracts useful skill prior knowledge by learning from both expert demonstrations and general low-cost demonstrations in the offline prior learning stage. Building on this, it employs a skill-based soft actor-critic algorithm to leverage the acquired priors for efficient training of a skill policy network in the downstream online RL stage. In addition, we propose a simple skill-level data enhancement technique to mitigate data sparsity and further improve both skill prior learning and skill policy training. Experiments across multiple standard RL benchmarks demonstrate that SeRLA achieves state-of-the-art performance in accelerating reinforcement learning on downstream tasks, particularly in the early training phase.

cs.LG↗
arXiv2025

LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning

Reinforcement Learning (RL) is known for its strong decision-making capabilities and has been widely applied in various real-world scenarios. However, with the increasing availability of offline datasets and the lack of well-designed online environments from human experts, the challenge of generalization in offline RL has become more prominent. Due to the limitations of offline data, RL agents trained solely on collected experiences often struggle to generalize to new tasks or environments. To address this challenge, we propose LLM-Driven Policy Diffusion (LLMDPD), a novel approach that enhances generalization in offline RL using task-specific prompts. Our method incorporates both text-based task descriptions and trajectory prompts to guide policy learning. We leverage a large language model (LLM) to process text-based prompts, utilizing its natural language understanding and extensive knowledge base to provide rich task-relevant context. Simultaneously, we encode trajectory prompts using a transformer model, capturing structured behavioral patterns within the underlying transition dynamics. These prompts serve as conditional inputs to a context-aware policy-level diffusion model, enabling the RL agent to generalize effectively to unseen tasks. Our experimental results demonstrate that LLMDPD outperforms state-of-the-art offline RL methods on unseen tasks, highlighting its effectiveness in improving generalization and adaptability in diverse settings.

cs.LG↗
arXiv2025

Target-Oriented Single Domain Generalization

Deep models trained on a single source domain often fail catastrophically under distribution shifts, a critical challenge in Single Domain Generalization (SDG). While existing methods focus on augmenting source data or learning invariant features, they neglect a readily available resource: textual descriptions of the target deployment environment. We propose Target-Oriented Single Domain Generalization (TO-SDG), a novel problem setup that leverages the textual description of the target domain, without requiring any target data, to guide model generalization. To address TO-SDG, we introduce Spectral TARget Alignment (STAR), a lightweight module that injects target semantics into source features by exploiting visual-language models (VLMs) such as CLIP. STAR uses a target-anchored subspace derived from the text embedding of the target description to recenter image features toward the deployment domain, then utilizes spectral projection to retain directions aligned with target cues while discarding source-specific noise. Moreover, we use a vision-language distillation to align backbone features with VLM's semantic geometry. STAR further employs feature-space Mixup to ensure smooth transitions between source and target-oriented representations. Experiments across various image classification and object detection benchmarks demonstrate STAR's superiority. This work establishes that minimal textual metadata, which is a practical and often overlooked resource, significantly enhances generalization under severe data constraints, opening new avenues for deploying robust models in target environments with unseen data.

cs.CV↗
arXiv2025

Skill-based Safe Reinforcement Learning with Risk Planning

Safe Reinforcement Learning (Safe RL) aims to ensure safety when an RL agent conducts learning by interacting with real-world environments where improper actions can induce high costs or lead to severe consequences. In this paper, we propose a novel Safe Skill Planning (SSkP) approach to enhance effective safe RL by exploiting auxiliary offline demonstration data. SSkP involves a two-stage process. First, we employ PU learning to learn a skill risk predictor from the offline demonstration data. Then, based on the learned skill risk predictor, we develop a novel risk planning process to enhance online safe RL and learn a risk-averse safe policy efficiently through interactions with the online RL environment, while simultaneously adapting the skill risk predictor to the environment. We conduct experiments in several benchmark robotic simulation environments. The experimental results demonstrate that the proposed approach consistently outperforms previous state-of-the-art safe RL methods.

cs.LG↗
arXiv2025

Safety Modulation: Enhancing Safety in Reinforcement Learning through Cost-Modulated Rewards

Safe Reinforcement Learning (Safe RL) aims to train an RL agent to maximize its performance in real-world environments while adhering to safety constraints, as exceeding safety violation limits can result in severe consequences. In this paper, we propose a novel safe RL approach called Safety Modulated Policy Optimization (SMPO), which enables safe policy function learning within the standard policy optimization framework through safety modulated rewards. In particular, we consider safety violation costs as feedback from the RL environments that are parallel to the standard awards, and introduce a Q-cost function as safety critic to estimate expected future cumulative costs. Then we propose to modulate the rewards using a cost-aware weighting function, which is carefully designed to ensure the safety limits based on the estimation of the safety critic, while maximizing the expected rewards. The policy function and the safety critic are simultaneously learned through gradient descent during online interactions with the environment. We conduct experiments using multiple RL environments and the experimental results demonstrate that our method outperforms several classic and state-of-the-art comparison methods in terms of overall safe RL performance.

