Searcharxiv⌕ Search

arXiv subjects

Hao Zhou

Publications and source records attributed to Hao Zhou.

At least 19 recordsLinked to original sources
arXiv2026

On the Regularization Landscape for the Linear Recommendation Models

Recently, a wide range of recommendation algorithms inspired by deep learning techniques have emerged as the performance leaders on several standard recommendation benchmarks. While these algorithms were built on different DL techniques (e.g., dropouts, autoencoder), they have similar performance and even similar cost functions. This paper studies whether the models' comparable performance are sheer coincidence, or they can be unified under a single framework. We find that all linear performance leaders effectively add only a nuclear-norm based regularizer, or a Frobenius-norm based regularizer. The former ones possess a (surprising) rigid structure that limits the models' predictive power but their solutions are low rank and have closed form. The latter ones are more expressive and more efficient for recommendation but their solutions are either full-rank or require executing hard-to-tune numeric procedures such as ADMM. Along this line of finding, we further propose two low-rank, closed-form solutions, derived from carefully generalizing Frobenius-norm based regularizers. The new solutions get the best of both nuclear-norm and Frobenius-norm world.

cs.AI↗
arXiv2026

DriveMotion: A Large-Scale Multi-Source Benchmark for Driver Motion Sequence Modeling and Forecasting

Driver motion can provide cues to ongoing behavior, attention, and near-term driving intent. However, most existing driver-centric datasets focus on recognizing predefined driver behaviors from short video clips, while human motion forecasting benchmarks largely target motion outside the vehicle. We introduce DriveMotion, a multi-source benchmark for continuous driver motion forecasting. DriveMotion contains 393 hours of 133-keypoint motion sequences at 10 Hz from 360 drivers, integrating naturalistic driving data, curated public in-cabin videos, and the AIDE dataset into a unified representation with per-joint validity masks and synchronized driving context. Naturalistic driving contains long periods of limited body movement, making uniformly sampled evaluation dominated by persistence and less sensitive to brief but behaviorally meaningful motion. To address this, we use dynamics-anchored evaluation, placing forecasting windows around vehicle maneuvers identified offline from CAN signals without providing CAN to the model at inference. Arm motion in pre-maneuver windows is 3.4x greater than in route-matched stable-driving controls. On these anchored windows, learned models reduce forecasting error over persistence by up to 15%, while maneuver-enriched training improves forecast-derived Part-State F1 by 44% over the zero-motion reference. Training on the full multi-source corpus further reduces forecasting error on held-out web drivers by 38% compared with BATON-only training. DriveMotion provides identity-disjoint splits, fixed evaluation subsets, and reference implementations for reproducible evaluation of continuous driver motion forecasting. The dataset and benchmark are available at https://huggingface.co/datasets/HenryYHW/DriveMotion

cs.CV↗
arXiv2026

Observe Before You Alert: Adaptive Driver Alerting with Vision-Language Models

Driver alerting from dashcam video requires sequential decision-making under partial observability: a system must decide not only whether a scene is risky, but also when the evidence is sufficient to warn. Most existing accident anticipation models output a binary risk score, leaving ambiguous scenes to be handled by thresholding. We propose VLAlert, a vision-language alerting framework that casts warning generation as a tri-action policy over SILENT, OBSERVE, and ALERT. The OBSERVE action acts as an internal evidence-gathering decision that delays uncertain warnings and changes the next observation window, creating a lightweight perception-action loop for adaptive alerting. VLAlert uses Qwen3-VL-4B as a safety-evidence generator and pools hidden states from structured belief spans to form compact representations for danger estimation and policy prediction. We evaluate VLAlert on VLAlert-Bench, a unified per-tick benchmark from four real-world dashcam alert datasets, and further test transfer to held-out naturalistic ADAS takeover clips. On VLAlert-Bench validation, VLAlert achieves the highest deployment-oriented utility among tested baselines, with DAUS 0.4878 compared with 0.4752 for Open-BADAS, and improves AUROC, AP_tick, F1_t, and balanced accuracy from 0.610, 0.176, 0.276, and 0.581 to 0.689, 0.195, 0.297, and 0.648, respectively. On 221 held-out ADAS-TO-Critic clips, VLAlert improves R@5s from 74.2% to 88.7% and F1 from 0.585 to 0.686. These results indicate that adaptive observation and safety-focused VLM representations provide measurable gains for driver-facing alert decisions.

