每天知道
你的领域
出了什么

Mobile manipulation extends robot interaction beyond a fixed kinematic workspace by making the reachable region itself controllable. This flexibility introduces two central challenges: spatially grounded perception under continuous ego-motion and coordinated control of heterogeneous arm and base actions. Existing approaches strengthen geometry through explicit 3D representations or predictive world models, and often decouple mobility and manipulation into separate action streams. We argue that effective mobile manipulation requires not only decoupling, but also representations that support efficient cross-stream collaboration. We present MM-ABC, a foundation model built around Seeing, Coordinating, and Imagining Arm-Base Collaboration. MM-ABC combines sparse multi-level VLM features for spatial perception; a training-only future branch that uses world imagination and geometric intent as extra supervision, strengthening perception and manipulation-intent prediction and improving the overall learning signal; and MM-APT, which coordinates separate manipulation and mobility streams through masked joint attention and clean-action x-prediction. In controlled ablations, replacing clean-action prediction with velocity prediction lowers success on RoboCasa365 composite-seen tasks from 32.8% to 29.2%, and removing future supervision or multilevel conditioning causes larger drops. We pretrain MM-ABC on 5,000+ hours of heterogeneous robot data spanning 400K+ episodes, 12 datasets, and 17 embodiments. Experiments cover EBench, RoboCasa365, ManiSkill-HAB, LIBERO, LIBERO-Plus, and real-world mobile manipulation. MM-ABC achieves 44.71% success on EBench, 61.2% on RoboCasa365, 99.1% on LIBERO, 82.8% on LIBERO-Plus without perturbation training, and 83% mean success on five real-world tasks.

Reward-maximizing reinforcement learning (RL) is widely used to post-train stochastic diffusion and flow policies for text-to-image (T2I) generation. However, reward-maximizing RL causes policy mode collapse even under reference KL or entropy regularization, reducing the policy to a single high-reward mode. In T2I, this produces similar images and reward hacking. When extended to vision-language-action (VLA) models, the same collapse removes alternative successful strategies and weakens task and scene generalization. To address this limitation, we introduce Unified Trajectory Matching Policy Optimization (Uni-TMPO), a unified RL post-training framework for diffusion and flow policies. First, Uni-TMPO converts standardized rewards into a target distribution within each trajectory group and derives the policy distribution from trajectory log probabilities. Then, forward Kullback-Leibler optimization matches the two distributions instead of maximizing expected reward. A progress-conditioned coarse-to-fine scheduler efficiently constructs T2I trajectories. Within the unified framework, feedback-conditioned sampling uses updated observations to construct VLA trajectories. Extensive experiments show that Uni-TMPO achieves higher T2I rewards and VLA ID success rates than the strongest baselines. More importantly, it achieves the best T2I reward-diversity-efficiency trade-off and VLA generalization to held-out tasks and scenes, while real-robot evaluation demonstrates the value of multiple action strategies when the higher-reward target is blocked.

Compact JEPA world models enable efficient latent-space planning, but low-dimensional representation trained under reward-free self-supervision must encode both action-conditioned dynamics and predictable visual context. This competition can entangle controllable state with high-rank nuisance appearance and degrade planning as scenes become more complex. We introduce LRC-JEPA, a lightweight end-to-end world model that routes information into a compact predictive latent $\mathbf{z}$ and learned-query residual-context embeddings $\mathbf{u}$. Only $\mathbf{z}$ is propagated by the dynamics model and used for planning, while $\mathbf{u}$ captures temporally persistent information for cross-attention reconstruction; a differentiable residual connection encourages the latent to retain complementary dynamic content. Under explicit assumptions, we show that the resulting representation is sufficient, minimal, nuisance-invariant, and disentangled. Across four simulated control environments, LRC-JEPA improves average planning success over a parameter-matched JEPA baseline by 9 percentage points and matches or exceeds substantially larger pretrained models. On the real-world Bridge-v2 set, its 5.5M-parameter active encoder outperforms DINO-WM (22.1M) and V-JEPA2 (303.9M) encoders while also enabling faster planning. Physical-state probes, reconstruction interventions, and ablations confirm the effectiveness of LRC-JEPA's representation disentanglement.

