Search arXiv⌕ Search

arXiv subjects

Yujie Zhou

Publications and source records attributed to Yujie Zhou.

At least 19 recordsLinked to original sources
arXiv2026

WorldReward: Reward Modeling for Camera-Conditioned World Models

Camera-conditioned world models generate interactive videos in which commanded actions should induce the expected scene changes while appearance, geometry, and temporal dynamics remain coherent. Existing rewards assess these requirements separately: geometry-based rewards estimate trajectory execution but cannot judge the visual quality of the executed motion, whereas image-based rewards measure frame quality without capturing action execution or temporal dynamics. We posit that a vision-language model (VLM) offers a shared reasoning space for relating actions to their visual outcomes. However, judging a complete long video against its full action sequence creates a lengthy, noisy context in which short-lived local action evidence can be missed or diluted. We present WorldReward, a VLM-based pairwise preference reward model that unifies action-consistency and visual-quality evaluation for camera-conditioned world models. WorldReward decomposes paired videos into action-aligned chunks, organizes each chunk into structured visual evidence, and aggregates chunk-level decisions by voting into separate video-level action and visual-quality preferences. To train it, we construct a large-scale reasoning-augmented preference dataset using structured judgments generated by a frontier VLM and refined through tool-based agent auditing and targeted human review. We further introduce WorldReward-Bench, a human-annotated benchmark measuring reward-model agreement with human preferences across action consistency, appearance quality, and motion quality. WorldReward achieves the highest agreement on all three dimensions, exceeding GPT-5.5 by 3.42, 1.45, and 3.56 percentage points, respectively. When used for RL post-training of HY-WorldPlay 1.5, it consistently improves both action execution and visual quality across short- to long-term horizons.

cs.CV↗
arXiv2026

HPSD: Hybrid-Policy Self-Distillation for Text-Image-to-Video Diffusion Models

Text-Image-to-Video (TI2V) models are an emerging unified architecture, where a single model simultaneously supports text-to-video (T2V) and image-to-video (I2V) generation. Given a high-quality first frame or a detailed textual prompt, TI2V models unlock substantially better visual quality than their T2V mode, raising a natural question: can the capability elicited by such privileged conditions be internalized into the model's own base generation ability? A common approach toward this goal is model self-distillation. However, the most straightforward solution, supervised fine-tuning, follows an off-policy strategy: its supervision is confined to teacher-generated endpoints from a fixed offline distribution rather than student-visited states, lacking precise correction tailored to the evolving policy. Recent on-policy distillation methods instead suffer from condition-state mismatch, where supervision is steered toward the given first frame instead of the student's actual content, misleading the correction. To achieve self-distillation that absorbs the teacher's privileged prior while retaining precise policy correction, in this work, we propose Hybrid-Policy Self-Distillation (HPSD), a novel self-distillation framework where a single TI2V model acts as both teacher and student under different conditions: the teacher operates in TI2V mode with a high-quality first frame and an enhanced prompt, while the student runs in the base T2V mode with only the vanilla prompt. Specifically, the student inherits off-policy teacher trajectory points as anchors, locally refines them toward its own policy, and finally receives velocity-level supervision on these self-generated roll-outs. Extensive experiments demonstrate that HPSD significantly improves T2V performance while also delivering notable TI2V gains, effectively strengthening the model's base generation ability.

