Spontaneous movement is one of the earliest windows onto an infant's neuromotor health, and structured clinical instruments that score it are validated early predictors of cerebral-palsy risk. However, they require specially trained raters, are time-consuming, and carry inter-rater variability. This motivates automated, video-based markerless assessment, especially as marker-based motion capture is impractical in infants. Yet the foundation models that make markerless capture possible are trained almost entirely on adults: our recent multi-view infant study found that no single model is jointly best, with strong 2D keypoint accuracy and direct 3D body recovery split across different models. While that study identifies this trade-off, it does not resolve it. Here, we perform cross-model distillation from the Sapiens 2 pose model into the SAM 3D Body model, using unannotated infant video alone. A frozen teacher supplies dense pseudo-labels, and a differentiable renderer aligns the predicted mesh to them in the training loop. On eleven held-out infants (18 sessions, 173 recordings) under our prior study's multi-view protocol, fine-tuning improves same-view 2D keypoint agreement with the Sapiens reference (median body percentage of correct keypoints @ 10px 0.22 -> 0.42, face 0.22 -> 0.42) and Procrustes-aligned mean per joint 3D position error (25.5 -> 22.2 mm). This demonstrates how cross-model distillation improves SAM 3D Body model performance on infants.
Real-world image super-resolution (Real-ISR) aims to preserve structures supported by the degraded observation while reconstructing perceptually realistic details. However, existing Real-ISR methods largely optimize fidelity and perceptual quality within a shared network, causing the two objectives to interfere throughout training and making their balance difficult to control. Recent one-step methods reduce sampling steps, yet often inherit both this coupled optimization behavior and the expensive high-resolution backbone of their multi-step predecessors. We argue that efficient Real-ISR requires not only a shorter sampling trajectory, but also specialized modeling of faithful reconstruction and perceptual detail synthesis. Based on this insight, we propose PixelIR, a fidelity-perception decoupling framework built upon pixel-space image-residual flow matching. PixelIR first learns an image flow that maps the degraded observation to a faithful reconstruction. Then, a residual flow synthesizes the missing perceptual details from noise without repeatedly relearning or overwriting the complete restoration solution. We further distill the teacher into a deployment-oriented one-step student within a coarse-to-fine pyramid architecture. Extensive experiments show that PixelIR achieves leading PSNR, SSIM, and LPIPS on both RealSR and DRealSR. The final model completes pixel-space restoration in a single evaluation with only 32.9M parameters, 89.7G MACs, and 8.5ms latency, demonstrating a strong practical fidelity-perception-efficiency balance.
Interactive world models extend video generation from offline clip synthesis toward persistent simulation of interactive virtual worlds, enabling applications in games, robotics, embodied agents, and XR. Achieving stable long-horizon interactive generation, however, remains challenging, as the model must simultaneously preserve scene geometry, dynamic consistency, and camera control while supporting real-time autoregressive generation. Building upon Matrix-Game 3.0, we present Matrix-Game 3.5, as shown in Figure 1, which advances real-time interactive world generation toward geometry-aware and long-horizon consistent simulation through three key improvements. First, we propose a unified geometry-aware memory framework, whose patch-memory and tiled-PRoPE components introduce no additional learnable parameters, combining explicit 3D patch retrieval with projective camera conditioning to enable geometry-consistent camera control and faithful long-horizon scene recall. Second, we introduce a static-dynamic disentangled world representation that separately models static scene geometry and dynamic subjects, preserving both geometric consistency and subject identity throughout long-horizon generation. Third, we develop a two-stage progressive real-time distillation framework that converts a bidirectional diffusion model into a few-step causal generator through Perceptual Flow Matching and curriculum based Self-Rollout DMD, enabling minute-long real-time interactive generation. Extensive experiments demonstrate that, with a unified training corpus spanning Unreal simulation environments, open-world games, and internet videos, MatrixGame 3.5 achieves strong performance in long-horizon scene recall, precise camera control, subject consistency, prompt-driven world generation, and stable real-time open-world interaction.
Conventional video editing primarily focuses on scene-level content, whereas live streaming places greater emphasis on the human subject. However, directly applying existing video-editing methods to human-centric live streaming remains challenging, as they may introduce facial-expression inconsistencies and typically depend on multiple offline inference steps, making them unsuitable for real-time interaction. We propose EditaLive, a novel framework for real-time streaming character video editing. In detail, we start from a pretrained image animation model (Wan-Animate), which naturally decouples appearance from motion, and repurpose it as the base model for instruction-based human-centric video editing by reference frame editing and video reconstruction via the collected CharEdit-50K dataset. Besides, we adapt the model from offline bidirectional to causal streaming generation, and design an aligned self-rollout distillation strategy that compresses the model into a two-step sampler, where fixed RoPE and align forcing reduce training--inference discrepancies, and first-frame preserved sparse attention filters redundant historical information to mitigate appearance drift. Extensive experiments demonstrate that EditaLive delivers state-of-the-art editing performance with faithful preservation of facial expressions and low-latency real-time streaming inference.