On modern production text-to-image systems, successful policy violations are rare, and previously effective human-written seeds are often patched out. Current automated red-teamers are poorly matched to this regime in two ways: unreliable success measurement and poor exploration. First, we find that judges widely used in prior T2I red-teaming work are unreliable under vague unsafe-content targets: they either miss true violations or reward benign borderline images on hardened APIs. We therefore define strict category-specific success criteria and calibrate strong VLM judges against human labels. Second, we show that broadly used prompt-modification pipelines do not solve the exploration problem: on harder guardrail settings they remain tied to seed prompts, fail to transfer, or cannot bootstrap positive examples. We introduce RISE, which evolves reusable strategies used to generate prompts rather than rewriting them one by one. The best discovered strategies are then reused to generate attacks across new scenarios. On DALL-E 3, Nano Banana 2 (Google) and GPT-Image-2, RISE reaches up to 13% human-verified ASR; under the same calibrated evaluation, prior methods with reported ASR as high as roughly 30% fall to near zero.

Modern AI models are aligned through post-training to adapt them to downstream tasks. Recent work shows that fine-tuning language models on narrow tasks can induce emergent misalignment (EM), causing broadly harmful behaviors beyond the training task. However, EM has been studied almost entirely in text-only tasks, leaving its manifestation in multimodal models unclear. In this paper, we define and analyze EM in the context of vision-language models. We first induce EM via fine-tuning on narrow multimodal tasks targeting vulnerable code, careless household-object use, and conspiratorial interpretations of ordinary scenes. Across fifteen commercial and open-source models with different scales, we find that narrow multimodal fine-tuning can induce coherent and broadly misaligned behavior that transfers to unrelated tasks, including misaligned opinions, visual factual dishonesty, unsafe image generation, vulnerability to visual jailbreaks, and risky agentic actions. We further find that multimodal EM does not depend on the apparent harmfulness of training data but is sensitive to training-evaluation modality alignment. EM can arise under both supervised fine-tuning and preference optimization and can propagate through intermediate reasoning. Finally, we explore several mitigation strategies, including prompt inoculation, benign continued training, and activation-level steering, which can partially reduce EM. Overall, our findings suggest that multimodal EM reflects a behavioral shift rather than a general loss of capability, extending beyond text to the visual modality.

Photographic color editing is inherently personal: the same image can appear too warm, too muted, or already satisfactory to different users. Most lookup table (LUT) and reference-guided methods target a specified appearance rather than model persistent preferences from repeated user choices. To address this gap, we introduce PrefLUT, a reusable and refinable user-preference modeling framework for deployable 3D LUTs, encoding ordered preferred/non-preferred image pairs into a lightweight Reusable User Profile that is reused across queries and refined using additional user preference pairs, without per-user optimization. A Query-Conditioned LUT Predictor combines this profile with each image to predict a LUT latent vector and edit strength. An Identity-Residual LUT Decoder and Edit-Strength Controller then produce an exportable 3D LUT. Experiments on three datasets demonstrate effective personalized editing and general-purpose enhancement. Each quantized profile requires only 260 bytes, and editing takes 1.365 ms/image on an RTX 5090 GPU. We also introduce the Preference-Conditioning Verification Protocol (PCVP), an evaluation protocol to verify whether personalized image edits depend on user preferences and the query image through controlled changes to user profiles, preference orders, pair correspondences, and query images.

