多模态生成与编辑

Reliable video generation requires more than high-quality frames to form a coherent story: a model must maintain a persistent state, transporting visual attributes such as identity, scene layout, motion, and fine details across time. Existing training-free methods mainly strengthen cross-frame attention or analyze local attention entropy, but these views do not reveal whether temporal interactions stay in a healthy transport regime. In this work, we study video generation through the perspective of Temporal State Transport. We introduce Spectral Tension, a signed diagnostic that compares local attention diffuseness with global spectral diversity, and use it to identify two opposite temporal failures: fragmented transport and over-mixing hotspots. Based on this diagnosis, we propose Spectral Transport Homeostasis, a training-free regulator that softly corrects pathological temporal states while largely preserving balanced ones. Experiments on pretrained video generation models show that the original model often occupies imbalanced temporal regimes, whereas our method selectively applies larger corrections to the worst temporal hotspots and improves temporal consistency and visual quality without finetuning. Code: https://github.com/lytang63/temporal-state-transport

Unified multimodal models integrate visual understanding and generation within a single network, yet the two capabilities are commonly optimized as separate tasks. We introduce Generative Grounding Feedback(GGF), a self-evolving post-training framework that uses only text prompts and the model's own visual experience. Given a prompt, the model first generates a visual ``dream.'' Flow-level feedback compares text-, image-, and repair-conditioned predictions at the same noisy latent state, transferring image-grounded generation directions to the prompt condition. Dream replay grounding replays this dream through captioning and re-imagination, training claim-level evidence to remain consistent across the replay while separating unrelated visual experiences. Jointly optimized, these two directions let generation provide visual grounding for understanding and understanding refine subsequent generation without paired image--text supervision. Experiments across unified models with different understanding--generation integration designs show consistent improvements in text-to-image generation together with modest gains in visual understanding.

Recent advances in video generation have made prompt-based control increasingly central to AIGC video generation. Prompts specify what a video should depict and how it should be represented, controlling factors such as visual style or camera behavior. Understanding this recoverability is important both for creative reuse and editing, and for assessing prompt leakage risks. However, existing video understanding benchmarks do not measure this capability: a caption may describe what is visible, but a replayable prompt must recover the generation-relevant controls needed to reproduce the video. To address this gap, we introduce VI-Bench, a benchmark built from 16.1 million real-user prompts and 900 human-verified AIGC videos. VI-Bench spans three progressively harder settings, namely single-shot semantic grounding, control over style and camera behavior, and multi-shot compositional inversion, and evaluates five generation-critical dimensions: subject, action, scene, style, and camera. We evaluate 18 representative VLMs, including 2 proprietary and 16 open-source models on VI-Bench, using an Inversion Score that measures prompt-level alignment with the original prompt and video-level fidelity of the regenerated video. The results reveal substantial limitations: even the strongest model achieves only 0.632 on Inversion Score, performance degrades sharply as samples require richer control and multi-shot reasoning, and models often produce plausible prompts whose regenerated videos deviate from the reference. These findings show that video prompt inversion is a distinct and under-evaluated capability requiring models to transform visual understanding into replay-stable generative control.

Diffusion models have become a core paradigm for multimedia generation, offering powerful concept-driven controllability for personalization, semantic editing, and selective unlearning. However, as semantic control extends beyond natural-language prompts to learned embeddings and intervention pipelines, the safety and governance of these systems become increasingly difficult to evaluate in a unified manner, especially for safety-sensitive, identity-linked, and other privacy-relevant concepts. Existing studies mainly rely on heuristic audits, adversarial probing, or task-specific erasure benchmarks, and therefore provide limited support for systematic comparison across models, conditioning channels, and deployment conditions. We present a concept-level probabilistic audit and reporting framework for diffusion models. We formalize governance-relevant concept behaviors as Bernoulli semantic events induced by stochastic generation, and define a Concept Risk Operator that maps model-channel configurations to structured risk profiles, enabling comparison across prompting interfaces, learned embedding channels, models, and recorded conditions. We apply sample-level post-hoc calibration and configuration-level risk aggregation, and show that probability error can change thresholded actions near policy boundaries. Experiments on SD1.5, SD2.1, and SDXL reveal consistent yet non-uniform operational risk patterns across concept families, channels, recorded conditions, and shifted protocols. In particular, embedding-based access and obfuscated prompts expose risks often understated by standard-prompt evaluation. A pooled multi-protocol calibrator improves held-out probability reliability, but we do not claim transfer from a standard-only calibrator. CLRC provides a common audit schema for probabilistic and decision-aware governance of multimedia generation systems.

