Searcharxiv⌕ Search

arXiv subjects

Yuanxing Zhang

Publications and source records attributed to Yuanxing Zhang.

At least 19 recordsLinked to original sources
arXiv2026

Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling

Video generation has progressed from isolated clips to coherent short-form audiovisual sequences, and the bottleneck is shifting from rendering to semantic control. This report summarizes the observations and insights on multimodal understanding gained from successive generations of Kling. We argue that generation quality is the projection of multimodal understanding through the entire data--conditioning--alignment--evaluation chain, and we examine this chain module by module. Kling-MLLM, a shared multimodal foundation model that unifies image, video, audio, synchronized audio--video, and interleaved inputs, is specialized for each downstream module. Because a DiT is trained on far fewer training samples than a language model, we treat captioning as a semantic contract that maximizes description density, and extend it to reference-grounded captioning that makes reference bindings explicit. Prompt enhancement translates user intent into this caption distribution: basic PE is derived from captions of compelling videos and refined with text-level and generator-in-the-loop reinforcement learning, while agentic PE refines the story and retrieves compelling examples. We show that a reliable text encoder comes from perceptual training rather than from stronger language ability, and that candidates can be screened from text alone before end-to-end training. Reward modeling pairs a general reward model for explainable, localized critiques with a decision reward model for fast multidimensional scoring, treating perceptual bandwidth as a first-class design parameter. Finally, we review task-specific automatic evaluation, focusing on protocols that expose scoring shortcuts and help trace failures to their upstream source. We hope these lessons offer practical guidance for building the understanding stack behind controllable video generation.

cs.CV↗
arXiv2026

Reviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning

Multimodal large language models (MLLMs) can generate detailed video captions, yet they may overemphasize minor details while overlooking essential context and key events. We argue that not all visual evidence deserves equal attention, as the importance of visual information depends on the content of each video. Motivated by this observation, we propose Reviso, an agentic video captioning framework that learns what to observe and how to gather relevant visual evidence. From a low-frame-rate global preview, Reviso constructs a hierarchical Context--Focus--Points (CFP) observation plan that identifies the video context, prioritizes key aspects, and defines concrete observation targets and corresponding tools. Guided by this plan, Reviso performs goal-directed active perception by selectively revisiting temporal segments and combining tools for fine-grained inspection. It interprets the acquired evidence, updates its plan as needed, and integrates global and local information to generate the final caption. To learn this observation strategy, we develop a verification-guided pipeline that constructs high-quality training trajectories through factual verification and teacher-guided refinement. We further train Reviso using Group Relative Policy Optimization (GRPO), incorporating a key-fact reward for caption quality, a Plan Alignment Reward (PAR) for identifying important observation targets, and an Unproductive Tool-Call Penalty (UTCP) that adjusts observation-cost penalties based on caption quality. Experiments across four video captioning benchmarks show that Reviso outperforms the evaluated open-source baselines, while its generated captions better support downstream video question answering. These findings highlight the effectiveness and potential of priority-guided active observation for video captioning.

cs.CV↗
arXiv2026

CodeCap-Bench: Can Code Serve as a Good Video Caption?

Video captioning aims to preserve visual information through compact descriptions, predominantly using natural language. However, precisely expressing fine-grained spatial structures and temporal dynamics in natural language often leads to lengthy and potentially ambiguous descriptions. In this work, we explore Code as Video Caption, a paradigm where executable programs serve as a complementary representation of visual content through graphical primitives, layout rules, and functions of time. To examine whether code captions effectively preserve video information, we compare them with natural language captions on downstream question answering and video reconstruction tasks. Our results show that code captions achieve superior reasoning accuracy and reconstruction fidelity. Despite these advantages, realizing the potential of code captioning depends on whether current multimodal large language models (MLLMs) can generate faithful code captions. To systematically assess this capability, we introduce CodeCap-Bench, which comprises 323 videos spanning five categories of structured 2D content, along with fine-grained annotations and a multi-level evaluation framework. Extensive experiments reveal that while leading proprietary MLLMs demonstrate promising code captioning capabilities, they still struggle to faithfully capture complex temporal dynamics, with open-source models lagging substantially behind.