cs.LG↗
arXiv2025

Context-Aware Self-Adaptation for Domain Generalization

Domain generalization aims at developing suitable learning algorithms in source training domains such that the model learned can generalize well on a different unseen testing domain. We present a novel two-stage approach called Context-Aware Self-Adaptation (CASA) for domain generalization. CASA simulates an approximate meta-generalization scenario and incorporates a self-adaptation module to adjust pre-trained meta source models to the meta-target domains while maintaining their predictive capability on the meta-source domains. The core concept of self-adaptation involves leveraging contextual information, such as the mean of mini-batch features, as domain knowledge to automatically adapt a model trained in the first stage to new contexts in the second stage. Lastly, we utilize an ensemble of multiple meta-source models to perform inference on the testing domain. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on standard benchmarks.

cs.LG↗
arXiv2025

Zero-Shot Action Generalization with Limited Observations

Reinforcement Learning (RL) has demonstrated remarkable success in solving sequential decision-making problems. However, in real-world scenarios, RL agents often struggle to generalize when faced with unseen actions that were not encountered during training. Some previous works on zero-shot action generalization rely on large datasets of action observations to capture the behaviors of new actions, making them impractical for real-world applications. In this paper, we introduce a novel zero-shot framework, Action Generalization from Limited Observations (AGLO). Our framework has two main components: an action representation learning module and a policy learning module. The action representation learning module extracts discriminative embeddings of actions from limited observations, while the policy learning module leverages the learned action representations, along with augmented synthetic action representations, to learn a policy capable of handling tasks with unseen actions. The experimental results demonstrate that our framework significantly outperforms state-of-the-art methods for zero-shot action generalization across multiple benchmark tasks, showcasing its effectiveness in generalizing to new actions with minimal action observations.

cs.LG↗
arXiv2025

Single Domain Generalization with Adversarial Memory

Domain Generalization (DG) aims to train models that can generalize to unseen testing domains by leveraging data from multiple training domains. However, traditional DG methods rely on the availability of multiple diverse training domains, limiting their applicability in data-constrained scenarios. Single Domain Generalization (SDG) addresses the more realistic and challenging setting by restricting the training data to a single domain distribution. The main challenges in SDG stem from the limited diversity of training data and the inaccessibility of unseen testing data distributions. To tackle these challenges, we propose a single domain generalization method that leverages an adversarial memory bank to augment training features. Our memory-based feature augmentation network maps both training and testing features into an invariant subspace spanned by diverse memory features, implicitly aligning the training and testing domains in the projected space. To maintain a diverse and representative feature memory bank, we introduce an adversarial feature generation method that creates features extending beyond the training domain distribution. Experimental results demonstrate that our approach achieves state-of-the-art performance on standard single domain generalization benchmarks.

cs.LG↗
arXiv2025

A Unified Framework for Heterogeneous Semi-supervised Learning

In this work, we introduce a novel problem setup termed as Heterogeneous Semi-Supervised Learning (HSSL), which presents unique challenges by bridging the semi-supervised learning (SSL) task and the unsupervised domain adaptation (UDA) task, and expanding standard semi-supervised learning to cope with heterogeneous training data. At its core, HSSL aims to learn a prediction model using a combination of labeled and unlabeled training data drawn separately from heterogeneous domains that share a common set of semantic categories; this model is intended to differentiate the semantic categories of test instances sampled from both the labeled and unlabeled domains. In particular, the labeled and unlabeled domains have dissimilar label distributions and class feature distributions. This heterogeneity, coupled with the assorted sources of the test data, introduces significant challenges to standard SSL and UDA methods. Therefore, we propose a novel method, Unified Framework for Heterogeneous Semi-supervised Learning (Uni-HSSL), to address HSSL by directly learning a fine-grained classifier from the heterogeneous data, which adaptively handles the inter-domain heterogeneity while leveraging both the unlabeled data and the inter-domain semantic class relationships for cross-domain knowledge transfer and adaptation. We conduct comprehensive experiments and the experimental results validate the efficacy and superior performance of the proposed Uni-HSSL over state-of-the-art semi-supervised learning and unsupervised domain adaptation methods.

cs.LG↗