Language-conditioned robot policies have made clear progress in multitask manipulation, but task-relevant local visual evidence usually stays hidden inside a visual backbone or attention layers. This leaves the policy difficult to inspect and fragile under visual change, two symptoms of a missing explicit, task-aligned local visual channel. We present TLC-DiT, a plug-in extension of the Multitask Diffusion Transformer (DiT) policy that adds explicit task-guided local visual feature maps without changing the diffusion objective or the action-generation process. For each camera view, frozen DINOv2 patch features are modulated by the CLIP task embedding through FiLM and refined by a lightweight CoordConv CNN adapter into smooth spatial maps, which are concatenated with the original global image, language, joint-state, and timestep conditions. On LIBERO, TLC-DiT reaches a 93.5% average success rate, compared with 86.5% for Multitask DiT and 79.25% for SmolVLA. On LIBERO-plus, the total success rate improves from 54.07% to 57.24%, with larger gains under camera, background, and sensor-noise changes. In real-world bimanual tasks, TLC-DiT raises Teabag Putting completion from 44% to 89% while maintaining comparable Match Box Opening performance. Feature-map visualizations confirm that the model attends to task-relevant regions across views and perturbations, providing a direct way to inspect the visual evidence.

Long-horizon camera-controlled video generation requires recovering previously observed content from an ever-growing visual history. Existing approaches either search historical context implicitly or reconstruct it into persistent 3D memory, facing inefficient memory access or accumulated geometric errors. Our key insight is that geometry need not explain the scene--it only needs to determine where visual memory should be read from, while attention decides what should be recovered. Based on this insight, we introduce GEAR, a Geometry-Enabled Attention Routing framework that uses geometry as an explicit token-level address for visual memory. Rather than fusing historical observations into a persistent global 3D representation, GEAR retains them as frame latents and uses per-frame geometry only to establish token-level correspondences with target views, thereby avoiding persistent error accumulation from global fusion. Guided by these correspondences, Geometric Correspondence Attention (GCA) selectively injects geometrically matched historical features into noisy target patches during denoising. We further introduce an Invisible Octree to accumulate visibility evidence and reject geometrically plausible but occluded correspondences. Extensive experiments demonstrate that GEAR achieves state-of-the-art visual quality, precise camera control, and revisit consistency, enabling minute-long video generation along challenging trajectories.

Post-training foundation video models on heterogeneous reward-weighted data usually assume that all data categories induce compatible updates. This assumption is fragile when categories correspond to different skills, domains, or evaluation dimensions. We study this problem in text-to-video post-training, where VBench2.0 dimensions define data buckets and an external multimodal reward pipeline assigns sample weights. We propose G$^3$-LoRA (Gradient-Guided Grouped LoRA), a data organization procedure that probes category-level gradients induced by reward-weighted video samples, removes the shared global update direction, clusters categories by residual gradient compatibility, trains group-specific LoRA experts, and consolidates them into one adapter by weight merging followed by on-policy distillation from the experts. We motivate this procedure by viewing reward-weighted flow matching as velocity-field regression: incompatible reward dimensions may prefer different denoising directions in overlapping noisy latent regions, causing shared LoRA training to average capabilities. On Wan2.1-T2V-1.3B-Diffusers, the merged grouped adapter improves the matched VBench2.0 evaluation over the base model, a joint reward-weighted LoRA baseline, and random, semantic, and raw-gradient partitions trained with the same pipeline; an independent evaluator agrees, and on CogVideoX-2B grouping avoids the negative transfer of joint training. The gain is not uniform: merging compresses the largest specialist gains, distillation recovers part of this loss, and camera motion and several local-quality dimensions remain challenging. Together, these results suggest that gradient compatibility can serve as a practical diagnostic for organizing reward-weighted video post-training data.

Few-step autoregressive video generation commonly relies on Distribution Matching Distillation (DMD), requiring a bidirectional diffusion teacher and an online fake-score model. We instead learn the rollout distribution directly from reference videos, eliminating both score models during post-training. Our framework minimizes maximum mean discrepancy (MMD) in frozen self-supervised video representation spaces, using a hybrid Nyström--Monte Carlo estimator to balance approximation bias and sampling variance. Memory-efficient replay and gradient subsampling make this objective practical. Using the same architecture and initialization as Self-Forcing, our 1.3B model improves the VBench Total score from 83.80 to 84.64 while retaining 17 FPS. Removing auxiliary score models also enables 14B post-training on eight H200 GPUs. Beyond distillation, learning from reference videos enables the acquisition of new visual styles, semantic concepts, and spatial priors without a target-specific diffusion teacher.