cs.CV↗
arXiv2026

Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos

Recent advances in video generation have made synthetic videos increasingly realistic, placing greater demands on reliable AI-generated video detection. Existing artifact-based detectors typically identify generation artifacts as evidence for source prediction, yet they may either fail to recognize subtle artifacts or reach the correct source decision without faithfully identifying the evidence underlying it. In this work, we systematically investigate how to design and train effective artifact detectors and formulate artifact detection as a structured process comprising three complementary capabilities: Inspection Planning, which determines what should be examined; Evidence Verification, which verifies whether the inspected content exhibits genuine generation artifacts; and Evidence Aggregation, which integrates the verified evidence into the final source decision. Building on this formulation, we introduce Verus-Insight, trained with human-anchored full-process supervision and progressive capability training to strengthen both fine-grained artifact detection and video-level detection. We further introduce Verus-Bench, a benchmark with fine-grained human annotations of perceptible artifacts for evaluating artifact detection. Extensive experiments across diverse benchmarks demonstrate that Verus-Insight achieves strong performance in both fine-grained artifact analysis and AI-generated video detection, with substantial gains in recovering human-perceived artifacts. Further analyses reveal that the three capabilities are complementary yet distinct, and that Verus-Insight more reliably converts relevant inspection targets into supported artifact evidence without increasing spurious artifact claims.

cs.CV↗
arXiv2026

Think Before You Score: Thinking Reward Model for Visual Generation

Visual reward models are essential for evaluating and improving visual generation models, yet existing approaches typically map task conditions and candidate outputs directly to scalar rewards, leaving implicit what should be evaluated for each individual case. We introduce Think Before You Score, a paradigm that explicitly determines what matters for each case before judging how well the candidate performs. Following this principle, we propose the Thinking Reward Model (TRM), which formulates case-adaptive rubrics, performs rubric-guided assessment, and produces fine-grained pointwise rewards. We further observe that conventional pairwise preference optimization can induce score polarization, and introduce Pairwise Dual-Group Relative Policy Optimization (PD-GRPO), which leverages pairwise supervision to improve reward discrimination while preserving fine-grained pointwise scoring. Extensive experiments on image generation and editing reward-modeling benchmarks demonstrate that TRM achieves state-of-the-art performance among open-source reward models while remaining highly competitive with proprietary alternatives. Moreover, using TRM as a reward for reinforcement learning consistently improves diverse visual generation models, demonstrating that its fine-grained, case-adaptive rewards translate into effective optimization signals for visual generation.

cs.CV↗
arXiv2026

FlowCred: Hierarchical Credit Assignment and Functional Coordination for Joint Text-to-Video Post-Training

Prompt optimization and generator post-training are two complementary ways to improve text-to-video (T2V) generation, and recent systems increasingly train both modules jointly. However, optimizing a prompt policy and a video generator from the same terminal reward creates two ambiguities: prompt quality is confounded with stochastic generation, and the two modules may realize overlapping local improvements. We introduce FlowCred, a two-level framework for joint T2V post-training. First, hierarchical credit assignment uses matched prompt-seed rollout grids to separate prompt-level credit from prompt-conditioned generator residuals under shared randomness. Second, functional coordination probes alternative current-policy prompts at states from actual generation trajectories, providing generator-aware evidence for prompt optimization while selectively attenuating generator updates already supported by conditioning changes. Across multiple T2V benchmarks, FlowCred consistently improves matched joint-training baselines. On LTX-2.5, FlowCred improves a strictly matched joint-training control from 61.47 to 64.46 on T2V-CompBench and from 55.58 to 58.08 on StoryEval, without increasing decoded-video or reward-model-call budgets. Factorial and realized-update analyses show complementary contributions from prompt shaping and generator routing, while human evaluation and transfer across backbones and updater families provide further supporting evidence.