Chunk-autoregressive video world models typically condition each generated chunk on one action. An action received during sampling must therefore wait for the next chunk, condition future solver evaluations on a state produced under the previous action, or trigger rollback that repeats completed evaluations. We introduce ActionSplice, an inference framework that formulates this problem as Counterfactual State Transport (CST). A lightweight corrector transports the interrupted backbone-native representation toward the matched state induced by the revised action at the same solver step. The world model and sampler remain frozen, and sampling resumes without replaying completed evaluations. The retargeting variant $\mathrm{CST}*{R}$ updates the entire active chunk, while the temporal-splicing variant $\mathrm{CST}*{T}$ preserves a temporal prefix and updates only the suffix. Across minWM-Wan Action2V and HY-WM1.5, $\mathrm{CST}*{R}$ reduces rollback-relative LPIPS by 61.5% and 75.9% relative to direct condition swapping. $\mathrm{CST}*{T}$ reduces suffix LPIPS by 56.1% and 77.5%, respectively, while providing $2.73\times$ and $1.69\times$ pixel-ready speedups over waiting. Under the HY-WorldPlay protocol, $\mathrm{CST}_{R}$ obtains a PSNR of 25.66 dB, an SSIM of 0.6902, and an LPIPS of 0.1337 against the original rollout.

World models take multimodal inputs like text, photos, and diagrams to generate dynamic scenes in accordance with the laws of physics, thus opening a compelling application: fusing multimodal legal evidence to re-create a crime scene and re-enact how an offence could have been committed. However, feeding the raw, unorganized evidence into a world model fails in forensic use: it silently drops evidence, glosses over contradictory testimony, and produces motion that violates the evidentiary record. This paper presents VeriScene, an agent that orchestrates the world model: it reconstructs crime scenes from forensic photographs and witness statements of varying reliability, keeping every claim traceable to evidence and every motion physically plausible. VeriScene iteratively fuses the evidence into a cited narrative under an auditing loop, verifies the hypothesized dynamics via probe rollouts in the world model with corrective constraint injection, and renders the offence as a re-enactment video from a fused keyframe. On a benchmark of 25 crime scenarios across 7 physically-driven case types (139 forensic-style photographs and 65 statements with planted unreliability), VeriScene attains 0.9014 evidence coverage and 0.7217 factual consistency (0-1 scale) on the 20 test scenes, outperforming an end-to-end multimodal-LLM baseline by 20.35% in factual consistency and 34.88% in temporal coherence, while generalizing across four LLM orchestration backends at USD 1.82 per scene.

Recent multi-shot audio-video generators can produce increasingly coherent and cinematic outputs, but coherence does not imply the ability to execute editing techniques. Professional editing depends on shot structure, transition grammar, audio-video cut relations, and montage, yet existing benchmarks largely rely on proxies such as content quality, synchronization, or physical plausibility, systematically missing whether such editing instructions are actually executed. We introduce CutCraft, the first benchmark for editing-technique execution in multi-shot audio-video generation. CutCraft extends structured multi-shot prompts with explicit editing specifications and is paired with a hierarchical hybrid evaluation framework that combines shot-structure alignment, expert-model metrics, tool-grounded multimodal judgment, and rubric-based question answering. Beyond evaluation, we design an agentic editing baseline that decomposes generation into planning, shot-level synthesis, and post-hoc composition, explicitly realizing editing semantics such as J-cuts, L-cuts, and transition timing. Across 13 state-of-the-art closed- and open-source models, CutCraft reveals a consistent gap between coherence and editing-technique execution: current systems often produce plausible multi-shot videos yet fail to execute editorial instructions reliably. We find unstable shot structures, weak control of transition execution, and sharp degradation on higher-order montage, while aesthetic quality is only weakly correlated with editing-technique compliance. The benchmark and metrics, and the editing agent baseline are available at https://github.com/AlibabaResearch/cut-craft-bench.