cs.CV↗
arXiv2026

Segment Any Motion with Radar: Robust Multimodal Moving-Object Segmentation and Tracking

Moving-object perception must decide which image regions correspond to real motion and keep every instance identified over time. Methods that read motion from appearance, optical flow, or estimated trajectories lose that evidence under poor illumination, adverse weather, reflections, and occlusion. Radar is a natural remedy because it measures radial velocity directly instead of inferring it from photometric correspondence. However, existing benchmarks do not jointly provide radar measurements, dense moving-instance masks, and temporally consistent identities for surveillance. We therefore introduce RGBTR-Motion, a synchronized and calibrated fixed-camera benchmark that pairs RGB, thermal, and radar streams with dense instance masks and temporally consistent identities across diverse surveillance scenes. We also develop SAM-Radar, an RGB, thermal, and radar-based segmentation and tracking framework built on SAM 3. SAM-Radar's radar-aware detector fuses calibrated RGBT features with radar returns that are grounded at their projected image locations, and motion supervision, implemented as foreground classification of those projected returns, teaches the detector to reject clutter without any text prompt. The tracker associates accepted radar returns with individual trajectories and uses them as physical evidence that a visually degraded target remains present. This allows it to bridge short periods of low visibility or occlusion and reconnect a reappearing target to its existing identity instead of starting a new track. SAM-Radar attains 0.7027 IoU and 0.8090 F1-50, and raises MOTA, HOTA, and IDF1 by 0.2977, 0.1603, and 0.2857 over the strongest competing values.

cs.CV↗
arXiv2026

Physical-Field Reconstruction from Sparse Observations: When Are Diffusion Models Preferable to Deterministic Regression?

Reconstructing physical fields from sparse observations is central to system identification, forecasting, and control, yet sparse measurements generally underdetermine the full field. This makes reconstruction an ill-posed inverse problem rather than simple interpolation. Although many deterministic and generative methods have been developed, there is still no clear consensus on when a single point estimate is sufficient and when a distribution of plausible reconstructions is more useful. We conduct a fair comparison of a deterministic U-Net, conditional diffusion, and prior-guided diffusion under matched experimental settings, including 2D Poisson equation, 2D Navier-Stokes flow, and 1D Kuramoto-Sivashinsky dynamics. Through this comparison, we make three observations. First, accuracy is field- and regime-dependent, with no systematic advantage for diffusion under higher complexity or sparser observations. Second, ensemble means improve phase-aligned accuracy, whereas individual samples better preserve variability and can retain high-wavenumber power in selected regimes. Third, conditional diffusion provides more reliable uncertainty estimates at lower cost, while prior-guided diffusion is more robust to mask-distribution shifts but requires substantially higher inference cost and guidance tuning. These results clarify when generative reconstruction is useful and provide guidance for improving uncertainty estimation, fine-scale sample fidelity, robustness, and computational efficiency in sparse field reconstruction.

physics.comp-ph↗
arXiv2026

PLUME: Parameter-Efficient Personalization of Large Language Models via Low-Rank User Modulation in Shared Subspaces

Personalizing large language models (LLMs) is essential for delivering AI assistance that aligns with individual users' styles, intents, and preferences. While per-user fine-tuning can substantially enhance personalization quality, it introduces significant parameter and storage overhead, limiting scalability to large user populations. We propose PLUME (Personalized Low-Rank Adaptation through User Modulation and Shared Subspace), a lightweight framework that achieves efficient and expressive per-user adaptation by leveraging a shared task-specific subspace. Specifically, PLUME first learns a global task subspace from aggregated user data. Personalization is then achieved by training only a lightweight small square matrix within this subspace, enabling each user to obtain a tailored model while keeping shared components fixed. Cross-layer shared parameters and rank-1 residual terms are further introduced to significantly reduce redundancy while maintaining expressiveness. Experiments on multiple personalized text generation benchmarks demonstrate that PLUME achieves comparable or superior performance to strong baselines, while reducing per-user parameters by over 95%. These results establish shared-subspace modulation with minimal residuals as a scalable and semantically grounded approach to LLM personalization.