cs.CV↗
arXiv2026

VARI: Robust Text-to-Video Generation via Group-Structured Intent Alignment

Modern text-to-video (T2V) models generate visually compelling videos, yet meaning-preserving changes in prompt wording can substantially alter semantic realization and overall quality. Existing prompt rewriting modifies the inference input, whereas conventional post-training constructs supervision from one prompt formulation at a time; neither explicitly optimizes reliability across equivalent forms. We introduce VARI (Verified Alignment over Representations of Intent), a group-structured framework that treats automatically verified formulations of the same visual intent as a shared supervision unit. VARI builds matched form-seed rollout pools, cross-scores each video against all forms, and applies a wording-independent structured intent audit to identify valid realizations and hard semantic failures. Group-Consistent Distillation (GCD) aligns every verified form with interchangeable valid realizations, while Form-Contrastive Flow-DPO (FC-DPO) learns group-level preferences from audited positive-negative pairs, prioritizing same-seed, different-form contrasts. On HunyuanVideo-1.5, VARI attains the highest T2V-CompBench, VBench, and StoryEval scores among the evaluated methods. On prompt-form extensions of T2V-CompBench and VBench, it improves weakest-form alignment over the strongest prompt-level baselines by 2.45 and 3.55 points and reduces cross-form drop by 30.5% and 32.2%, respectively, while preserving visual quality. Human evaluation, natural-caption controls, prompt-enhancement experiments, diversity analyses, and transfer to LTX-2.3 further support the robustness and transferability of these gains, while VARI requires no additional inference-time module.

cs.CV↗
arXiv2026

Flux-OPD: On-Policy Distillation with Evolving Contexts

Large language model training in open-ended domains lacks verifiable rewards, making task preferences difficult to formalize as effective supervision. Contexts derived from task feedback can provide richer supervision, yet fixed contexts cannot adapt as the student evolves, motivating contexts that evolve with student performance. However, directly using evolving contexts as in-training supervision results in unstable distillation targets and conflicting distributions, requiring mechanisms to stabilize the target and downweight conflicts. In this paper, we characterize context distillation through a reverse-KL decomposition, showing that the student is distilled toward the geometric mean of context-conditioned teachers, while the objective contains a conflict term measuring disagreement among these teachers. Motivated by this characterization, we propose Flux-OPD, an OPD paradigm that uses evolving contexts as in-training supervision to incorporate contextual signals derived from task feedback. Flux-OPD treats differences between context-conditioned and context-free teachers as contextual difference signals, injects them as contextual corrections into the context-free teacher, and weights the correction strength using the conflict term. Experiments show that Flux-OPD achieves the best results among OPD paradigms, highlighting the potential of combining teacher supervision with evolving contexts as in-training supervision.

cs.LG↗
arXiv2026

PIGEONS: Incremental Long-Video Captioning with Persistent Identity Gallery and Evolving Overarching Narrative Summary

Detailed video captioning has become an essential semantic interface for multi-modal understanding and generation. While existing methods mainly target short videos, extending them to long videos remains challenging, primarily due to limited context windows of current video understanding models. A naive solution is to adopt segment-wise captioning followed by concatenation, yet this paradigm often suffers from inconsistent subject references and fragmented long-range narratives. To mitigate these issues, we introduce PIGEONS, an incremental long-video captioning model built upon a Persistent Identity Gallery and an Evolving Overarching Narrative Summary. Before caption generation, PIGEONS scans the entire video to construct an identity gallery that captures key subjects along with their visual references, thereby providing a stable referential anchor. The model then performs clip-by-clip captioning conditioned on the persistent gallery and an evolving overarching narrative summary, which compactly maintains and updates essential long-range contextual information after each captioning step. To enable these capabilities, we develop a three-stage training strategy that integrates supervised fine-tuning and reinforcement learning. Extensive experiments demonstrate that PIGEONS markedly improves long-video captioning performance, achieving superior accuracy, completeness, and subject referential consistency over existing methods, while maintaining competitive performance on short-video captioning.