cs.CV↗
arXiv2026

Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition

Group Relative Policy Optimization(GRPO) has emerged as an effective paradigm for aligning flow-based generative models with human preferences. However, the high cost of group rollouts forces existing methods to use very few denoising steps, resulting in sparse temporal supervision and leaving most intermediate stages without direct reward guidance. To address this, we propose Pave-GRPO, which reformulates the GRPO objective through principled average velocity decomposition. Rather than generating expensive high-step rollouts, we maintain efficient few-step group sampling but decompose each coarse transition into an equivalent ensemble of finer sub-trajectories spanning multiple intermediate timesteps, propagating reward feedback to a denser set of temporal stages for more comprehensive preference alignment. Crucially, this incurs no additional stochastic rollout generation or reward evaluation: the decomposed sub-trajectories are constructed analytically around the observed transitions, requiring only a small number of extra velocity-network evaluations during the policy update. This design offers two benefits: (i) rollout-free horizon expansion: through the direct reuse of few-step group samples and their associated rewards, Pave-GRPO significantly broadens the effective optimization scope under a fixed sampling and reward budget; and (ii) comprehensive temporal supervision: by equivalently decomposing an instantaneous velocity target into a multi-timestep ensemble, it distributes reward signals across more intermediate stages of the denoising process, enabling finer-grained and more thorough preference optimization.

cs.CV↗
arXiv2026

EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models

Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusion frameworks primarily as text encoders to tackle complex tasks such as spatial reasoning. However, this paradigm suffers from two critical limitations: (i) MLLMs text encoder exhibits insufficient reasoning depth. Single-step encoding fails to activate the Chain-of-Thought process, which is essential for MLLMs to provide accurate guidance for complex tasks. (ii) The guidance remains invariant during the decoding process. Invariant guidance during decoding prevents DiT from progressively decomposing complex instructions into actionable denoising steps, even with correct MLLM encodings. To this end, we propose Endogenous Chain-of-Thought (EndoCoT), a novel framework that first activates MLLMs' reasoning potential by iteratively refining latent thought states through an iterative thought guidance module, and then bridges these states to the DiT's denoising process. Second, a terminal thought grounding module is applied to ensure the reasoning trajectory remains grounded in textual supervision by aligning the final state with ground-truth answers. With these two components, the MLLM text encoder delivers meticulously reasoned guidance, enabling the DiT to execute it progressively and ultimately solve complex tasks in a step-by-step manner. Extensive evaluations across diverse benchmarks (e.g., Maze, TSP, VSP, and Sudoku) achieve an average accuracy of 92.1%, outperforming the strongest baseline by 8.3 percentage points. The code and dataset are publicly available at https://internlm.github.io/EndoCoT/.

cs.CV↗
arXiv2026

CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning

Image and video captioning are fundamental tasks that bridge the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Current state-of-the-art captioning models are typically trained with Supervised Fine-Tuning (SFT), a paradigm that relies on expensive, non-scalable annotations and often causes models to memorize specific ground-truth answers, limiting their generality and ability to generate diverse, creative descriptions. To overcome these limitations, we propose applying Reinforcement Learning with Verifiable Rewards (RLVR) to the open-ended task of multimodal captioning. We introduce Captioning Reinforcement Learning++ (CapRL++), a novel reference-free training framework that redefines caption quality through its utility: a high-quality caption should enable a non-visual language model to accurately answer questions about the corresponding visual content. CapRL++ employs a decoupled two-stage pipeline where an LVLM generates a caption, and the objective reward is derived from the accuracy of a separate, vision-free LLM answering Multiple-Choice Questions based solely on that caption. Evaluations on more than 20 image and video benchmarks show that CapRL++ improves dense caption quality and strengthens caption-based pretraining across tasks such as spatial and temporal understanding. Pretraining on scalable image and video caption datasets annotated by CapRL++ yields substantial downstream gains. Furthermore, within the Prism Framework for caption quality evaluation, compact models trained with CapRL++ achieve dense captioning performance comparable to substantially larger models such as Qwen2.5-VL-72B and Qwen3-VL-235B-A22B. These results validate that CapRL++ effectively trains models to produce generalizable, high-fidelity descriptions, establishing a robust foundation beyond the limitations of traditional SFT.