cs.AI↗
arXiv2026

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, executable environments remain scarce. However, environments are what agent post-training actually requires: each can be re-queried into many verifiable tasks and provides execution feedback, whereas a trajectory is a single frozen demonstration. Rather than generating environments from scratch, we observe that the tool-execution history in existing trajectories exposes the structure and contents of the environments in which they ran, making it possible to reconstruct those environments from the trajectories themselves. Thus, we introduce Terminal-Universe, a framework which turns each trajectory into a reusable environment and explores it for synthesizing new tasks and continued interactions. Specifically, Terminal-Universe replays the file operations recorded in a trajectory to restore each file before the agent modified it, yielding a partial workspace; a completion agent then supplies the missing files and dependencies. On this recovered workspace, we both reconstruct the original intent task and synthesize entirely new ones. Besides, we also scale the tasks along two complementary axes: breadth and depth. For breadth, we mine directional dependency relations between related environments and synthesize cross-workspace queries spanning multiple codebases, as developers routinely do in real-world development. For depth, we extend the initial single-turn query into a multi-round session that captures iterative user feedback and requirement refinement via a user agent. Applied to public terminal agent trajectories, Terminal-Universe produces 37.3k task-sufficient environments. Supervised fine-tuning of Qwen3.5-27B on this corpus improves single-round performance on Terminal-Bench 2.1 by 11.9 points and multi-round performance on EvoCode-Bench v2 MT@4 by 13.8 points.

cs.AI↗
arXiv2026

Large Language Models (LLMs) for Telecom Root Cause Analysis (RCA): A Structured Reasoning Framework for Evidence-Grounded Diagnosis

Root cause analysis (RCA) is a critical task in telecom network operations, but diagnosing performance degradations in modern 5G and emerging 6G networks remains challenging due to complex cross-layer dependencies. While large language models (LLMs) offer promising capabilities for reasoning and knowledge integration, directly applying vanilla LLMs to telecom RCA often leads to hallucination, unstable reasoning, and poor alignment with structured network evidence. This work first reviews the evolution of telecom RCA from rule-based and machine learning (ML) approaches to emerging LLM-enabled techniques, and provides an overview of recent paradigms, including structured reasoning, retrieval-augmented knowledge grounding, agentic orchestration, and verifiable reasoning. Building upon these insights, we propose a structured reasoning framework for LLM-enabled telecom RCA that aligns diagnostic reasoning with telecom-specific evidence and domain knowledge. The proposed approach first organizes heterogeneous network telemetry into canonical contexts, and then enforces decision-path reasoning during diagnosis, and finally generates evidence-grounded explanations for reliable fault identification. Experimental results on two 5G RCA datasets, TeleLogs and TelecomTS, demonstrate that the proposed framework consistently improves diagnostic accuracy and decision consistency compared with baseline techniques. These cross-dataset results highlight the importance of structured reasoning design for practical LLM-based RCA systems in next-generation telecom networks.

cs.AI↗
arXiv2026

Investigating three-body resonances in $\alpha\alpha\Omega/\Omega_{ccc}$ clusters within the $^{9}_{\Omega/\Omega_{ccc}}{\mathrm{Be}}$ nucleus

We investigate the bound and resonant states of the $\alpha+\alpha+\Omega$ and $\alpha+\alpha+\Omega_{ccc}$ three-body systems, corresponding to $^{9}_{\Omega}{\mathrm{Be}}$ and $^{9}_{\Omega_{ccc}}{\mathrm{Be}}$, within the Gaussian expansion method combined with the complex scaling method. The $\alpha\Omega$ and $\alpha\Omega_{ccc}$ interactions are constructed by folding the $N\Omega$ and $N\Omega_{ccc}$ potentials obtained from lattice QCD calculations by the HAL QCD Collaboration with the nucleon density distribution of the $\alpha$ particle. The uncertainty associated with the $\alpha$-particle matter radius is also examined. For the $\Omega$ sector, the strong $N\Omega$ attraction generates deeply bound $0_1^+$, $2_1^+$, and $4_1^+$ states in $^{9}_{\Omega}{\mathrm{Be}}$, accompanied by a pronounced contraction of the $\alpha\alpha$ core, demonstrating a strong gluelike effect of the $\Omega$ baryon. An unconventional inversion between the $0_1^+$ and $4_1^+$ levels is also predicted. In contrast, the $\Omega_{ccc}$ baryon produces considerably weaker attraction: the $0_1^+$ state of $^{9}_{\Omega_{ccc}}{\mathrm{Be}}$ is weakly bound, whereas the $2_1^+$ and $4_1^+$ states remain resonances. Their resonance energies and widths exhibit a clear dependence on the strength of the $\alpha\Omega_{ccc}$ interaction. These results reveal qualitatively different gluelike behaviors of the $\Omega$ and $\Omega_{ccc}$ baryons and provide predictions for the spectroscopy of exotic multistrange and triply charmed hypernuclei.