cs.CV↗
arXiv2026

EmoTrace-Bench: Diagnosing Emotional Expression in Text-to-Video Generation through Controlled Cues and Intensity

Text-to-video (T2V) models are increasingly used to generate videos with targeted emotional expressions, yet existing evaluation methods mainly rely on holistic video-text alignment and provide limited insight into whether failures arise from target-emotion expression, intensity control, or specific affective cues. We introduce EmoTrace-Bench, a fine-grained diagnostic benchmark that controls emotion intensity and selected affective cues in prompts and evaluates generated videos at multiple levels. EmoTrace-Bench contains 448 controlled prompts covering eight emotions, two intensity levels, and diverse cue conditions. Using 12 T2V models, we generate 5,376 videos and evaluate target-emotion presence, perceived intensity, and ten audiovisual dimensions of emotional expression with an automated evaluator calibrated and validated against human annotations on a subset of the data. Results reveal substantial differences across models and prompt designs. Prompts that explicitly describe a character's emotional reaction are followed more reliably than prompts that describe only events or scenes, whereas adding more affective cues or using more explicit cinematic audiovisual language does not consistently improve emotional generation. These results illustrate how aggregate alignment scores may overlook localized differences in target-emotion expression, intensity control, and cue realization. EmoTrace-Bench provides a traceable and interpretable framework for diagnosing emotional video generation without modifying existing generation pipelines, and we release the prompts and the automated evaluation rules.

cs.CV↗
arXiv2026

Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling

Recent image editing models have achieved remarkable progress in instruction following, multimodal understanding, and complex visual editing. However, existing benchmarks often fail to faithfully reflect human judgment, especially for strong frontier models, due to limited task difficulty and coarse-grained evaluation protocols. In parallel, reward models have become increasingly important for RL-based image editing optimization, yet existing reward model benchmarks still rely on unrealistic evaluation settings that deviate from practical RL scenarios. These limitations hinder reliable assessment of both image editing models and reward models. To address these challenges, we introduce Edit-Compass and EditReward-Compass, a unified evaluation suite for image editing and reward modeling. Edit-Compass contains 2,388 carefully annotated instances spanning six progressively challenging task categories, covering capabilities such as world knowledge reasoning, visual reasoning, and multi-image editing. Beyond broad task coverage, Edit-Compass adopts a fine-grained multidimensional evaluation framework based on structured reasoning and carefully designed scoring rubrics. In parallel, EditReward-Compass contains 2,251 preference pairs that simulate realistic reward modeling scenarios during RL optimization.

cs.CV↗
arXiv2026

Fine-Grained Caching for Diffusion Transformers with Few Calibration Conditions

Diffusion transformers require repeated denoiser evaluations, making image and video generation computationally expensive. We propose a training-free framework that uses a few calibration conditions to construct a fixed, fine-grained module-reuse schedule without schedule search. The design is motivated by an empirical effect along deterministic sampling trajectories: with initial noise fixed, condition-dependent deviations in several module outputs evolve similarly across adjacent steps, so temporal differencing attenuates much of their variation. We term this effect Conditional Common-Mode Rejection (CCMR). Motivated by this observation, we rank timestep--layer--module locations using normalized ratios of consecutive feature displacements and construct a Cache Book through two-stage calibration. The second stage updates a scorer-only reference with each provisional bit after recording its indexed score, while retaining full-compute trajectories. At inference, the fixed schedule requires no per-input policy estimation and can be nested within fixed step-wise cache policies. Module caching alone achieves $1.66$--$1.72\times$ speedup on the evaluated image models and $1.54$--$1.68\times$ on the video models. Combining it with MagCache or SeaCache provides further acceleration at a model-dependent cost in paired fidelity.