A growing body of work establishes that large language models are not mere statistical memorizers, but are capable of in-context learning: performing inference at test time using only examples provided in the prompt, without any parameter updates. Prior theoretical work has shown that this capability extends to supervised learning tasks such as linear regression. We prove that in-context learning extends further to data generation: frozen transformers can simulate iterative generative samplers from in-context samples. We first show that transformers can realize closed-form and smoothed closed-form diffusion samplers. The construction identifies a concrete generative role for softmax attention: it computes responsibility weights and weighted empirical averages, while feedforward layers implement Euler updates. To empirically relate these constructions to pretrained language models, we study semantic-topic sampling: prompts consisting of words drawn from a common semantic category, such as animals, foods, or cities. Across transformer layers, the normalized hidden states exhibit a two-stage geometry: they move toward a uniform spherical reference in intermediate layers and then return to structured, topic-dependent representations near the output. We further measure an interacting-particle energy on these hidden-state clouds and observe the same U-shape pattern. We then prove that transformers can approximate an energy-based sampler, constructing the same U-shape energy across the layers.

Generating human-centric videos that preserve both visual identity and person-specific expressive behavior remains a fundamental challenge. In addition to reproducing appearance, a model must replicate the facial behaviors that characterize how a subject expresses emotion over time. However, most state-of-the-art methods condition generation on a single reference image, which contains no information about these temporal dynamics. As a result, they tend to preserve the subject's visual identity but often produce expressions with limited variation and weak subject specificity. To mitigate this issue, we introduce BEACON, a lightweight framework for person-specific video generation that produces more expressive videos by disentangling visual identity from expressive behavior. BEACON conditions generation on two complementary signals: a reference image encoding the identity and a reference video capturing subject-specific facial dynamics. By conditioning on these complementary signals, BEACON generates videos that better preserve both the subject's appearance and characteristic facial dynamics, while also supporting identity-expression transfer. Our experiments on the MEAD and RAVDESS datasets show that by fine-tuning on approximately 2,000 pairs and updating about 1% of the pretrained Wan video diffusion model, BEACON improves facial expressivity over state-of-the-art video generation methods while maintaining competitive identity preservation.

Learning physically plausible dynamics from visual observations is essential for interactive world models and embodied agents. However, modeling real-world deformable objects remains challenging because their dynamics often arise from complex, spatially heterogeneous material responses. To address this challenge, we propose PhysReal, a video-driven framework for learning and simulating the underlying physics of real deformable objects. PhysReal integrates a spatially varying hybrid expert-neural constitutive model with a differentiable MPM simulator and 3DGS renderer. Analytical expert models provide interpretable physical priors, while neural constitutive residuals capture material responses beyond predefined formulations. Spatially distributed patches parameterize the constitutive field, enabling a continuous representation of local material variations. To organize the identification of this model from sparse visual observations, we adopt a progressive curriculum that sequentially optimizes global material properties, spatially varying local parameters, and neural constitutive residuals, together with complementary motion and mask supervision. Extensive experiments on diverse deformable-object interactions demonstrate that PhysReal achieves superior performance in dynamic reconstruction and future-state prediction, while showing strong potential for downstream robotic applications.

We introduce FlexMoGen, a novel framework for flexible human motion synthesis conditioned on both natural language descriptions and motion style references. Text prompts are effective at defining semantic content, but they are often limited in capturing fine-grained style details such as timing, limb articulation, and expressive dynamics. A style example clip supplements the text by conveying these nuanced motion characteristics directly, enabling the model to preserve high-level intent while reproducing the desired stylistic traits. Given a text prompt and a style example clip, FlexMoGen generates high-quality motions that preserve semantic content while faithfully reflecting the target style, offering users greater control over the animation generation process. Unlike prior methods that rely on discrete style labels and do not generalize to long or multi-style generation, FlexMoGen learns a variational style encoder without style supervision and supports long, time-varying, multi-style synthesis. Our framework jointly pre-trains the style encoder and a text-to-motion latent diffusion model within a unified architecture, modulating motion style through a lightweight adaptation module. It integrates an efficient relative positional encoding scheme and is trained on both stylized and non-stylized datasets, enabling strong generalization to unseen text-style combinations. Experiments show that FlexMoGen achieves the best balance between content fidelity and style reflection.