cs.CV↗
arXiv2026

AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO

Group Relative Policy Optimization (GRPO) has demonstrated remarkable success in aligning text-to-image (T2I) flow models with human preferences. However, we have identified that the learning loop of current flow-based GRPO is fundamentally decoupled from the learner's current capability, suffering from critical blind spots at both prompt selection and advantage estimation: (i) Existing methods sample prompts randomly, overlooking the substantial impact of data selection on reinforcement learning (RL) efficacy--a factor proven crucial in GRPO for large language models; (ii) They evaluate sample quality solely relying on intra-group statistics, lacking a global perspective to accurately measure true policy improvement. To address these issues, we propose Adaptive GRPO (AdaGRPO), a novel capability-aware RL algorithm tailored for flow models. Specifically, AdaGRPO consists of two principal components: (i) Online Curriculum Filtering Strategy: Dynamically tracks the model's proficiency and adaptively selects prompts that best match its current learning boundary; (ii) Cross-Level Advantage Fusion: Synergistically integrates fine-grained intra-group advantages with macro-level global advantages, providing a comprehensive and unbiased policy evaluation. As a lightweight, plug-and-play module, AdaGRPO can be seamlessly integrated with existing frameworks such as Flow-GRPO, DanceGRPO, and Flow-CPS. Extensive experiments demonstrate that AdaGRPO consistently drives performance gains while significantly stabilizes GRPO training for flow models.

cs.CV↗
arXiv2026

JointHRRP-Net: A Statistically Constrained Decoupling Network for Joint Target and Jamming Recognition in Composite Jamming

High-resolution range profile (HRRP)-based radar automatic target recognition suffers from severe performance degradation in composite jamming environments. Active jamming introduces suppression- and deception-related components into the received range profile. After pulse compression, these components are coupled with target echoes in the HRRP domain, making target-related scattering peaks difficult to distinguish and weakening feature separability. To address this problem, this paper proposes JointHRRP-Net, a unified framework for joint target-jamming recognition. A statistically constrained decoupling module is first developed to generate target-dominant and jamming-dominant latent branches from the mixed HRRP representation. Correlation-guided statistical constraints are imposed to suppress redundant cross-branch information and alleviate target-jamming feature entanglement. A multi-scale temporal encoding module is then designed to model local scattering structures and long-range range-cell dependencies, followed by a dual-expert decision module for single-label target classification and multi-label jamming classification. Experiments under diverse signal-to-jamming ratio (SJR) and signal-to-noise ratio (SNR) levels demonstrate that JointHRRP-Net outperforms representative baseline methods in both target recognition and composite jamming recognition. Open-set evaluation further shows that the learned target representation remains discriminative for unknown-target rejection. These results demonstrate the effectiveness and robustness of JointHRRP-Net in composite jamming scenarios.

eess.SP↗
arXiv2026

SANEmerg: An Emergent Communication Framework for Semantic-aware Agentic AI Networking

Future networking systems are envisioned to become part of an agentic AI-native ecosystem in which a vast number of heterogeneous and specialized AI agents cooperate seamlessly to fulfill complex user requirements in real time. However, traditional networking paradigms are characterized by a rigid decoupling of communication and computation, which often leads to significant inefficiencies in large-scale agentic AI networking (AgentNet) systems. Emergent communication offers a novel solution by enabling autonomous agents that support task-specific signaling protocols for information exchange and collaborative coordination. In this paper, we consider a multi-agent emergent communication framework, tailored for semantic-aware AgentNet systems in which the user's semantic intent can be automatically detected, inferred, and linked to a set of sub-tasks to be assigned to a set of agents. We investigate how communication and signaling protocols can emerge among collaborative agents with computationally bounded intelligence under stringent bandwidth constraints. Our proposed framework, called SANEmerg, is designed to facilitate the emergence of communication for collaborative task fulfillment while adhering to the physical limits of AgentNet. SANEmerg incorporates a bandwidth-adaptable importance-filter that dynamically prioritizes the transmission of higher-contribution message dimensions, ensuring robust performance in bandwidth-limited environments. Furthermore, SANEmerg integrates a complexity-regularizer grounded in the Minimum Description Length (MDL) principle to facilitate the emergence of computationally bounded signaling. Evaluated via an AgentNet prototype and extensive experimentation, SANEmerg demonstrates significant performance improvements over state-of-the-art solutions, achieving superior task accuracy while significantly reducing bandwidth and computational overhead.