On-policy distillation (OPD), which leverages a pre-trained, specialized teacher model to provide dense supervisory signals, has achieved significant success in Large Language Models (LLMs) and has recently been adapted to flow matching models. However, this paradigm suffers from two major issues: First, training a separate, task-specific teacher for every new objective incurs high computational costs. Second, the discrepancy between teacher and student distributions often leads to compounding errors along the generation trajectory. In this paper, we introduce \textbf{Self-OPD}, a teacher-free OPD framework for flow matching models that turns the student's own self-exploration into step-wise supervision. At each timestep, Self-OPD branches the deterministic next-state prediction into $K$ stochastic SDE candidates, rolls them out with the ODE sampler, and compares their rewards against a deterministic self-reference baseline to obtain normalized advantages. The velocity field is optimized with an all-branch pull-push objective, where high-advantage branches attract the student and low-advantage branches repel it under direction-aware attenuation and SDE-variance normalization. For multi-objective alignment, Self-OPD fuses normalized scores at the reward level, avoiding direct gradient conflict. Experiments on single and mixed reward benchmarks show that Self-OPD outperforms prior RL and OPD methods without task-specific teachers.
Diffusion-based Video Virtual Try-On (VVT) achieves high visual fidelity through bidirectional spatio-temporal modeling, but complete-clip dependence incurs prohibitive latency and computational overhead in practical continuous deployment. Naively enforcing causality disrupts pretrained bidirectional priors and substantially degrades synthesis quality. We introduce LiveVVT, a rolling streaming diffusion framework that preserves bounded bidirectional modeling within causal recurrent generation. Within a fixed-size window, LiveVVT jointly denoises multiple video chunks under bounded look-ahead, preserving local bidirectional interactions while emitting one clean chunk per iteration. Beyond the window, two complementary memories sustain long-term consistency: a bounded temporal memory propagates recent dynamics and occlusion context, whereas a persistent global appearance memory, constructed once from the target garment and a frontal try-on keyframe, anchors garment details and dressed appearance throughout the stream. We further introduce a progressive distillation framework integrating bidirectional VVT learning, teacher-trajectory regression for causal few-step adaptation, and Collaborative Matching Distillation, which couples teacher-distribution matching with rolling flow matching on real videos to align optimization with recurrent inference. Experiments on paired and unpaired long-sequence benchmarks demonstrate superior generation quality over similarly sized models, with $26\times$ lower latency and $11\times$ higher throughput, enabling high-fidelity real-time streaming VVT.
An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time. The tension is structural: control wants a short horizon, memory wants an unbounded one. ReWorld separates the two during training and bounds them at inference. Mixed per-head attention windows confine most heads to the recent past while a small set of global heads attends over the entire history, and random head routing keeps either capability from binding to particular heads; random chunk dropping makes sparse histories in-distribution. At inference the whole past lives under a fixed budget: a bounded KV cache backed by a pose-indexed landmark bank, from which the model retrieves the landmarks nearest the current pose. A metric-scale-aligned data engine places eight sources -- Unreal-rendered fly-throughs, game roaming, and real-world footage -- on one physical action scale, so the same key press moves the camera the same distance in every source, and palindrome trajectories supply the revisit evidence that memory training needs. Distribution-matching distillation confined to a LoRA adapter then compresses sampling to four steps: one backbone serves both a high-fidelity multi-step mode and a real-time interactive one, streaming 704x1280 video across photorealistic, game-style, and stylized worlds. Under a three-axis protocol covering action following, long-horizon recall, and video quality, against six recent interactive world models it attains the best control fidelity ($11.95^\circ$ rotation error and the best camera-motion consistency) and the best generation quality; and on minute-long out-and-back rollouts ($64$\,s, $384$ latents), its fixed 12-chunk cache still regenerates the starting view -- at rollout lengths where a sliding window has long evicted the evidence and full-KV attention runs out of memory.