hep-ph↗
arXiv2026

AgenticGen: Reward-Guided Agentic Video Generation for Advertising

Advertising video generation is not only a video synthesis task, but also a product-conditioned reasoning problem whose success is measured by online business metrics. Recent video foundation models can generate realistic clips from multimodal conditions, yet they do not optimize how a product should be transformed into an effective advertisement or how future generation should be improved from online business feedback. To close this loop, we propose AgenticGen, a reward-guided agentic framework that decomposes advertising video generation into two trainable reasoning stages, strategy selection and draft generation, thereby exposing optimization targets that online business feedback can supervise. AgenticGen learns a performance-based reward from accumulated online feedback and a complementary rubric-based reward aligned with human quality standards, then uses them to supervise policy optimization. DPO first moves the agentic policies toward online preferences, and GRPO further refines both stages with process and outcome rewards. Offline experiments validate the reward models and successive policy optimization. Online A/B experiments in the TikTok advertising system show that AgenticGen after DPO and GRPO improves CTR by 2.72%, CVR by 2.63%, and Advv by 9.61% over the SFT baseline.

cs.CV↗
arXiv2026

RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation

Standard clothing asset generation---restoring forward-facing flat-lay garment images from diverse real-world contexts---holds immense commercial value yet demands both macroscopic topological accuracy and microscopic physical fidelity. Although our previous work RAGDiffusion effectively eradicated large-scale structural hallucinations via retrieval-augmented macro-constraints, achieving industrial-grade micro-texture realism remains an unsolved bottleneck. We formally identify this limitation as High-Frequency Trajectory Collapse: supervised fine-tuning (SFT) converges to the conditional mean of the training distribution, which is dominated by smooth, low-frequency textures, causing high-frequency patterns (e.g., fabric weaves, intricate logos) to become nearly un-sampleable. Naively applying Reinforcement Learning (RL) post-training further triggers Artifact Hacking, where models exploit semantic biases in generic reward models by generating deceptive checkerboard noise. Our key insight is that RL can fundamentally reshape the sampling distribution of flow models---elevating the probability of high-fidelity trajectories under accurate reward guidance---while adversarial regularization prevents exploitation of reward blind spots. Realizing this principle requires three prerequisites: (i)inherent capacity, established through a 27,725-pair high-complexity garment dataset (STGarment-Plus) and a Dual-Image-Stream FLUX architecture upgrade; (ii)perceptive reward, provided by a novel attribute-aware reward model (Garment-RM) trained on 500K images via fine-grained contrastive learning, achieving 84.67% human preference accuracy; and (iii)hacking prevention, enforced by our Adversarial-Regularized GRPO (AR-GRPO) strategy that integrates a dynamic discriminator into the RL sampling trajectory to penalize artifacts while enriching authentic high-frequency details.

cs.CV↗
arXiv2026

Rubric-to-Code Credit Assignment for Reinforcement Learning

Interactive web application generation requires models to produce usable HTML, CSS, and JavaScript applications from natural language requests. Unlike conventional code generation, application quality depends on multiple user-facing functional requirements, each often tied to localized code regions such as event handlers, state updates, DOM fragments, or CSS selectors. Standard GRPO collapses these structured outcomes into a single sequence-level reward and applies the resulting advantage uniformly to all tokens, weakening credit assignment. We propose \textbf{Rubric-to-Code Credit Assignment} (RCCA), a reinforcement learning framework that converts rubric-level functional feedback into localized optimization signals over generated code. RCCA builds training tasks around explicit functional rubrics, uses a hierarchical reward to separate format, source-code, runtime, and functional failures, and aligns evaluator-generated textual attributions with responsible code spans and generated tokens. The resulting model, \textbf{Ling-RCCA-Flash}, scores 41.25 on MiniAppBench, improving Ling-3.0-Flash by 32.20 points and slightly surpassing Claude Opus 4.5. It also reaches 76.19 on ArtifactsBench, improving the SFT model by 4.48 points and establishing a new top score under the official ArtifactsBench leaderboard setting by surpassing the GPT-5 score by 3.64 points, suggesting transferable implementation-level gains.