Recent image generation models can take multiple reference images as input and combine them into a new image. However, multi-reference image generation remains challenging: models may omit or duplicate subjects from the references, or produce images in which multiple subjects appear unnaturally pasted. Recent work has proposed image generation agents that combine image generation models, reasoning models, and a harness, which is an executable program that specifies how reference images are interpreted, how generation is performed, how outputs are diagnosed, and how the final image is selected. In multi-reference generation, however, references play different roles and outputs must satisfy many criteria at once, such as fidelity to each reference and the naturalness of the whole image, so many parts of the harness could be improved, from how references are processed to how outputs are diagnosed. This makes it hard to predict which changes will improve performance and by how much, and good harnesses difficult to design by hand; indeed, human-written harnesses vary widely in performance. We therefore propose AutoRef, which optimizes the harness automatically while keeping both models frozen: a coding agent iteratively rewrites the harness code. AutoRef separates the tasks whose feedback informs proposals from the tasks used to select candidates, and continues the search from a beam of the top-ranked harnesses on the selection tasks. Using this procedure, we discover AutoRef-Harness, which improves the open-weight FLUX.2 [klein] 4B from 5.72 to 7.37 on held-out four-reference tasks of the MultiBanana benchmark, matching or exceeding proprietary models including Nano Banana Pro and GPT-Image-1.5. Without re-optimization, the same harness also improves results when the generator, number of references, benchmark, evaluator, or reasoning model differs from those used in the search.

Video generation must account for two sources of motion, one induced by the observer's camera path and the other caused by scene dynamics. An ideal camera-controlled video model should account for both motions: let users move the camera while evolving the scene dynamics. While current models handle camera-induced motion well in static settings, they struggle for dynamic scenes: objects are static, move incorrectly, or degrade in generation quality. We introduce DynaTokens, a lightweight set of learnable scene-specific tokens that teach dynamics to an existing camera-controlled world model. Our method is motivated by a simple asymmetry between the two sources of motion: whereas camera motion affects the generated view globally, object dynamics are spatially localized. Through cross-attention, DynaTokens trains the learnable tokens from a few example trajectories for a scene while keeping the base model frozen, and enables dynamics under new query camera paths. DynaTokens achieves a better simultaneous dynamics-camera tradeoff on VBench2 and WorldScore evaluations than LoRA, block finetuning, and specialized trainable-layer baselines. Analyses of token attention, ablations, and motion temporality suggest that matching the trainable interface to the structure of the learning target is important for effective adaptation. Project website: https://glab-caltech.github.io/dynatokens/

Interactive world models must respond quickly to controls while preserving scene consistency. Existing acceleration methods can miss heterogeneous control responses and spatial transport when recovering skipped features. We observe that interaction-induced feature changes correlate with approximation error, while low-frequency interpolation errors are phase-sensitive and show more predictable phase progression. These findings motivate CAST, a reconstruction-coupled inference framework. CAST selects anchors by interaction sensitivity and cross-layer coverage, reconstructs skipped residuals with frequency- and confidence-aware Phase-Aware Reconstruction (PAR), and coordinates historical KV routing according to downstream reconstruction responsibility. On Matrix-Game 3.0 and HY-World 1.5, CAST achieves 2.15x and 3.48x speedups, respectively, while maintaining visual quality close to Native (Figure 1). It also attains the highest VBench scores among compared methods and leads non-native baselines on seven and six of thirteen WorldMark dimensions, demonstrating a balance of generation speed, visual quality, and interactive responsiveness under real-time control. Code is available at https://github.com/lokiniuniu/CAST.