Md Thamed Bin Zaman Chowdhury, Moazzem Hossaincs.CV cs.AI
Road traffic injuries remain a major challenge in low- and middle-income countries, where proactive road safety auditing is limited by incomplete crash records, shortages of qualified auditors, and the high cost of large-scale field inspections. To address this problem, we propose Expert-Grounded Distillation (EGD), a novel artificial intelligence framework that transfers institutional road safety expertise into a compact vision-language model for scalable visual road safety auditing. The key innovation is a quantified expert-grounding stage in which the teacher vision-language model is calibrated against authoritative field audits. Large-scale annotation is permitted only after the teacher reaches substantial agreement with expert risk assessments (Cohen's kappa = 0.74). The calibrated teacher then generates structured supervision that is distilled into an 8-billion-parameter student vision-language model using Low-Rank Adaptation and a single leakage-free prompt. We also introduce Bangladesh Road Safety Audit (BD-ARSA), the first open, expert-grounded Bangladeshi visual road safety audit dataset containing 21,947 image-audit records with near-national coverage, and Expert-Grounded Road Safety Auditor (EG-ARSA), the first vision-language model developed specifically for this task. Experimental results show that grounded fine-tuning substantially improves ordinal risk assessment over the zero-shot baseline, while blind expert evaluation demonstrates that the compact student outperforms both its 31 billion-parameter teacher and Gemini-2.5-Flash. These findings demonstrate that EGD provides an effective and scalable engineering solution for proactive road safety auditing in resource-constrained environments.
Huaiyuan Qin, Gabriel James Goenawan, Zihang Lin +2cs.CV cs.LG
While linear attention is a compelling mechanism for high-resolution object detection due to its reduced cost for global token mixing, converting the Softmax-attention ViT backbone of a trained detector into a linear-attention one is not a trivial drop-in replacement. Directly swapping the attention operator leads to severe performance degradation, and generic label-free distillation, though effective for classification, often fails on detection tasks. We argue that the central challenge is \textit{detector-interface preservation}: the converted backbone must reproduce the exact feature tensors expected by the fixed downstream detector, rather than merely imitating internal Softmax hidden states. To address this, we introduce Detector-Interface Distillation (DiD), a label-free conversion method that exclusively trains the linear-attention backbone by aligning detector-facing interface tensors with those of a frozen Softmax teacher. On DOTA-v1.5, DiD substantially outperforms established baselines and matches supervised, fully trained linear models. Adaptation completes in roughly 87 minutes on 4 GPUs, and the linearized backbone cuts inference latency by ~62% and peak memory by ~49%. We hope our findings offer the community a simple, label-free route to reusing trained Softmax detectors as efficient linear ones, and encourage interface-aware objectives in future architecture-conversion work.
Omnimodal generation is central to a wide range of content creation and editing applications. In-context conditioning is essential to this paradigm. It allows diffusion transformers to process text instructions and visual references in a shared attention sequence. However, each reference image introduces thousands of tokens. Computation therefore grows rapidly with the number of references. Existing methods reduce computation through structured sparse attention, which limits interactions between reference and target tokens. This structure also makes the reference K and V independent of the denoising target, allowing them to be computed once and reused across steps. However, it blocks visual references from attending to the text instruction. This substantially degrades instruction following and reference fidelity in multi-reference editing. To resolve this conflict, we jointly redesign the token sequence and attention mask. Our beyond-mask design uses static text anchors to connect the instruction to the reference branch. It preserves exact K and V reuse without adding parameters. However, this direct architectural conversion degrades generation quality. We recover the lost performance through teacher-forced velocity distillation, followed by a short on-policy stage in which the teacher supervises student-visited states. To our knowledge, this is the first use of on-policy distillation for architectural recovery in diffusion models. Across three image-editing benchmarks, our method matches full-attention generation quality. With five reference images, it accelerates the complete 40-step denoising process by 3.92x, while static text anchors introduce negligible runtime overhead; the speedup reaches 5.47x at ten references in our scaling study.
We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing. Our goal is to explore how far a relatively small visual generator can be pushed through systematic training engineering under a constrained computational budget. Swift-Image adopts an efficient 6B single-stream DiT and a progressive training pipeline that evolves from broad semantic coverage to higher resolution, stronger visual quality, and unified generation-editing supervision. For post-training, we employ parallel expert reinforcement learning followed by multi-teacher on-policy distillation to alleviate interference among heterogeneous objectives. We further decouple high-level reasoning from pixel-level rendering with a Prompt Enhancer that translates user requests into generator-aligned visual specifications. For efficient deployment, structural pruning and few-step distillation produce 3B and accelerated variants. Swift-Image achieves leading aggregate performance among evaluated open-source models with only 6B parameters and 243K GPU training hours; the compressed 3B model incurs nearly no loss, while few-step distillation further improves aggregate editing performance with substantially fewer sampling steps. Our study also summarizes practical lessons for architecture, data curriculum, post-training, prompt enhancement, and model compression.