cs.AI↗
arXiv2026

Not Just Reason, Not Just Scan: Reinforcement Learning for Proactive Scientific Error Verification over Academic Paper

Multimodal large language models (MLLMs) are increasingly capable scientific assistants, yet they remain far from fully autonomous research. This transition requires models to actively inspect academic papers, build global evidence views, and make traceable judgments without prespecified issues or evidence. However, existing work provides limited task paradigms or training studies for such issue- and evidence-absent verification. We study this challenge through scientific error detection, where models must determine whether errors exist and justify them with evidence-based reasoning. To fill this gap, we present VERA-RL, a reinforcement-learning formulation for scientific error detection over academic papers. Following a Reason--Verify--Scan progression, we construct VERA-13K, a 12,900-sample dataset organized into 4,300 matched chains, covering 6 scientific-error categories across the research workflow and broad natural-science domains. We further introduce fine-grained rewards for reasoning completeness, evidence alignment, and error precision. Training Qwen3-VL-8B with VERA-RL substantially improves verifiable reasoning, approaching flagship MLLMs such as Gemini 3 Pro and Qwen3-VL-235B-A22B on Scan.

cs.CL↗
arXiv2026

Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation

Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized reinforcement learning (RL) experts into a single generalist student via dense, token-level reward supervision. Despite its practical success, the optimization dynamics governing multi-teacher capability integration remain poorly understood, and open, rigorously reproducible recipes are conspicuously lacking. In this work, we establish a controlled M-OPD benchmark on SmolLM3-3B-Base with oracle routing, isolating capability integration from routing ambiguity. Our investigation reveals a pronounced capability integration gap: standard M-OPD captures only 35.6% of the available headroom relative to a domain-routed oracle ensemble, with concise tasks such as instruction following suffering severe degradation and premature stagnation. Crucially, we show that this failure stems not from gradient conflict, but from a severe misallocation of the token-level optimization budget. This pathology is driven by three orthogonal factors: structural sequence-length disparities across domains, dynamic convergence drift due to non-uniform learning rates, and multi-step reward staleness from asynchronous policy updates. To resolve these imbalances, we introduce Open-MOPD, a principled framework incorporating token-share balancing, gap-aware dynamic budget allocation, and student reward refresh. Together, these mechanisms systematically restore cross-domain balance, elevating headroom recovery from 35.6% to 83.4% in a single deployable student. We fully open-source our end-to-end post-training recipe, training trajectories, and evaluation suites on an academically accessible hardware budget.

cs.LG↗
arXiv2026

LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset

Uncrewed aerial vehicles (UAVs) are increasingly deployed for autonomous navigation in complex outdoor environments, where dynamic conditions and mission requirements require intelligent adaptive decision-making. Existing optimization-based, Machine Learning (ML), and Reinforcement Learning (RL) approaches often rely on predefined models or task-specific training, limiting their generalization and adaptability in uncertain scenarios. Recent Large Language Model (LLM)-assisted approaches offer promising reasoning capabilities but remain constrained by limited agentic functionality, including insufficient memory, planning, and tool interaction mechanisms.This paper proposes an LLM-Agent-Based Path Finder (LAPF) framework for autonomous UAV navigation in town-scale outdoor environments. LAPF extends LLM-assisted navigation by integrating perception, memory, planning, and action modules into a closed-loop cognitive architecture. The proposed agent leverages prior navigation experiences, performs Chain-of-Thought (CoT) reasoning, couples each detected hazard to a bounded corrective action, and dynamically refines waypoint decisions based on environmental feedback.The three independent trials per method demonstrate that LAPF achieves mean path lengths of 512.83 m and 506.37 m, compared to the straight-line optimum of 497.33 m, corresponding to path length reductions of 17.2% and 15.6% relative to CoT prompting and absolute path efficiencies of 97.1% and 98.1% in open-field and obstacle-injected scenarios, respectively. Furthermore, LAPF is the only evaluated approach that couples every detected hazard to a bounded, metric-neutral corrective action while maintaining near-goal stability, with zero clamp events in both scenarios, whereas CoT prompting increases from 9.7 to 14.0 events.