Compared with relying solely on initial observations and language instructions, predicting goal images with generative models as high-level visual guidance can significantly enhance the robustness of Vision-Language-Action (VLA) models. However, most existing foundation models have not systematically incorporated goal image conditioning due to the high computational training cost. To this end, we propose Goal-Injected Fine-Tuning (GIFT), a lightweight and efficient fine-tuning framework that seamlessly integrates generated goal images into multiple representative pretrained VLA models. Our approach introduces goal image features into observations via a zero-initialized convolution which progressively grows parameters from zero and prevents harmful noise from disrupting the pretrained policy during fine-tuning. As training proceeds, goal information is gradually incorporated, enabling efficient goal understanding without disrupting model stability. We further introduce a refined image editing method to generate semantically and visually consistent goal images from initial observations and task instructions. Experiments show that goal-aware VLA models achieve substantial performance gains across tasks: with only a single epoch of fine-tuning, GIFT outperforms the base model by 6.0% and 13.4% on two SIMPLER settings, and by 4.7% on LIBERO, demonstrating both efficiency and effectiveness.

Localizing a font into new languages is a highly intricate task requiring precise design adaptation of glyphs, color/texture, and spacing/kerning, from source to target languages. Most existing methods focus on single glyph generation with limited capability in handling multilingual font rendering. In this work, we propose LoGAN, a VLM-based agentic framework for few-shot multilingual font localization, which takes in a small number of individual glyphs from a font or letters from a logo and uses them to generate complete character sets in other languages. LoGAN breaks down this task into multiple components: a glyph-level diffusion model, a style finetuning module, a spacing and kerning transfer algorithm, and a texture expansion model, with a VLM agent coordinator. LoGAN achieves broad language coverage for font localization with various styles, including Chinese/Korean/Japanese (CJK). We evaluate our approach on both font and real-world logo datasets spanning more than 27 languages and compare it against both specialized font generation and state-of-the-art image editing models with strong text rendering capabilities (e.g., FLUX, Nano-Banana). Our approach yields higher glyph fidelity while maintaining better style, texture, and kerning consistency according to both quantitative and qualitative evaluations.

World models increasingly serve as the predictive core of model-based reinforcement learning agents, enabling them to simulate future dynamics and reason over imagined trajectories before acting. Their substantial training demands make pretrained world models attractive for distribution and reuse, exposing downstream systems to model supply chain threats. Backdoor attacks offer a targeted and stealthy means of exploiting such supply chains, yet their threat to interactive world-model agents remains largely unexplored. To fill this gap, we present TrojanWorld, a backdoor framework for world-model agents that induces attacker-specified behavior by steering internal imagination. A physical object placed in the scene acts as the trigger, enabling deployment-time activation through the agent's native observation pipeline without digitally manipulating the observation stream. To achieve effective, stealthy, and persistent control, TrojanWorld combines Decision-Reflective Induction to steer trigger-conditioned imagination toward attacker-specified actions using decision feedback, Clean Behavior Anchoring to preserve trigger-free predictive and behavioral fidelity, and Causal Propagation to sustain the induced preference along subsequent trajectories after the trigger disappears. Together, these mechanisms establish an end-to-end attack chain from physical perception through corrupted imagination to malicious action selection. Experiments with the TD-MPC2, DreamerV3, and R2-Dreamer systems across the DeepMind Control, MetaWorld, MyoSuite, and RoboDesk benchmarks show that under trigger activation, TrojanWorld achieves a target-action deviation as low as 0.026 while retaining at least 98.8% of the corresponding clean performance. Even after trigger removal, the compromised agent can remain trapped in the induced behavioral trajectory, continuing to execute attacker-specified actions.

Learned world models typically assume that observations arrive synchronously, an abstraction inherited from simulators that return a complete state vector at each environment step. Physical sensing instead operates at heterogeneous rates, leaving most observation channels stale at any given instant. Interpolating stale channels introduces measurements that were never observed, while downsampling to the slowest sensor discards valid measurements. A natural alternative is to zero-order-hold the most recent reading and provide the known sampling schedule to the model through two features, staleness and time-to-refresh. We test this prediction using transformer world models across three regimes of increasing causal coupling: open-loop rollouts in continuous-control locomotion, closed-loop model-predictive planning in which each learned model serves as the planner dynamics, and a linear latched-actuator system in which refresh events apply a zero-order-held command to the plant. Our findings show that the effectiveness of time-to-refresh depends on the causal role of the sampling schedule, specifically when refresh events affect the system rather than merely report its state. These results establish when sampling schedules provide useful information for predictive world models operating under asynchronous physical observations.