Recently, open-vocabulary 3D object detection (3D-OVD) has gained increasing attention for its ability to detect unseen objects in 3D scenes. Existing approaches typically adopt a two-stage pipeline that first discovers novel objects using foundation models and then trains a 3D-OVD model based on these discovered objects. Although effective, this pipeline often suffers from inaccurate localization and mismatched classification during the discovery stage, which subsequently limits the performance of the model training stage. To address these limitations, we advocate for improving both the reliability of novel object discovery and the robustness of model training, and propose an innovative framework. Specifically, for reliable discovery, our co-distillation strategy distills high-quality novel objects by applying Hungarian matching over a comprehensive score that incorporates geometric consistency, structural objectness, and semantic certainty. To enhance robust model training, we further propose a dual-guidance learning scheme, incorporating a scene-awareness-guided uncertainty regularization for the regression head and an LLM-guided hierarchical alignment for the classification head, effectively mitigating the negative effects of imprecise 3D bounding boxes and semantic ambiguity. Extensive experiments on SUN RGB-D and ScanNetV2 demonstrate that our method achieves significant performance gains over state-of-the-art approaches. Code is available at https://github.com/shangboyuan/Co-3DGT
Vision encoders are a critical component of vision-language models, and scaling their capacity effectively improves performance. However, dense scaling increases compute cost and inference latency. Mixture-of-Experts (MoE) architectures offer a compelling alternative, having enabled efficient scaling in LLMs, yet the MoE design space for CLIP-style vision encoders remains underexplored at State-of-the-Art (SOTA) levels. In this work, we systematically study MoE designs for vision encoder scaling and find that fine-grained MoE topologies yield substantial gains over both dense and standard MoE counterparts. We further propose an auxiliary-loss-free balancing variant for better expert utilization, and design a specialized MoE kernel to mitigate inference latency overhead. To enhance video capabilities while preserving image knowledge, we introduce frame-level distillation paired with a novel freezing mechanism. We pretrain a series of Mixture-of-Experts Vision Encoders (MoE-ViE) across a range of sizes, all consistently outperforming their dense counterparts. Our largest model matches the zero-shot performance of a SOTA encoder 1.7x its size at 76% of its latency. When aligned with an LLM, MoE-ViE surpasses all compared encoders on image and video benchmarks, including those with up to 5x more activated parameters. Code is available at https://github.com/facebookresearch/moe_vie.
Interactive video generation and editing are becoming increasingly important for creative design. In this report, we introduce EditStream: a unified framework for interactive video generation and editing. EditStream unifies multiple video creation and manipulation tasks within a single DiT-based model through flexible task-specific conditioning, and further transforms it into a fast, few-step autoregressive model for efficient streaming. It supports Text-to-Video, Image-to-Video, Video-to-Video, Editing Propagation, Reference-guided Video Editing, and Camera Pose Change, enabling flexible control over video generation, transformation, and editing within one system. To make the unified model practical for interactive use, we develop a two-stage distillation approach that combines Velocity Moment Matching (VMM) with autoregressive unrolling. VMM matches conditional velocity moments at student-reached intermediate states to preserve generation quality and motion, while unrolling exposes the student to its own autoregressive predictions to improve temporal stability. Together, they alleviate common challenges in few-step autoregressive video generation, including over-saturation, degraded motion, temporal instability, and complex training. EditStream provides a practical and scalable solution that bridges high-quality diffusion-based video models with interactive creative workflows.
Action-conditioned video world models require low-latency causal generation and reliable responses to game-native controls. Although causal distillation enables one- or few-step video synthesis, extending it to interactive world models remains challenging, as discrete keyboard states and continuous mouse motion must remain aligned with temporally compressed latent chunks during causal training and autoregressive rollout. We introduce ForgeWM, a progressive framework that transforms a bidirectional action-conditioned video generator into efficient few-step world models through domain adaptation, teacher-forced causal training, causal consistency distillation, and on-policy distribution matching with a bidirectional teacher. The resulting budget-specialized students operate at steady-state denoising budgets of 1, 2, and 4 steps. ForgeWM further supports a dual-path deployment protocol combining latency-critical interaction with optional replay-time refinement, where the one-step student re-noises and refines its saved draft. On paired Minecraft trajectories, ForgeWM leads the evaluated systems in Imaging Quality, reference-aligned motion-profile agreement, action-sign accuracy, and mouse-control accuracy, while achieving the lowest reference LPIPS; the same four-stage recipe transfers to gamepad-controlled FPS gameplay. Replay-time refinement matches four-step reference quality while remaining roughly three times closer to the experienced trajectory than regeneration from noise. These results demonstrate ForgeWM's effectiveness for controllable few-step video generation.