Interactive world models require responding in real time to versatile controls and maintaining long-horizon consistency. However, modeling heterogeneous controls remains difficult, while explosive contexts and unstable distillation impede achieving both long-horizon consistency and real-time responsiveness. In this paper, we present WorldPlay2, an interactive world model that couples a factorized hybrid control interface with a co-design of compressed memory and stable distillation. 1) Our factorized hybrid control interface integrates frame-aligned action control with structured semantic control that explicitly disentangles scene appearance, character identity, and dynamic semantic events, thereby facilitating effective control learning. 2) To achieve efficient long-horizon modeling, we compress historical contexts into compact memory tokens shared by the autoregressive student and the bidirectional teacher. This design enables clip-wise, memory-conditioned score evaluation instead of jointly processing an entire long rollout, substantially reducing distillation overhead. 3) We further propose Stable Forcing, which initializes the autoregressive student via a few-step strategy and leverages full-rollout replay to preserve the quality of long-horizon rollouts, ensuring robust and stable distillation. Extensive experiments demonstrate the strong generalizability of our model and its superior performance compared to existing methods.

Unified multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image gets wrong, revise it, observe the result, and diagnose again. Whether a revision helps is known only after it is rendered, so the reflection text and the image generation must be learned jointly, over the whole loop. Supervised fine-tuning (SFT) on reflection trajectories gives a cold start but does not find the high-success repair paths, and naive RL that optimizes only the renderer or only one head leaves most of the gain untapped. We introduce UMM-Reflection, which applies reinforcement learning (RL) to complete reflection trajectories inside one unified model: sibling trajectories share one initial image, so the group-relative advantage compares reflection strategies, and one trajectory-level advantage updates both the reflection tokens and the flow-based revisions, avoiding the combinatorial blow-up of per-round credit assignment. Unlike single-round editing or pipelines with an external critic, credit flows across rounds and to both roles of the same model, and no verifier is needed at inference. On BAGEL, UMM-Reflection improves GenEval by 12.05 points over SFT, and the gains transfer to WISE (+10.97), OneIG-Bench (+3.48), and T2I-CompBench++ (+4.63), none of which is used in training.

Flow-based image editing (FlowEdit) enables inversion-free semantic changes through the difference between source and target velocities. In this paper, we observe that FlowEdit's default classifier-free guidance (CFG) configuration, with asymmetric source and target scales, causes substantial background leakage. Matching these guidance scales, for example by removing CFG, improves edit-relevant localization but severely degrades editability. To get the best of both worlds, we propose DecFlowEdit, which decouples the optimal guidance scales for localization and for editing in flow-based generative models. In particular, DecFlowEdit first extracts an edit-relevant prior by temporally aggregating velocity differences evaluated without CFG, and then uses this prior to reweight the original updates under default CFG. Our method remains training-free and inversion-free, requiring neither external spatial masks nor attention manipulation. Experiments on PIE-Bench across FLUX, SD3, and SD3.5 show that DecFlowEdit improves background preservation, reducing structure distance by approximately 61 to 73 percent and background LPIPS by 68 to 80 percent relative to FlowEdit at comparable editing fidelity.

AI agents increasingly carry out long-horizon professional work, but their evaluations rarely require a finished creative deliverable. To this end, we introduce Timeline-Bench, a benchmark of 56 real video-editing tasks, each asking an agent to turn raw production material into a finished video. Tasks range from selecting dialog takes and shaping interview footage into a story to cutting commercials from product shots, voiceovers and graphics. Every task provides a brief, source assets, a container and a set of tests. A task is resolved when the output passes every test. The tests check the delivery format, the content and the brief's explicit requirements, and include a quality test calibrated on 2,582 blind judgments by 43 video editors. We evaluate 16 agents that pair frontier models with coding-agent harnesses such as Codex, Claude Code and OpenCode. The best, GPT-6 Astra in Codex with curated editorial guidance, resolves only 15 of the 56 tasks (26.8%), and the average agent resolves 14.0%. Human editors prefer the reference edit in 83.5% of judgments. Most unresolved runs (562 of 771) fail only the quality test: agents perceive footage through stills and transcripts and check their renders for defects, not craft. We release the tasks, verifier and per-run results at https://timelinebench.tensortest.com.