Local pedestrian-vehicle forecasting spans heterogeneous physical scales: pedestrians combine root locomotion with articulated motion, whereas vehicles are rigid bodies described by kinematic state and oriented extent. Existing road-agent forecasters typically omit pedestrian articulation, while pose forecasters leave vehicle futures outside the learned rollout. We introduce PV-WM, a history-only world model over structured post-perception tracks. It recurrently advances pedestrian root motion, 15-joint articulation, and learned vehicle states within a synchronized heterogeneous state. The generated pedestrian and vehicle chunks supply the next recurrent boundary; vehicle boxes are reconstructed from predicted center and heading with observed extent, and P-V geometry is recomputed after every transition. Relative to a matched one-shot complete-state predictor, recurrent execution reduces Root ADE by 12.7% and MPJPE by 14.8%. Feedback interventions show that later predictions depend on the content, temporal order, and pedestrian identity of generated articulation. Across 824 aligned Waymo contexts, with 797 providing valid future vehicle support, PV-WM reduces Root ADE by 5.2%, MPJPE by 7.6%, P-V distance error by 11.9%, and oriented-box closest-approach error by 5.8% relative to a validation-selected Modular Specialist. The single-network model uses 57.1% fewer parameters, 96.5% lower average FLOPs per local scene, and 25.5% lower measured p95 latency. PV-WM unifies this heterogeneous future state while preserving type-specific pedestrian and vehicle dynamics.

Natural adversarial examples (NAEs) reveal that vision models can fail under realistic semantic changes beyond norm-bounded perturbations. However, generating NAEs in a black-box setting remains challenging because existing generative attacks often rely on surrogate models, learned attack priors, or costly query-based optimization, whereas the natural transformations that expose model vulnerabilities are unknown a priori. We propose Adversarial Scenario Attack (ASA), a query-based black-box framework that searches over natural-language editing scenarios using a multimodal language model and a modern text-guided generative editor. ASA jointly explores background, weather, and material/color transformations through winner--loser feedback, and uses a greedy explorer to compose only attack-improving scenarios. Across diverse ImageNet classifiers, ASA achieves substantially higher attack success rates than prior query-based generative attacks while requiring fewer victim-model queries and preserving competitive perceptual quality. Moreover, ASA exhibits both image-level and prompt-level transferability: its adversarial images remain effective across victim-model architectures, while its discovered editing scenarios can be reused across same-class images and, in some cases, across architectures. These findings suggest that vision models possess reusable vulnerabilities to natural transformation patterns, which ASA can efficiently identify in a black-box setting.

Long-form narrative-to-film generation requires shot-level controllability and cross-clip consistency in both visual identity and character behavior-requirements that remain difficult to satisfy with current prompt-based workflows. A core reason existing workflows remain brittle is the lack of a structured intermediate layer between scripts and video models, especially when screenplays are underspecified at key cinematic decision points. We introduce a structured orchestration layer for film-oriented script-to-video generation, implemented as a multi-agent framework that operates between scripts and off-the-shelf video generators. The layer is centered on FilmDSL, a film-oriented domain-specific language that makes cinematic constraints explicit, including shot and camera directives, asset and continuity requirements, and persona cues, so that agents coordinate through a shared structured specification for planning, generation, critique, and repair. Specifically, a generation agent constructs asset packs and storyboard keyframes that anchor composition before clip-by-clip synthesis, while a critic agent produces structured QA signals and triggers targeted refinement without retraining the base model. Experiments on TV-style segments show improved controllability and consistency over text-only and reference-only baselines.