Interactive autoregressive video generation demands both low-latency rollouts and precise online control. Few-step distillation accelerates generation by reducing denoising steps, while online control imposes a causal constraint: frames and blocks should depend on history and controls available during generation. Existing video distribution matching distillation (DMD) pipelines, however, often supervise causal few-step students using bidirectional teachers that score complete clips. The score for a target can therefore depend on future frames and controls that were unavailable when the student generated it, misaligning teacher supervision with the student's causal information set. We introduce Context-Matched Distillation (CMD), a causal DMD framework that aligns teacher supervision with the information available when each target is generated. CMD replaces bidirectional full-clip scoring with a causal teacher that evaluates each target without access to future frames or controls. The same causal teacher initializes the few-step student, establishing a consistent causal formulation across teacher training, student distillation, and inference. Beyond aligning the temporal information boundary, Prefix Scoring matches supervision to the student's realized rollout context by evaluating each target under the cached student-generated prefix that produced it. Prefix Corruption further stabilizes training by perturbing unreliable prefixes produced early in training while preserving this target-context alignment. With a simple causal formulation, CMD naturally extends to frame-wise and chunk-wise generation, long video distillation, and camera-conditioned distillation. Experiments demonstrate state-of-the-art aggregate performance among autoregressive methods on both short- and long-video benchmarks, together with substantially improved adherence to time-varying camera controls.
Infrared-visible image fusion (IVIF) is pivotal for multimodal perception, yet reconciling the inherent information disparity between thermal and textural features remains a fundamental challenge. Existing prior-guided methods often rely on static constraints that induce optimization conflicts or utilize extrinsic semantic priors from large-scale foundation models (e.g., CLIP/DINO), which frequently fail to exploit the intrinsic modality characteristics essential for high-fidelity fusion. To address these issues, we propose P2Fusion, a prior-guided distillation-based framework that reformulates IVIF via dual intrinsic prompts. Instead of imposing hard-coded penalties, we distill image-intrinsic priors, thermal saliency and spatial quality, into learnable dynamic regulators. Specifically, a Teach-to-Fuse mechanism provides dual-granularity progressive guidance, coupled with a Gated Dynamic Expert Recalibration (GDER) module for decoupled feature refinement. This design enables the network to adaptively mediate modal competition through expert specialization. Extensive experiments demonstrate that P2Fusion achieves state-of-the-art performance across five mainstream datasets. Notably, our framework demonstrates consistent performance advantages in fusion quality, achieving state-of-the-art results in 14 out of 20 key evaluation metrics across 5 benchmarks. Furthermore, it effectively contributes to the robustness of downstream perception, such as +3.2% mAP on MSRS, +0.5% mAP on M3FD and +0.9% mAP on DroneVehicle for object detection. Our code will be available at https://github.com/YiShi99/P2Fusion
Existing streaming video systems often rely on sequential, distillation-centered training pipelines to enable few-step long-video generation. However, this paradigm suffers from two limitations. First, failures or distribution shifts introduced in earlier stages affect later optimization, complicating the training process to converge. Second, the distillation-centric objective favours short-term generation but is prone to quality degradation when autoregressive errors accumulate over long rollouts. We propose Avatar-Forever, a decoupled parallel training framework for high-quality real-time infinite interactive avatars. Instead of coupling generation efficiency and long-horizon robustness under a sequential distillation pipeline, we treat them as two independent capabilities that can be trained in parallel. One branch performs full-parameter distillation to train an efficient generator with high visual quality, while another trains a lightweight long-horizon adapter via Recovery-oriented Rollout Training (RRT), which improves generation robustness under long-horizon inference conditions. Our decoupled parallel training design simplifies the overall training process and avoids unnecessary objective conflicts between few-step generation and long-horizon adaptation. We further introduce ForeverCache, a chunk-wise feature caching mechanism to substantially reduce redundant history computation during streaming inference. Built upon a 22B video foundation model, Avatar-Forever supports unbounded audio-driven avatar generation while maintaining identity consistency, motion coherence, and visual fidelity, enabling an end-to-end throughput of high-resolution 768x512 videos at 27.2 FPS on a single H100 GPU and providing a practical path toward stable digital humans.