Instruction-based image editing has achieved strong performance in single-turn settings, yet practical editing is often iterative, with each instruction applied to the output of the previous turn. We find that existing editing models degrade rapidly under recursive editing and attribute this failure to a train-test mismatch in the conditioning distribution: models are trained on clean source images but must repeatedly condition on their own imperfect outputs at inference time. To address this, we propose MT-OPSD, an on-policy self-distillation framework that trains the model on self-generated conditioning states with editing supervision from a clean-conditioned teacher, without requiring multi-turn annotations. We further introduce LME-Bench, a benchmark of 100 ten-turn editing sessions for evaluating long-horizon robustness. Experiments across three editing backbones show that MT-OPSD substantially improves long-horizon editing success and reduces multi-turn collapse while largely preserving single-turn editing quality.

Video text editing aims to replace or add text in a video while keeping the rest of the video unchanged, which requires the edited text to be correct in every frame and to move coherently with the scene. Despite the remarkable progress of video diffusion models, they struggle to reproduce exact stroke structures and often produce garbled or wrong characters, especially for characters with complex strokes. To address this, we propose a trajectory-aligned glyph rendering reference that provides explicit per-frame glyph guidance following the position and perspective of the text, and a depth-normalized recognizer feature supervision that supervises the generated text on multi-depth features of a frozen text recognizer with per-depth normalized errors, targeting stroke errors overlooked by the diffusion loss. We further build VTEdit, a benchmark of 288 real-scene clips with 440 annotated text trajectories covering text replacement and text addition, which will be publicly released to facilitate future research. Experiments on VTEdit show that our method outperforms image text editing methods, video editing methods, and commercial models in text accuracy and background preservation, achieving a sentence accuracy of 0.9408, and receives the highest preference in a user study.

Predicting the next state is a core paradigm of World Models for modeling physical dynamics, emphasizing prediction fidelity. As World Models evolve into World-Action Models (WAMs), existing methods still fix the next state before training as RGB, a single latent feature, or a static combination of predefined targets, thereby constraining action learning to the inductive biases preserved by a particular representation. To address this limitation, we propose CF-WAM, a dynamic next-state prediction framework that samples visual, semantic, geometric, and interaction projections of the same future, standardizes them into a common video form, and supervises a unified WAM across these projections. The action-relevant constraints exposed by these projections accumulate across training steps, forcing WAM to capture the underlying state-transition structure that supports multiple projections of the same action-conditioned future. This dynamic mechanism also provides a natural cross-embodiment dynamics reference frame for Human and Robot learning. By jointly learning across different next-state parameterizations, heterogeneous Human and Robot experience can bypass appearance differences and directly contribute to shared state-transition learning, improving cross-embodiment generalization. Experiments show that CF-WAM improves both training efficiency and final control performance, while translating Human experience effectively into policy gains. CF-WAM achieves state-of-the-art performance on RoboCasa-GR1 with an average success rate of 82.50%, while reaching 82.65% on LIBERO-Plus and up to 84.00% in real-world evaluations.

Reference-guided diffusion editors struggle to faithfully reproduce user-provided references. We identify a potential bottleneck in diffusion editors: many methods provide limited reference-attention allocation. For example, in LoomVideo, edit-region queries assign less than 1% of their attention mass to the reference. We introduce RefGAP, a training-free correction that determines logit-offset magnitudes online at each layer from the reference-attention mass measured during the forward pass. Positive offsets to reference logits strengthen reference usage by edit-region queries, while negative offsets for keep-region queries limit reference-induced changes outside the edit. Two global coefficients control the correction; they are selected once on validation data from four development diffusion editors and held fixed. Across seven diffusion-based image/video editors, RefGAP improves identity fidelity in head swapping and face swapping. RefGAP achieves a fidelity-preservation trade-off comparable to separately tuned constant edit-side biases, without per-approach strength sweeps. Additional experiments on virtual try-on and background replacement evaluate transfer beyond identity editing.