cs.CV↗
arXiv2026

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

The fundamental goal of agentic visual reasoning is to improve the success rate of multimodal large language models (MLLMs) on complex tasks. We rethink agentic visual reasoning through two key dimensions of tool use: Mode Adaptiveness and Tool Effect. Mode Adaptiveness characterizes whether an MLLM recognizes when tools are necessary and invokes them accordingly, avoiding unnecessary computational overhead while improving performance on problems requiring tool assistance. Tool Effect characterizes whether tools extend the model's capabilities on problems unsolvable through tool-free reasoning without introducing errors on problems it can already solve. Our analysis quantifies these properties and reveals that existing models exhibit limited Mode Adaptiveness, while tool-use gains on hard examples are largely offset by harm on easy ones. Motivated by these observations, we propose Beacon, a novel agentic visual reasoning model trained with supervised fine-tuning (SFT) and reinforcement learning (RL). Its RL stage combines Necessity-Aware Adaptive Reward and Hint-Guided Capability Expansion. Necessity-Aware Adaptive Reward encourages tool-free solutions when they succeed while preserving full reward for successful tool use when tool-free rollouts fail. Hint-Guided Capability Expansion uses verified, answer-free expert hints to recover learning signals from all-wrong rollout groups, aiming to extend tool-use capability on the hardest problems. Across 13 benchmarks, Beacon achieves the highest average score among the evaluated open-source models and ranks first on 11 benchmarks. On five diagnostic benchmarks, it improves the average tool-available accuracy over its tool-free accuracy by 1.96 points and achieves the largest tool-gain minus tool-harm score (+3.14 points). These results show Beacon's advanced performance, Mode Adaptiveness, and the net benefit of tool use.

cs.CV↗
arXiv2026

HiRAE: Hierarchical Representation Autoencoding with Residual Budgets

Pretrained visual representations support image generation, but may not fully preserve the fine-grained details needed for faithful reconstruction. Meanwhile, intermediate encoder layers contain complementary visual details, but learning to fuse them for reconstruction can produce a latent distribution that is difficult to model. Existing fusion methods require empirical tuning of layer selection or staged optimization of fusion and decoding, increasing configuration effort or training complexity. We introduce HiRAE (Hierarchical Representation Autoencoder), which learns a hierarchical fusion framework over the full encoder hierarchy to improve reconstruction fidelity while maintaining compatibility with generative modeling. HiRAE groups encoder layers by depth and learns residual corrections to the deepest representation. Group-wise norm caps bound these corrections relative to the deep anchor, with tighter budgets for shallower groups. Our HiRAE-24 preserves the latent token count and channel dimension. On ImageNet-256, HiRAE-24 reduces reconstruction FID from 0.299 to 0.209 relative to RAEv2 while maintaining competitive guided generation quality. For text-to-image generation, HiRAE-24 improves alignment over RAEv2 on GenEval, DPG-Bench, and GenAI-Bench both before and after supervised fine-tuning. Under the same generator-training and evaluation protocol, post-fine-tuning GenEval increases from 84.86 to 87.70.

cs.CV↗
arXiv2026

SkillPE: Creativity-Oriented Cinematic Skill Evolution for Text-to-Video Prompt Engineering

Achieving high-quality, cinematic results in text-to-video generation remains challenging for non-experts, whose prompts often lack professional narrative and creative design. We propose SkillPE, a prompt engineering (PE) framework that evolves reusable cinematic skills from expert-authored seeds. SkillPE represents shot logic, composition, lighting, sound design, and other filmmaking cues in a fine-grained format, and retrieves movie references categorized as resonators (good matches), dissonants (weak matches), and divergents (creatively useful near-misses). The first two refine when and how a skill should be applied, while divergents inspire alternative cinematic realizations at different degrees of modification while preserving the user intent. Candidate skills are assessed through generated videos along prompt fidelity, cinematic quality, narrative appeal, and creativity to construct the final skill libraries. Experiments on StoryEval and VBench show improvements of up to 1.40 points over the strongest external baseline and 0.51 points over seed skills on 7-point four-dimensional evaluation, while remaining competitive on benchmark-native metrics. Overall, SkillPE offers a practical approach to balancing fidelity and creativity in cinematic text-to-video generation. Code is available at https://github.com/Ais0n/SkillPE .