Diffusion models have enabled high-quality video generation in recent years, but the high cost of iterative sampling hinders their practical deployment. Few-step distillation alleviates this cost, yet exposes a quality--diversity trade-off between its two dominant paradigms: trajectory-level distillation (e.g., sCM) favors diversity, whereas distribution-level distillation (e.g., DMD) favors quality. Targeting extreme two-step video generation, we introduce DUET, which reconciles the two paradigms through a noise-level duet of experts: an sCM expert takes the high-noise step to lay out diverse structure, and a DMD expert takes the low-noise step to refine appearance detail. Since the two experts are trained independently with their native objectives, DUET sidesteps the optimization difficulties of loss-level combinations and delivers quality and diversity jointly rather than trading one for the other. We further identify the relay interface and the high-noise stage as the remaining bottlenecks, and address them with RL-guided expert adaptation, yielding DUET+. With the Wan2.1-T2V-1.3B backbone, DUET lifts the two-step quality of sCM close to the level of DMD while retaining nearly all of its structural diversity---about twice that of DMD---and DUET+ further improves overall quality while preserving this diversity advantage. Together, these results establish noise-level expert specialization as a simple, effective paradigm for reconciling diversity and quality in two-step video generation.
Flow-matching models are now a mainstream method to image generation, but its adaptation to diverse downstream scenarios typically relies on post-training, which may cause conflicts among task-specific optimization objectives. Reinforcement learning enables direct optimization of task-specific rewards beyond the original models, yet trajectory-level optimization may incur high-variance gradients and cross-task interference. On-policy distillation (OPD) offers dense and stable supervision on student rollouts, but conventional teacher matching remains imitation-based. We propose DreOPD, a Degraded-reference extrapolative OPD method for flow-matching models that bridges these two paradigms. Our DreOPD converts implicit reward extrapolation into closed-form velocity regression, enabling extrapolative post-training with the stability of OPD. It further uses a mildly degraded reference to strengthen the teacher-reference contrast, yielding a clearer extrapolation direction. Experiments on single- and multi-teacher settings show that DreOPD outperforms OPD and multi-task RL baselines in average performance, while surpassing specialized teachers on most metrics.
Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We instead take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide a natural source of distillation supervision rather than a disposable byproduct of sampling. Based on this insight, we propose REST (Reward-Enhanced Scored-Trajectory Distillation), a single-stage RL-distillation co-training framework that attaches a decoupled student to an arbitrary RL teacher. The student learns segment-wise from the teacher's evolving rollout trajectories while leaving the original teacher optimization unchanged. To prevent uniform imitation from preserving undesirable low-reward behaviors, we further introduce Advantage-Modulated Distillation (AMD), which transforms rollout advantages into signed weights over a base distillation loss. AMD strengthens supervision from preferred trajectories and mildly repels the student from low-reward ones. The resulting framework is lightweight and plug-and-play, requires no extra image rollouts, no separate distillation dataset, and no adversarial training. Experiments on compositional generation, visual text rendering, and human-preference alignment show that REST enables few-step CFG-free inference that matches or surpasses its 40-step RL teacher, with an overall additional training cost below 25% over pure RL. REST improves DrawBench PickScore over RTDMD by 0.82 while requiring only one-fifth of the training iterations.
Streaming world models predict future visual states online while maintaining physically coherent dynamics over long horizons. However, their rollouts often violate basic physical constraints. A common approach distills pretrained bidirectional DiTs into few-step causal generators. However, this paradigm suffers from two fundamental limitations: generic bidirectional teachers acquire limited physical priors from visually oriented pretraining, and the limited priors suffer further loss during bidirectional-to-causal distillation. We present PhyS, a three-stage framework for distilling physical priors into streaming world models. To acquire physical priors from real-world interactions, we construct PhyS-120K, a dataset of 120K real-world physical-interaction videos spanning rigid-body dynamics, soft-body deformation, fluid phenomena, and phase transitions. Each video is annotated with structured descriptions of object properties and causal state transitions. Physics-aware supervised fine-tuning injects the physical priors into a bidirectional 14B DiT teacher, which we then distill into a lightweight 1.3B causal DiT for few-step autoregressive streaming generation. Finally, we use online reinforcement learning to incentivize the distilled model to generate physically plausible rollouts and further propose Temporal Credit Routing (TCR) to address temporal credit assignment. TCR evaluates physical consistency over overlapping temporal windows and routes the resulting group-relative advantages to temporally aligned denoising actions. On PhysicsIQ, PhyS improves the Wan2.1-14B teacher by 18.2\% and the Self Forcing, Rolling Forcing, and Causal Forcing by 23.7\%, 14.8\%, and 31.4\%, respectively. Results also improve the physics-aware video benchmarks VideoPhy, VideoPhy2, and PhyGenBench. The dataset, code, and more sample videos are available on our Project Page.