cs.AI↗
arXiv2026

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

Recent advancements highlight the importance of GRPO-based reinforcement learning methods and benchmarking in enhancing text-to-image (T2I) generation. However, current methods using pointwise reward models (RM) for scoring generated images are susceptible to reward hacking. We reveal that this happens when minimal score differences between images are amplified after normalization, creating illusory advantages that drive the model to over-optimize for trivial gains, ultimately destabilizing the image generation process. To address this, we propose Pref-GRPO, a pairwise preference reward-based GRPO method that shifts the optimization objective from score maximization to preference fitting, ensuring more stable training. In Pref-GRPO, images are pairwise compared within each group using preference RM, and the win rate is used as the reward signal. Extensive experiments demonstrate that PREF-GRPO differentiates subtle image quality differences, providing more stable advantages and mitigating reward hacking. Additionally, existing T2I benchmarks are limited by coarse evaluation criteria, hindering comprehensive model assessment. To solve this, we introduce UniGenBench, a unified T2I benchmark comprising 600 prompts across 5 main themes and 20 subthemes. It evaluates semantic consistency through 10 primary and 27 sub-criteria, leveraging MLLM for benchmark construction and evaluation. Our benchmarks uncover the strengths and weaknesses of both open and closed-source T2I models and validate the effectiveness of Pref-GRPO.

cs.CV↗
arXiv2026

Uni-Classifier: Leveraging Video Diffusion Priors for Universal Guidance Classifier

In practical AI workflows, complex tasks often involve chaining multiple generative models, such as using a video or 3D generation model after a 2D image generator. However, distributional mismatches between the output of upstream models and the expected input of downstream models frequently degrade overall generation quality. To address this issue, we propose Uni-Classifier (Uni-C), a simple yet effective plug-and-play module that leverages video diffusion priors to guide the denoising process of preceding models, thereby aligning their outputs with downstream requirements. Uni-C can also be applied independently to enhance the output quality of individual generative models. Extensive experiments across video and 3D generation tasks demonstrate that Uni-C consistently improves generation quality in both workflow-based and standalone settings, highlighting its versatility and strong generalization capability.

cs.CV↗
arXiv2026

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space

Group Relative Policy Optimization (GRPO) has emerged as a powerful framework for preference alignment in text-to-image (T2I) flow models. However, we observe that the standard paradigm where evaluating a group of generated samples against a single condition suffers from insufficient exploration of inter-sample relationships, constraining both alignment efficacy and performance ceilings. To address this sparse single-view evaluation scheme, we propose Multi-View GRPO (MV-GRPO), a novel approach that enhances relationship exploration by augmenting the condition space to create a dense multi-view reward mapping. Specifically, for a group of samples generated from one prompt, MV-GRPO leverages a flexible Condition Enhancer to generate semantically adjacent yet diverse captions. These captions enable multi-view advantage re-estimation, capturing diverse semantic attributes and providing richer optimization signals. By deriving the probability distribution of the original samples conditioned on these new captions, we can incorporate them into the training process without costly sample regeneration. Extensive experiments demonstrate that MV-GRPO achieves superior alignment performance over state-of-the-art methods.

cs.CV↗
arXiv2026

CTPX1: A Highly Integrated and High-Throughput Data-Driven Camera Based on Timepix4