Lightweight scene proxies let creators control scene layout and motion while leaving room for imagination in appearance, lighting, and visual effects. However, a suitable proxy is not uniquely defined, making paired proxy-video data difficult to construct automatically at scale. We present Proxy2World, a controllable world model that learns these complementary capabilities from ordinary posed RGBD videos, without training on authored proxy-video pairs. The model jointly learns depth-conditioned RGB generation and joint RGBD generation through cross-modal flow matching. Learning both tasks enables proxy-camera hybrid denoising at inference to follow the proxy structure while producing natural, detailed visuals. We further introduce ProxyBench to evaluate this capability across a diverse set of scenes, camera trajectories, and subject motions. Experiments on ProxyBench show that Proxy2World achieves a better balance between structural adherence and visual quality than camera-controlled and geometry-conditioned methods, supported by quantitative metrics, VLM assessments, human evaluations and diverse qualitative results.

Despite rapid progress, world models still lack explicit, persistent structural memory, making it difficult to preserve consistent world structure during continual scene expansion and cross-view revisits. To address this limitation, we present WorldWeave, a world generation framework that decouples world-state maintenance from visual rendering. Specifically, WorldWeave combines continual elevation-map generation with agent-guided scene organization and stitching to build an expandable explicit 3D world that incrementally extends structural memory while preserving existing structure. First, its terrain module uses diffusion-based image outpainting to generate continuous metric elevation maps under neighborhood conditioning and boundary constraints. Next, an agent integrates user intent, terrain evidence, and cross-region connectivity constraints to construct scenes through hierarchical semantic planning, deterministic geometry compilation, and local revision. Finally, during visual generation, planned camera trajectories query world geometry through a read-only interface, producing depth sequences that guide video synthesis without writing the generated results back into the world state. As a result, structural memory remains independent of short-window video generation, enabling continual expansion without predefined map boundaries and providing a consistent geometric basis for observations across trajectories and repeated visits.

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 .

Real-world driving is inherently multi-agent, yet most existing driving world models generate observations from a single ego vehicle. Independently extending them to multiple vehicles does not ensure that different agents observe a consistent shared world. We present CoDrive, a cross-vehicle, multi-view driving video generation framework that jointly generates observations of vehicles sharing the same dynamic scene with precise camera-trajectory control. CoDrive interleaves local self-attention, which models spatiotemporal dependencies among the views of each vehicle, with global self-attention, which enables information exchange and consistency modeling across vehicles. To explicitly encode their spatial relationships, all camera trajectories are represented in a shared world coordinate system and injected into the attention layers through projective relative positional encoding. We further adopt a progressive mixed-task training strategy that combines large-scale real-world single-agent data with synthetic cross-agent interaction data, allowing the model to benefit from real-world appearance distributions while learning cross-agent consistency from simulation. For systematic evaluation, we introduce CoDrive-Bench, a benchmark covering real and synthetic multi-vehicle scenarios and evaluating trajectory controllability, scene geometry consistency, and instance-level consistency. Experiments show that CoDrive improves trajectory controllability and cross-agent geometric and instance consistency while maintaining competitive visual quality.

Video editing has advanced substantially in recent years, with methods increasingly accounting for the visual consequences of edits, such as changes to shadows and occlusions. However, the physical consequences of edits, including changes to subsequent motion and interactions, remain less explored. We formulate this problem as physical counterfactual video editing (PCVE), which aims to generate a counterfactual video depicting the resulting motion and interactions given a source video, a physical edit, and its execution frame. PCVE is challenging because it requires understanding scene physics and inferring the downstream motion and interactions induced by a physical intervention, while paired factual and counterfactual data and dedicated evaluation metrics are lacking. We introduce VideoPhysEdit, a new training-free pipeline for PCVE in rigid-body scenes. It makes physical reasoning explicit through a novel physical scene reconstruction method that recovers a scene reproducing the observed motion and interactions under simulation, enabling the pipeline to apply physical edits as interventions and use the resulting trajectories to guide counterfactual video generation. We further construct PCVE-RigidBench, a synthetic benchmark with paired source and counterfactual target videos and physical ground truth, and introduce the Physical Edit Score. VideoPhysEdit achieves substantially higher physical edit accuracy than open-source methods and commercial models while maintaining competitive visual fidelity. Its Physical Edit Score is 0.376, the only positive score among the compared methods. Qualitative comparisons on real videos further show that VideoPhysEdit applies to real-world scenes and better depicts the downstream motion and interactions induced by the edits than the compared methods. Code: https://github.com/Hammour-steak/VideoPhysEdit