Oliver Lemke, Alexander Liniger, Abel Gawel +1cs.CV cs.RO
LiDAR serves as a primary sensing modality for robots operating in outdoor environments. However, the performance of deep learning models in this domain is severely limited by the scarcity of labeled data, a direct result of the high cost of 3D annotation. Self-supervised learning addresses this scarcity by learning general-purpose features from unlabeled data. In this work, we present a multi-modal, multi-teacher distillation framework for self-supervised learning on outdoor LiDAR point clouds. Building upon the Sonata architecture, we introduce Vernata, consisting of three extensions: sparse view augmentation to improve robustness against varying point densities, a memory bank mechanism to stabilize resource-constrained training, and cross-modal distillation utilizing dense, high-resolution 2D image features to enable fine-grained semantic guidance. We evaluate our method on the GrandTour, TartanGround, and Waymo datasets, as well as data collected from our own robotic platforms. Our experiments demonstrate a significant performance improvement over Sonata baselines, yielding mIoU scores of 54.7 on TartanGround (+5.9 points, +12.1%) and 57.1 on Waymo (+7.3 points, +14.7%). Finally, we show that the self-supervised approach maintains strong performance even in reduced-modality settings (lacking color or normals), achieving competitive mIoU scores of 49.4 and 50.2 on the respective datasets.
Kevin Lane, Zhongying Wang, Esther Rolf +1cs.CV cs.AI
The plethora of readily available geospatial data offers exciting opportunities to learn high quality representations of the planet, but the sheer size of the Earth Observations (EO), differing modalities, and different sensor types pose significant challenges in doing so. Location encoders have emerged as an efficient way of compressing EOs into location-specific embeddings. However, current state-of-the-art location encoders rely on computationally expensive CLIP-style frameworks that require large batch sizes in the 16K--32K range, suffer from false negative samples, and scale poorly with additional modalities. We introduce the Scalable Location Encoder via Distillation (SLED), a distillation-based location encoder that uses geospatial location as a binding modality to pretrain location encoders with any modality of geospatial data. The resulting location encoder framework is lightweight, modular, and can flexibly incorporate multiple modes, while eliminating the need for spatiotemporal coregistration of samples. SLED is performant with batch sizes as small as 128, enabling pretraining at a fraction of the runtime and compute costs of current state-of-the-art models. We demonstrate our approach by pretraining unimodal and multimodal SLED models on Sentinel-1, Sentinel-2, and Landsat imagery. We show that both unimodal and multimodal SLED models keep pace with or outperform existing approaches on a diverse set of 19 human-centric benchmark tasks and explore the benefits of using additional modes in pretraining.
We present InsertFuse, a unified framework for multi-category reference-guided image insertion. Its key idea is to decouple category-specific expertise learning from cross-category capability consolidation. InsertFuse first trains specialized experts for different insertion categories and then introduces Insertion On-Policy Distillation (IOPD) to consolidate their capabilities into a single student. By querying the matched expert at states visited by the student, IOPD preserves category-specific insertion behavior while mitigating the cross-category interference caused by direct joint training. To improve spatial control, we propose Token-Aligned Geometry Conditioning (TAGC), which maps mask-derived geometric cues to the visual token grid, and Region-Balanced Flow Matching, which separately normalizes prediction errors inside and outside the insertion region to prevent background-dominated and scale-dependent supervision. We further introduce Reference CFG to isolate and strengthen the guidance induced by the visual reference under fixed scene and geometry conditions, with IOPD transferring this enhanced supervision into the unified student. Extensive experiments on the public AnyInsertion benchmark and our multi-category test set demonstrate state-of-the-art performance on most metrics, showing strong reference fidelity and generation quality across diverse insertion categories.
Character image animation remains a foundational yet challenging task in computer vision. Existing approaches can be broadly categorized into three paradigms: methods based on explicit motion representations suffer from extraction errors and identity drift; methods based on implicit motion features lose fine-grained dynamics through compression; and in-context learning approaches avoid intermediate representations but incur prohibitive computational costs. Furthermore, all current systems are designed for offline synthesis, unable to meet the real-time requirements of interactive applications such as digital avatars and live-streaming hosts. To address these limitations, we present Wan-Animate-2, an end-to-end character animation framework that directly consumes the driving video within a redesigned Diffusion Transformer. Our architecture achieves superior motion fidelity and identity preservation by eliminating intermediate motion extractors entirely. We further introduce text driven viewpoint control that decouples the output camera perspective from the driving video--a capability rarely supported by prior character animation methods that rely on explicit motion representations. Beyond generation quality, we present Wan-Animate-2-Lite, an efficient variant that reduces inference latency to real-time thresholds through a three-stage training paradigm: teacher forcing pretraining with error buffer mechanism, and Self-Forcing distillation with chunk-wise backpropagation. This enables streaming character animation for interactive applications, opening new deployment scenarios that were previously infeasible. Qualitative evaluations and user studies demonstrate that Wan-Animate-2 achieves high-fidelity animation results across diverse characters and motion patterns. To foster further research and community development, we will release the Wan-Animate-2-Base model weights to the public.