The upgrade of the China Spallation Neutron Source (CSNS-II) will raise the proton beam power to 500 kW. Consequently, the existing Timepix3-based detector systems, limited to a count rate of 80 Mhits/s, will encounter severe saturation challenges. To address the demand of the Energy-Resolved Neutron Imaging instrument (ERNI) for next-generation higher count-rate electronics, this paper presents CTPX1, a high-performance data-driven camera system based on the Timepix4 ASIC. The system adopts a compact modular architecture, integrating readout electronics, a precision high-voltage bias unit, and a TEC temperature control subsystem. To fully exploit the readout potential of the Timepix4 ASIC's 16 high-speed serial links, this paper proposes a two-stage parallel processing architecture. This architecture achieves real-time data aggregation with a total bandwidth of up to 81.92 Gbps. Over a continuous 12-hour operation period, temperature fluctuations were kept within 0.1 °C while the high-voltage output noise remained below 1 mV. High-flux X-ray testing indicates that the system achieves a peak event readout rate of 1.17 Ghits/s, approaching the limit of the configured link speed. In-beam neutron verification at CSNS confirms that the camera successfully resolves fine spatial structures, achieving an imaging performance consistent with the 55 μm pixel pitch of the sensor. Furthermore, the clear observation of spectral features in the Time of flight (TOF) spectrum of a γ-Fe sample validates the system's good time resolution. This camera effectively addresses the data readout saturation challenges, validates the feasibility of Timepix4 technology for neutron imaging, and provides a viable solution for next-generation high-performance neutron imaging instruments.

physics.ins-det↗
arXiv2026

UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation

Recent progress in text-to-image (T2I) generation underscores the importance of reliable benchmarks in evaluating how accurately generated images reflect the semantics of their textual prompt. However, (1) existing benchmarks lack the diversity of prompt scenarios and multilingual support, both essential for real-world applicability; (2) they offer only coarse evaluations across primary dimensions, covering a narrow range of sub-dimensions, and fall short in fine-grained sub-dimension assessment. To address these limitations, we introduce UniGenBench++, a unified semantic assessment benchmark for T2I generation. Specifically, it comprises 600 prompts organized hierarchically to ensure both coverage and efficiency: (1) spans across diverse real-world scenarios, i.e., 5 main prompt themes and 20 subthemes; (2) comprehensively probes T2I models' semantic consistency over 10 primary and 27 sub evaluation criteria, with each prompt assessing multiple testpoints. To rigorously assess model robustness to variations in language and prompt length, we provide both English and Chinese versions of each prompt in short and long forms. Leveraging the general world knowledge and fine-grained image understanding capabilities of a closed-source Multi-modal Large Language Model (MLLM), i.e., Gemini-2.5-Pro, an effective pipeline is developed for reliable benchmark construction and streamlined model assessment. Moreover, to further facilitate community use, we train a robust evaluation model that enables offline assessment of T2I model outputs. Through comprehensive benchmarking of both open- and closed-sourced T2I models, we systematically reveal their strengths and weaknesses across various aspects.

cs.CV↗
arXiv2026

Unified Personalized Reward Model for Vision Generation

Recent advancements in multimodal reward models (RMs) have significantly propelled the development of visual generation. Existing frameworks typically adopt Bradley-Terry-style preference modeling or leverage generative VLMs as judges, and subsequently optimize visual generation models via reinforcement learning. However, current RMs suffer from inherent limitations: they often follow a one-size-fits-all paradigm that assumes a monolithic preference distribution or relies on fixed evaluation rubrics. As a result, they are insensitive to content-specific visual cues, leading to systematic misalignment with subjective and context-dependent human preferences. To this end, inspired by human assessment, we propose UnifiedReward-Flex, a unified personalized reward model for vision generation that couples reward modeling with flexible and context-adaptive reasoning. Specifically, given a prompt and the generated visual content, it first interprets the semantic intent and grounds on visual evidence, then dynamically constructs a hierarchical assessment by instantiating fine-grained criteria under both predefined and self-generated high-level dimensions. Our training pipeline follows a two-stage process: (1) we first distill structured, high-quality reasoning traces from advanced closed-source VLMs to bootstrap SFT, equipping the model with flexible and context-adaptive reasoning behaviors; (2) we then perform direct preference optimization (DPO) on carefully curated preference pairs to further strengthen reasoning fidelity and discriminative alignment. To validate the effectiveness, we integrate UnifiedReward-Flex into the GRPO framework for image and video synthesis, and extensive results demonstrate its superiority.