cs.CV↗
arXiv2026

From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models

Video generation has advanced to produce visually compelling and temporally coherent results. Yet, whether these models can genuinely think with video--executing symbolic rules, respecting physical laws, and pursuing intentional goals--remains an open question. Existing benchmarks only partially address this, often conflating visual quality with cognitive correctness. We introduce VWG-Bench (Video World Generalist Benchmark), a comprehensive benchmark spanning 9 reasoning dimensions and 38 fine-grained tasks. To enable precise diagnosis, we design a three-level VLM-as-Judge protocol that independently assesses video-level fluency, task-level rule adherence, and sample-level goal realization. Evaluations of leading models reveal a striking gap: while models achieve strong rendering scores, they consistently fail on logic-heavy and rule-constrained tasks. To address this, we propose Vid-PRE (Video Prompt Reasoner and Enhancer), a model-agnostic prompt rewriter that offloads the cognitive burden of reasoning to a dedicated VLM. Trained via reinforcement learning with purely text-based rewards, Vid-PRE produces concise, constraint-aware prompts without the instability of video-level reward signals. Experiments show that Vid-PRE yields substantial reasoning improvements across multiple generators without architectural modifications. Together, VWG-Bench and Vid-PRE offer a rigorous diagnostic lens and a scalable path toward true think-with-video capabilities. All data and code are publicly available at https://huggingface.co/datasets/KlingTeam/VWG-Bench.

cs.CV↗
arXiv2026

FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models

Preference alignment for flow and diffusion models now spans online reinforcement learning and offline preference optimization, but the relation between these methods remains unclear. In particular, existing forward-process alignment methods require fresh samples from the current model, while offline methods based on fixed preference pairs rely primarily on positive-only fine-tuning or DPO-style likelihood-ratio surrogates. We organize these approaches through a divergence-based framework and introduce FlowCPO, an offline forward-KL objective that uses both preferred and dispreferred samples without online rollouts. For linear interpolation, we show under explicit regularity conditions that the forward-KL objective is bounded by a contrastive flow matching loss, yielding a tractable surrogate on fixed data. We further show that this loss is nonnegative, whereas the signed regression loss of simplified FlowDPO can be unbounded below. In the in-domain setting, FlowCPO achieves higher mean GenEval and OCR scores than the evaluated baselines, reaching 0.84 and 0.87 versus 0.81 and 0.74 for FlowDPO at CFG 3.0. In the out-of-domain setting, the results are mixed, with the best GenEval result but lower reward scores than RFT on several metrics.

stat.ML↗
arXiv2026

Human-Centric Image Captioning with Subject-Centered Spatial Understanding

While multimodal large language models (MLLMs) achieve remarkable performance on generic image captioning, they frequently suffer from structural hallucinations in human-centric scenarios. Accurately modeling human subjects is foundational for critical downstream applications, such as accurate avatar/video/image generation and fine-grained human action understanding. However, these tasks require highly precise subject-centered spatial grounding, such as distinguishing egocentric left/right laterality and maintaining correct anatomical-object bindings. Although catastrophic for structural integrity, these localized spatial inversions are often overshadowed by overall descriptive metrics in existing benchmarks. To systematically expose and quantify this bottleneck, we introduce SPACE (Subject-centric Poses, Appearance, and Characteristics Evaluation), a benchmark designed to evaluate subject-centered spatial understanding. On SPACE, we reveal that despite strong generic perception, current MLLMs consistently fail to ground descriptions in the subject's intrinsic frame of reference. To bridge this gap, we propose a specialized data construction and alignment pipeline. We first extract structured spatial hints from fine-grained body-part localization to guide a two-stage caption rewriting process, yielding highly spatially-faithful training data. Furthermore, we design a rubric-based reward for Group Relative Policy Optimization (GRPO) that explicitly penalizes structurally critical spatial errors during alignment. Extensive experiments on SPACE demonstrate our framework significantly improves human-centric caption quality, particularly in subject-centered spatial reasoning, achieving performance competitive with strong closed-source models. Our benchmark and code are available at https://github.com/JHang2020/SPACE-Eval.

cs.CV↗