Dense colored LiDAR maps provide accurate city-scale geometry, but lifting them into 3D Gaussian Splatting (3DGS) retains millions of primitives, making the resulting models costly to store, transmit, render, and adapt. Aggressive primitive reduction alleviates this burden, but can remove the local surface support needed for stable novel-view synthesis and downstream geometric use. We introduce G$^2$ARD-GS, a geometry-guided distillation method that converts a dense Gaussian prior instantiated either as a training-free point-cloud lift or a trained GS model into a compact, reusable representation. G$^2$ARD-GS progressively consolidates the prior into surface-aware representatives, then recovers appearance on the resulting fixed topology under construction-time anchor constraints, with no primitives added or removed during recovery. Under limited supervision, geometry-aware view selection allocates the available view budget. On MatrixCity, G$^2$ARD-GS achieves the best PSNR, SSIM, and LPIPS across matched $5\times$--$30\times$ compression budgets, outperforming PUP by $3.2$--$6.8$,dB in PSNR. When reused as frozen geometry, the compact model improves off-trajectory appearance adaptation by $3.7$--$4.9$,dB over PUP 3D-GS and preserves image-to-model registration accuracy on Cambridge KingsCollege at $30\times$ compression. Project page: https://patrick1159.github.io/gardGS-page/.
Recent video models increasingly support generation, reference conditioning, and editing within a single model, yet typically expose them as separate operations over fixed inputs. Practical creation unfolds across multiple shots, requiring one model to generate from text, follow a reference, or edit source footage while maintaining shared history. We formalize this setting as interactive multi-shot video creation (IMVC) and introduce ContextMaster, a unified model with a role-aware context representation for these operations. An interactive model must retain access to an expanding history without allowing the context read cost at each denoising step to grow. ContextMaster combines reusable clean context states with fixed budget sparse context routing and uses ConstraintSink to keep task constraints visible. To address the dual challenges of sparse context access and inference with few denoising steps, we propose a two-stage privileged context distillation framework, which transfers full context behavior from a dense teacher through consistency distillation and then refines deployment rollouts with distribution matching. Experiments on the three primitive tasks demonstrate improved task fulfillment and consistency across shots over specialized baselines. User studies further validate flexibly composed workflows, while the model reaches 16 FPS on a single GPU.
Real-time video editing requires low-latency causal generation with bounded computational resources while preserving source fidelity and long-term temporal consistency. We present JoyAI-Video-Edit, a 16B-parameter autoregressive diffusion framework for real-time, open-ended video editing without access to future frames or a predefined video duration. Our method combines chunk-wise autoregressive adaptation, Source-Anchored Distribution Matching Distillation (SA-DMD), and Long-Horizon Autoregressive Distillation to reduce train--inference mismatch, preserve source fidelity during two-step generation, and mitigate accumulated temporal drift. Extensive automatic and human evaluations show that JoyAI-Video-Edit substantially outperforms existing streaming editors and remains competitive with strong offline systems on both short and long videos. The complete system achieves end-to-end 720p video editing at approximately 30 FPS on a single Nvidia B200 GPU. Code is available at https://github.com/jd-opensource/JoyAI-Video-Edit.
Real-time 3D perception is crucial for robotics, augmented reality, and embodied intelligence applications. Existing multi-view stereo (MVS) methods primarily rely on geometric correspondences, which often fail in textureless or repetitive regions, while monocular depth models leverage strong image-level priors but lack robust multi-view geometric constraints. More importantly, in robotics and embodied manipulation scenarios, high-quality 3D geometry is not only essential for static reconstruction, but also serves as a critical foundation for learning temporally consistent 4D representations. To obtain visual representations with stronger structural awareness and greater potential for spatiotemporal extension, we present LiteMVS, a lightweight multi-view depth estimation model that integrates plane-sweep geometric reasoning with strong monocular semantic and structural priors. The central idea of LiteMVS is to efficiently inject high-level monocular knowledge, obtained from lightweight segmentation models and large-scale vision foundation models, into a multi-view stereo framework. In particular, LiteMVS enriches the cost volume with semantic descriptors and employs a Mixture-of-Experts (MoE) formulation to enable adaptive geometric aggregation across depth hypotheses. Moreover, geometric priors distilled from vision foundation models further strengthen monocular guidance without increasing inference cost. Through this design, LiteMVS not only improves depth estimation and 3D reconstruction quality in static scenes, but also provides a more reliable geometric foundation for subsequent temporal modeling and 4D representation learning. Experiments on ScanNetv2 and 7-Scenes demonstrate that LiteMVS achieves high-quality depth prediction and 3D reconstruction while maintaining competitive efficiency.