Video and audio are perceived together, yet most generative models treat them in isolation. We examine methods that model the two modalities jointly, generate one from the other, or edit them in a coupled manner, organized around a single question: how is the output kept coherent across modalities in time and semantics? A unified formulation casts joint generation, cross-modal generation, and joint editing as three problems defined on a single distribution over audio-visual pairs, and a taxonomy compares methods along five design axes. To our knowledge, this is the first overview to systematically taxonomize joint audio-visual editing, which we map as nine edit categories spanning 28 edit types. We describe methods, datasets, and metrics for each setting and close with the open problems we view as most consequential.

We present EditWorld, a video world model for precise editing and flexible referencing in interactable worlds. Existing video world models primarily focus on navigation, letting users explore generated worlds but offering limited control over how existing world content is modified. EditWorld extends world modeling from exploration to precise modification by streaming editing instructions and reference images during autoregressive generation. To support these capabilities, EditWorld introduces Gated Causal Attention for temporally varying editing conditions and reference images, together with a Sparse Context mechanism that maintains a bounded historical context for long-horizon inference. We further adopt joint autoregressive and bidirectional training with annealed self-resampling, and construct a dedicated data synthesis and annotation pipeline that provides supervision for world editing. We also present WBench-Editing to systematically evaluate streaming world editing capabilities. EditWorld achieves the best overall performance on WBench-Editing with an overall score of 73.8 and an editing score of 80.0, substantially outperforming existing methods on editing-related metrics. https://github.com/leoisufa/EditWorld

World models for manipulation are typically trained from video, yet the events that determine how manipulation unfolds, such as making and releasing contact, are difficult to observe visually and are often easier to sense through touch. We present the Dexterous Tactile World Model (DTWM), a video world model for future-frame prediction of egocentric manipulation from both observed video and tactile signals from a glove worn on each hand. We condition a pretrained video diffusion transformer on each hand's tactile signal through a zero-initialized residual at the corresponding hand location in the video tokens, while a causal mask prevents predicted frames from accessing future information. Compared with a vision-only model matched in architecture, parameters, and training, DTWM reduces the underestimation of hand motion from 23% to 9%, while reducing the perceptual error in the hand region by 7.4% across three training runs per model. The benefit also increases over the prediction horizon, with the improvement in the later predicted chunks being about 4.1x larger than in the first. DTWM also outperforms other visual-tactile world models under the same setting, and training with touch improves future-frame prediction even when no touch is available at inference. Ablations show that the model benefits from both the magnitude and spatial location of force: replacing the tactile signal with binary contact states, either per hand or per location, increases prediction error. The observed course of the force indicates whether the interaction will persist or change.

Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-fidelity image and video generation. Recent DiT systems increasingly use structured prompts for training, improving caption quality and prompt adherence. However, their generation quality can degrade severely under out-of-domain (OOD) prompts, including the free-form descriptions supplied by users at inference time. Although LLM-based rewriting can convert these prompts into structured formats, it does not guarantee that the rewritten prompts align with the training distribution. Our analysis links this degradation to attention sinks and reduced early-step image-to-text attention and shows that sink suppression alone is insufficient to restore generation quality. Despite effective sink suppression, models trained with standard gated attention exhibit reduced early-step image-to-text attention and suboptimal generation quality. Based on these insights, we propose Timestep-Aware Gated Attention (TSGate), which injects a timestep-conditioned bias into the gate signal so that gating behavior adapts across denoising steps. Extensive experiments show that TSGate consistently outperforms both the baseline and standard gated attention across multiple benchmarks, improving the raw-prompt DPG score by 9.5% over the baseline.