Recent text-to-audio-video (T2AV) models jointly generate video, speech, sound effects, and ambience from a single text prompt. This capability poses new challenges for safety evaluation, as unsafe content may be conveyed through the audio track or arise only when the visual and audio tracks are interpreted jointly. Existing safety benchmarks largely focus on either generated video or generated audio in isolation and are therefore not designed to capture these risks. To close this gap, we introduce AV-SafetyBench, the first safety benchmark developed specifically for T2AV generation. AV-SafetyBench comprises a four-axis, 13-category taxonomy and 5,200 manually reviewed prompts that specify visual scenes, speech, and non-speech audio. Our evaluation protocol assesses each output under three views: Full-AV, Video-Only, and Audio-Only. It then uses the Video-Only and Audio-Only judgments to assign Full-AV unsafe outputs to one of four risk sources: Video-Only, Audio-Only, AV-Both, or AV-Joint. We evaluate five open-source T2AV models and validate the automated Full-AV judgments against human annotations. Across the five models, Full-AV Unsafe Rates range from 25.1% to 49.4%. Beyond these aggregate rates, risk-source analysis reveals that, for four of the five models, Audio-Only and AV-Joint cases-unsafe outputs missed by video-only evaluation-account for 41.6-48.3% of Full-AV unsafe outputs for which a risk source could be assigned. In the Cross-Modal Harm Emergence category, AV-Joint accounts for 87.5% of unsafe outputs withan assigned risk source. Together, these findings demonstrate the value of AV-SafetyBench for evaluating T2AV safety across the visual and audio modalities and their interaction.

Recent image-to-3D generation models built on flow-matching diffusion Transformers (DiT) can produce high-fidelity meshes, yet their post-training strategy remains largely unexplored. There exist several critical bottlenecks in reinforcement learning: the inherent difficulty of defining comprehensive rewards for 3D geometric quality, and the gradient interference that arises when jointly optimizing heterogeneous objectives. Inspired by the practicability of on-policy distillation (OPD) in large language models and image generation, we propose Flow3D-OPD, a two-stage post-training framework that introduces multi-teacher distillation into 3D geometry generation. In the first stage, we utilize the semi-policy to enhance the foundational capability of the pretrained model and then design an agentic verifier for 3D geometric quality evaluation. Based on the verifier, we could cultivate domain-specialized teacher models via direct preference optimization (DPO). In the second stage, we consolidate heterogeneous expertise into a unified student model through on-policy distillation with hard task-routing sampling and gradient accumulation, which could mitigate the gradient interference in joint optimization. Without relying on elaborate modifications, our straightforward yet effective design achieves consistent improvements across all geometric quality dimensions and surpasses all teacher models in the average metric. Extensive experiments demonstrate that our approach provides an effective paradigm for reinforcement learning in 3D generation.

We introduce DF26, a novel benchmark for detecting AI-generated videos containing fully synthetic clips produced by recent text-to-video and image-to-video models. The videos capture single-person public-speaking scenarios, spanning direct-to-camera recordings, official statements, and studio interviews - 271 real and 2,420 synthetic videos generated by seven modern video models. The study on DF26 shows that human performance in detecting AI-generated videos, as well as state-of-the-art deepfake detectors, is close to random chance. Our results highlight the limitations of current evaluation protocols and motivate the need for benchmarks that explicitly measure robustness to modern generative model distribution shifts.

Current text-to-image systems typically employ a "text encoder plus diffusion decoder" paradigm, in which text semantics directly modulate continuous latent noise. Despite their success, these methods lack an explicit, interpretable intermediate representation that effectively bridges high-level linguistic semantics and low-level visual signals. In this paper, we propose Vision-of-Thought (VoT), a framework that introduces a discrete visual-thinking layer between vision-language models (VLMs) and diffusion transformers (DiTs). Instead of treating VLMs merely as text encoders, we use them as multimodal planners that generate discrete VoT tokens representing high-level visual plans, such as objects and layouts, before rendering pixels. We train a specialized VoT tokenizer in the VLM semantic space with a closed-loop objective that combines VLM alignment, feature reconstruction, and vector-quantization losses. These objectives make the tokens semantically readable by the VLM while preserving the visual information needed for generation. Experimental results demonstrate that VoT improves semantic alignment and provides a structured interface for interpretable and controllable generation.