cs.RO↗
arXiv2026

Envs-FORGE: Frontier-Optimized Reward-Grounded Environment Synthesis for Agent RL

Reinforcement learning (RL) for terminal agents needs executable training environments with reliable rewards and useful difficulty. Fixed recipes such as few-shot, Self-Instruct, and Evol-Instruct apply the same prompting policy to every seed, even when the current policy would benefit from a harder, easier, or simply different task. We present Envs-FORGE, a prompting policy that converts verifier rewards into per-seed environment-synthesis actions. Envs-FORGE estimates seed pass rates, scores six projection--direction actions around a target learning frontier, and solves a per-seed mixed-integer linear program (MILP) to choose the action that conditions generation. The selected action drives synchronized rewriting of the instruction, fixtures, oracle solution, tests, and Docker environment; only gold-verified bundles enter RL training. The indexed MILP form also supports optional soft skill coverage for portfolio planning. On Qwen 3.5 35B, Envs-FORGE improves Pass@1 over Base by 9.2 percentage points on tb-core (40.0% to 49.2%) and 6.4 points on tb-2.0 (23.0% to 29.4%), exceeding the strongest fixed-recipe baseline by 2.4 and 2.1 points. It reaches 77.1% on SWE-bench Verified versus 73.4% for Base, and improves tb-core by 6.8--9.2 points across the evaluated 4B--35B models. All synthesis methods export 100 verified environments and use 2.27M--2.88M synthesis tokens, placing the comparison at the same downstream training-set size and the same operational scale. The source code is available at https://github.com/DataArcTech/DataArc-SynData-Toolkit/.

cs.CL↗
arXiv2026

Evo-Bench: Can Language Models Improve Agent Harness?

Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolution---the agent's capacity to autonomously optimize its own operating harness. However, systematically benchmarking this capability remains challenging, as existing evaluations fail to isolate harness improvements from base model strength, prevent task-specific overfitting, or capture long-horizon iterative research. To address these challenges, we introduce Evo-Bench, the first benchmark designed to evaluate models' intrinsic harness-evolving capabilities across Search, Office, and General agent domains. To rigorously isolate this capability, Evo-Bench employs a novel harness-guided construction framework: it leverages auxiliary-task evolution to identify tasks genuinely sensitive to framework improvements, followed by sensitivity-aware stratified splitting to ensure robust cross-suite generalization. Extensive evaluations across nine frontier and open-weight models reveal that top models achieve massive absolute gains reaching 16.6 points, closely approaching state-of-the-art human-engineered baselines. Crucially, while autonomous evolution outpeforms artificial harness in General tasks and excels in Search tasks, it struggles in Office tasks that demand highly specific processing workflows. Furthermore, our analysis exposes critical temporal anomalies like early saturation, while demonstrating that the synthesized harnesses act as highly transferable reasoning structures, consistently boosting diverse policy models.

cs.CL↗
arXiv2026

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation

Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We instead take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide a natural source of distillation supervision rather than a disposable byproduct of sampling. Based on this insight, we propose REST (Reward-Enhanced Scored-Trajectory Distillation), a single-stage RL-distillation co-training framework that attaches a decoupled student to an arbitrary RL teacher. The student learns segment-wise from the teacher's evolving rollout trajectories while leaving the original teacher optimization unchanged. To prevent uniform imitation from preserving undesirable low-reward behaviors, we further introduce Advantage-Modulated Distillation (AMD), which transforms rollout advantages into signed weights over a base distillation loss. AMD strengthens supervision from preferred trajectories and mildly repels the student from low-reward ones. The resulting framework is lightweight and plug-and-play, requires no extra image rollouts, no separate distillation dataset, and no adversarial training. Experiments on compositional generation, visual text rendering, and human-preference alignment show that REST enables few-step CFG-free inference that matches or surpasses its 40-step RL teacher, with an overall additional training cost below 25% over pure RL. REST improves DrawBench PickScore over RTDMD by 0.82 while requiring only one-fifth of the training iterations.

cs.CV↗