cs.CV↗
arXiv2026

DynaDrag: Dynamic Drag-Style Image Editing by Motion Prediction

To achieve pixel-level image manipulation, drag-style image editing which edits images using points or trajectories as conditions is attracting widespread attention. Most previous methods follow move-and-track framework, in which miss tracking and ambiguous tracking are unavoidable challenging issues. Other methods under different frameworks suffer from various problems like the huge gap between source image and target edited image as well as unreasonable intermediate point which can lead to low editability. To avoid these problems, we propose DynaDrag, the first dragging method under predict-and-move framework. In DynaDrag, Motion Prediction and Motion Supervision are performed iteratively. In each iteration, Motion Prediction first predicts where the handle points should move, and then Motion Supervision drags them accordingly. We also propose to dynamically adjust the valid handle points to further improve the performance. Experiments on face and human datasets showcase the superiority over previous works.

cs.CV↗
arXiv2025

Distributed Information Bottleneck Theory for Multi-Modal Task-Aware Semantic Communication

Semantic communication shifts the focus from bit-level accuracy to task-relevant semantic delivery, enabling efficient and intelligent communication for next-generation networks. However, existing multi-modal solutions often process all available data modalities indiscriminately, ignoring that their contributions to downstream tasks are often unequal. This not only leads to severe resource inefficiency but also degrades task inference performance due to irrelevant or redundant information. To tackle this issue, we propose a novel task-aware distributed information bottleneck (TADIB) framework, which quantifies the contribution of any set of modalities to given tasks. Based on this theoretical framework, we design a practical coding scheme that intelligently selects and compresses only the most task-relevant modalities at the transmitter. To find the optimal selection and the codecs in the network, we adopt the probabilistic relaxation of discrete selection, enabling distributed encoders to make coordinated decisions with score function estimation and common randomness. Extensive experiments on public datasets demonstrate that our solution matches or surpasses the inference quality of full-modal baselines while significantly reducing communication and computational costs.

cs.IT↗
arXiv2025

Fine-Grained GRPO for Precise Preference Alignment in Flow Models

The incorporation of online reinforcement learning (RL) into diffusion and flow-based generative models has recently gained attention as a powerful paradigm for aligning model behavior with human preferences. By leveraging stochastic sampling via Stochastic Differential Equations (SDEs) during the denoising phase, these models can explore a variety of denoising trajectories, enhancing the exploratory capacity of RL. However, despite their ability to discover potentially high-reward samples, current approaches often struggle to effectively align with preferences due to the sparsity and narrowness of reward feedback. To overcome this limitation, we introduce a novel framework called Granular-GRPO (G$^2$RPO), which enables fine-grained and comprehensive evaluation of sampling directions in the RL training of flow models. Specifically, we propose a Singular Stochastic Sampling mechanism that supports step-wise stochastic exploration while ensuring strong correlation between injected noise and reward signals, enabling more accurate credit assignment to each SDE perturbation. Additionally, to mitigate the bias introduced by fixed-granularity denoising, we design a Multi-Granularity Advantage Integration module that aggregates advantages computed across multiple diffusion scales, resulting in a more robust and holistic assessment of sampling trajectories. Extensive experiments on various reward models, including both in-domain and out-of-domain settings, demonstrate that our G$^2$RPO outperforms existing flow-based GRPO baselines, highlighting its effectiveness and generalization capability.

cs.LG↗
arXiv2025

Implicit Semantic Communication Based on Bayesian Reconstruction Framework

Semantic communication is a novel communication paradigm that focuses on the transportation and delivery of the \emph{meaning} of messages. Recent results have verified that a graphical structure provides the most expressive and structurally faithful formalism for representing the relational semantics in most information sources. However, most existing works represent the semantics based on pairwise relation-based graphs, which cannot capture the higher-order interactions that are essential for some semantic sources. This paper proposes a novel Bayesian hypergraph inference-based semantic communication framework that can directly recover implicit semantic information involving high-order hyperedges at the receiver based on the pairwise relation-based explicit semantics sent by the transmitter. Experimental results based on real-world datasets demonstrated that the proposed SBRF achieves up to 90\% recovery accuracy of the high-order hyperedges based on the pairwise relation-based explicit semantics.

cs.IT↗