The rapid evolution of video generation has shifted the paradigm from pure text-driven to multi-conditional controllable generation, with reference images now widely adopted as conditional inputs to achieve superior spatiotemporal consistency. While these reference images serve as powerful visual anchors that significantly enhance controllability, their impact on safety remains largely unexplored. In this work, we reveal the visual anchoring effect: by enforcing consistency, the mechanism prevents the generated content from drifting away from the original harmful intent, thereby eliminating the model's natural safety escape route from harmful to benign content. Consequently, visual anchors inherently increase the safety risk---this is the price of consistency. Building on this insight, we propose Decoupling Intent via Visual Anchors (DIVA), a training-free multimodal jailbreak framework for video generation that exploits this vulnerability. DIVA decouples harmful intent into a static visual anchor image and a dynamic motion text prompt, and employs dual-criteria selection to balance attack stealthiness with semantic preservation. Extensive experiments across various leading commercial platforms and mainstream open-source video generation models demonstrate that DIVA achieves a substantially higher Attack Success Rate than existing text-only methods. To facilitate future research, we additionally contribute TI2VSafetyBench, the first safety benchmark for multi-conditional video generation.

Ground-penetrating radar (GPR) B-scan image synthesis is important for data augmentation, algorithm validation, and simulation acceleration, yet generating radargrams with both visual realism and physical consistency remains challenging. Existing learning-based generative models often emphasize visual appearance but provide limited control over response geometry. In this paper, we propose PCFlow, a physics-conditioned flow matching framework for fast GPR B-scan image synthesis. The core of PCFlow is a Maxwell-informed dense physical condition field constructed from the parameterized physical model used for electromagnetic simulation, including material properties, target geometry, propagation cues, and response-domain priors. This condition field provides an interpretable interface between physical scene parameters and radar response geometry, and guides conditional flow matching in the VAE latent space toward physically feasible generation paths. We evaluate PCFlow on a gprMax-based buried-pipeline dataset with both in-distribution and out-of-distribution test cases. Experimental results show that PCFlow generates images with more accurate response geometry and high visual fidelity, demonstrating its effectiveness for controllable and physically faithful radar image synthesis.

Test-time scaling (TTS) can improve generation only when additional compute produces better candidates and the system can reliably identify them. This distinction is especially important for video world models, where a wider sample pool may contain stronger rollouts without improving the output that is ultimately selected. We introduce the Compute-Value Audit (CVA), a sequential framework that asks whether extra sampling creates opportunity, observable signals provide a reliable state, that state supports a beneficial action, and the resulting gain exceeds the full entry fee of generation and verification. On 192 Physics-IQ scenes, expanding the pool from 4 to 16 candidates increases oracle quality by +9.23 IQ (95% CI [+7.44, +11.14]), but Flow, Cycle, and VideoReward fail to recover this headroom reliably. Across three generators, none of twelve adaptive-depth policies outperforms uniform compute; they recover only 42-69% of the measured entry fee. A matched-60-NFE Predict-and-Perturb intervention on VideoPhy2 is likewise negative across three fresh-seed replicas. These negative results are not universal: anchor-explorer passes all four stages in a sparse PRM800K setting, MMLU-Pro exposes the gap between predictive state and useful action, and a privileged paired future establishes a positive video upper bound. Together, these results show that sampling headroom has deployment value only when it can be converted into a reliable decision whose benefit survives the complete compute charge. Code is available at https://github.com/YuhuaJiang2002/sampling-headroom-is-not-selection-gain.

Teleoperated demonstrations are often multimodal even when the underlying dynamics are nearly deterministic given the executed action. We argue that this multimodality typically mixes three factors--operator habit in action selection, shared physics, and observation nuisance--and that entangled next-observation predictors absorb all three. We formalize the split with a structural causal model a=g(h,z,u), z'=f(z,a), o=r(z,c), and test it with complementary interventions: replacing or shuffling actions at fixed state sharply increases next-state error, whereas appearance and camera changes should not; habit-aware reverse scoring improves ranking of feasible pasts without rewriting the dynamics. The associated adaptation rule is to freeze a shared physics readout and update only a thin interface. On StackCube, DROID, and RH20T this rule improves low-shot transfer relative to training from scratch, retains cleaner dynamics under corrupted adaptation data, and extends from proprioception to pixel observations with multi-view and multi-step checks. We do not equate latent actions with operator habit, and we do not target large-scale video generation benchmarks.

Training-free zero-shot video anomaly detection (ZS-VAD) leverages vision-language models (VLMs) to localize anomaly instances from a predefined anomaly vocabulary, without providing any video. Existing CLIP-based methods often emphasize anomaly-side semantics, while the competing normality side remains less carefully formulated. We identify two key limitations in existing solutions: (i) blurred decision boundary: normal prompts may contain ambiguous verbs, such as running, that are semantically close to anomalies, reducing normal and abnormal separation in the VLM embedding space; and (ii) modality gap: poor alignment between features of textual normal anchors and visual frames. We propose NOVA, a training-free ZS-VAD framework that strengthens the normal side at both linguistic and visual levels. NOVA introduces Normality-Aware Prompt Construction (NA), which excludes anomaly-adjacent verbs and biases normal descriptions toward static, low-motion scenes. To overcome the text-vision modality gap, NOVA constructs a Visual Normality Anchor (VNA), which creates a weighted visual normal anchor from the initial frames of each test video, providing a video-specific normal reference without task-specific training or annotations. NOVA achieves 89.86 percent AUC on UCF-Crime and 95.07 percent AUC and 84.82 percent AP on XD-Violence, reaching state-of-the-art performance among comparable training-free zero-shot methods.

Object-centric video models represent scenes with slots, yet exposed geometry can vary in meaning with appearance. In Invariant Slot Attention (ISA), explicit position and scale can disagree with the decoded center and extent; edits can yield unexpected motion or resizing, and replacing appearance can shift geometry. GeoCo-SAVi promotes geometric authority and semantic alignment. Its spatially equivariant, object-wise decoder makes position and scale effective commands: changing them moves or resizes the rendered support. Factual position alignment ties position to the decoded center, and normalized attention overlap discourages duplicate allocation. Appearance transplantation aligns geometry semantics across objects, so recipient geometry governs layout while donor appearance supplies shape. A temporal initializer propagates calibrated slots across frames. On Obj3D, GeoCo-SAVi matches ISA reconstruction, reduces p-centroid error by over 80%, and cuts appearance-induced size variation by over 50% while producing the expected translation and scale responses. On 250 MOVi-C videos, it also improves reconstruction, instance grouping, and fixed-identity geometry control over two same-protocol references. GeoCo-SAVi transforms explicit geometry into compositional control, making both position and scale more readable and editable.

Active mapping requires a robot to select camera viewpoints that efficiently reconstruct an unknown 3D scene. To reason about unobserved regions, recent systems use pretrained occupancy networks as world models that complete missing geometry. The predicted structure contributes to expected coverage gain and constrains feasible robot motion. Consequently, occupancy errors can change both what the robot chooses to explore and where it is able to move. We diagnose these effects by holding the planner fixed and varying only the occupancy representation provided to it. We consider planning without completion, with learned occupancy, with false positives removed by a ground truth oracle, with false negatives restored by an oracle, and with ground truth occupancy. Our experiments show that correcting false positives or false negatives alone does not consistently improve final coverage. This finding reveals a gap between occupancy accuracy and downstream planning performance. Ground truth occupancy provides a much larger improvement in coverage efficiency than in endpoint coverage, suggesting that planning and reachability remain important bottlenecks even when the geometric world model is accurate. Based on these findings, we introduce a dynamic filtering strategy that preserves predictions in unexplored space while suppressing repeatedly unsupported occupancy using online observations. Preliminary examples show that this strategy can redirect viewpoint selection toward reachable surfaces that would otherwise remain unobserved.

Embodied artificial intelligence has historically very much relied on visual perception, leading to a proliferation of multiple vision-centric world models. However, this reliance fails to capture spatial understanding in its entirety and can even present vulnerabilities in environments with visual occlusions, low-light conditions, or blackouts-scenarios, where acoustic information becomes a critical alternative for spatial awareness and navigation. Despite its potential, research into realistic spatial audio and particularly the development of audio-centric world models remains sparse. In this technical report, we introduce BinauralVAE: a flexible, open-source pipeline (https://github.com/Luizerko/BinauralVAE) that explores multiple models for spatialized audio reconstruction, progressing from fundamental baselines to advanced, mathematically grounded architectures. Our approach evaluates various Variational Autoencoder architectures — including complex-valued variants — to learn robust latent representations of binaural signals. Developed alongside AudioWorldSim, our methodology leverages realistic acoustic data captured as a simulated robot navigates an environment. This pipeline establishes a foundation for state representation in a future audio-based world model, designed to map the direct causal connection between navigational actions and their resulting acoustic consequences, and helping to enable sound as an essential complementary modality for spatial knowledge acquisition.