Teaching robots to fold, drape, or reposition deformable objects such as cloth will unlock a variety of automation applications. While remarkable progress has been made for rigid object manipulation, manipulating deformable objects poses unique challenges, including frequent occlusions, infinite-dimensional state spaces and complex dynamics. Just as object pose estimation and tracking have aided robots for rigid manipulation, dense 3D tracking (scene flow) of highly deformable objects will enable new applications in robotics while aiding existing approaches, such as imitation learning or creating digital twins with real2sim transfer. We propose DeformGS, an approach to recover scene flow in highly deformable scenes, using simultaneous video captures of a dynamic scene from multiple cameras. DeformGS builds on recent advances in Gaussian splatting, a method that learns the properties of a large number of Gaussians for state-of-the-art and fast novel-view synthesis. DeformGS learns a deformation function to project a set of Gaussians with canonical properties into world space. The deformation function uses a neural-voxel encoding and a multilayer perceptron (MLP) to infer Gaussian position, rotation, and a shadow scalar. We enforce physics-inspired regularization terms based on conservation of momentum and isometry, which leads to trajectories with smaller trajectory errors. We also leverage existing foundation models SAM and XMEM to produce noisy masks, and learn a per-Gaussian mask for better physics-inspired regularization. DeformGS achieves high-quality 3D tracking on highly deformable scenes with shadows and occlusions. In experiments, DeformGS improves 3D tracking by an average of 55.8 × 1.5 m in area. Website: https://deformgs.github.io .

This paper reconsiders intelligence from a vision-centered perspective and examines whether intelligence emerging from visual experience and learning may provide a pathway toward AGI. In the language domain, beginning with the introduction of the Transformer architecture, the GPT series has demonstrated transfer to unseen tasks through autoregressive language modeling on web-scale text combined with aggressive scaling. This raises a natural question, namely, what capabilities and forms of intelligence can emerge from visual modalities such as images, videos, and geometry? In this paper, we discuss whether visual intelligence can serve as a pathway toward AGI, referred to in this paper as visual general intelligence (VGI), by bringing together contributors from diverse standpoints and affiliations. Our aim is not to offer a single definition of visual intelligence, but to clarify the principles that computer vision should pursue in the AGI era, the visual input modalities, the benchmarks, the learning paradigms, and the relationship between vision, when taken as the core, and other modalities such as language.

We introduce CRISP, a method that recovers simulatable human motion and scene geometry from monocular video. Prior work on joint human--scene reconstruction relies on data-driven priors and joint optimization with no physics in the loop, or recovers noisy geometry with artifacts that cause motion-tracking policies with scene interactions to fail. In contrast, our key insight is to fit simulation-ready convex planar primitives to a depth-based point cloud reconstruction of the scene via a simple clustering pipeline over depth, normals, and flow. To reconstruct scene geometry that might be occluded during interactions, we use human--scene contact modeling (e.g., using human posture to reconstruct the occluded seat of a chair). Finally, we ensure that human and scene reconstructions are physically plausible by using them to drive a humanoid controller via reinforcement learning. Our approach reduces motion-tracking failure rates from 55.2\% to 6.9\% on human-centric video benchmarks (EMDB, PROX), while delivering 43\% faster RL simulation throughput. This demonstrates CRISP's ability to generate physically valid human motion and interaction environments at scale, advancing real-to-sim applications for robotics.

Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that can be applied to a variety of downstream tasks such as retrieval, classification, and segmentation. However, such representations tend to focus on the most salient visual cues in the image, with no way to direct them toward less prominent concepts of interest. In contrast, Multimodal LLMs can be guided with textual prompts, but the resulting representations tend to be language-centric and lose their effectiveness for generic visual tasks. To address this, we introduce Steerable Visual Representations, a new class of visual representations, whose global and local features can be steered with natural language. While most vision-language models (e.g., CLIP) fuse text with visual features after encoding (late fusion), we inject text directly into the layers of the visual encoder (early fusion) via lightweight cross-attention. We introduce benchmarks for measuring representational steerability, and demonstrate that our steerable visual features can focus on any desired objects in an image while preserving the underlying representation quality. Our method also matches or outperforms dedicated approaches on anomaly detection and personalized object discrimination, exhibiting zero-shot generalization to out-of-distribution tasks.

Many robotic tasks require short-term memory, whether it's retrieving an object that's no longer visible or turning off an appliance after a set period. Yet, most visuomotor policies trained via imitation learning rely only on immediate sensory input without using past experiences to guide decisions. We present PRISM, a transformer-based architecture for visuomotor policies to effectively use short-term memory via two key components: (i) gated attention, which filters retrieved information to suppress irrelevant details, improving performance by reducing the spurious correlations between the history and current action prediction, (ii) a hierarchical architecture that first compresses local information into compact tokens and then integrates them to capture temporally extended dependencies, improving its compute and memory footprint. Together, these mechanisms enable us to scale short-term memory in visuomotor policies for up to two minutes. To systematically evaluate memory in visuomotor control, we introduce ReMemBench -- a benchmark of eight diverse household manipulation tasks spanning four categories of short-term memory -- designed to foster general memory mechanisms rather than siloed, task-specific solutions. PRISM consistently outperforms prior works, including recurrent architectures, transformers, and their variants -- achieving an absolute improvement of 5%--12% over the strongest baseline. On the RoboCasa and LIBERO benchmarks, it achieves absolute improvements of 11%--15% over its no-memory variant and fine-tuned Vision-Language-Action baselines such as GR00T-N1-3B and OpenVLA, despite not leveraging any large-scale pretraining. Together, PRISM and ReMemBench establish a foundation for developing and evaluating short-term memory-augmented visuomotor policies that scale to long-horizon tasks. Additional materials are available at https://shahrutav.github.io/short-term-memory

Creating assembly products demands significant manual effort and expert knowledge in 1) designing the assembly and 2) constructing the product. This article introduces Prompt-to-Product, an automated pipeline that generates real-world assembly products from natural language prompts. Specifically, we leverage bricks as the assembly platform and automate the process of creating brick assembly structures. Given the user design requirements, Prompt-to-Product generates physically buildable brick designs and then leverages a bimanual robotic system to construct the real assembly products, bringing user imaginations into the real world. We conduct a comprehensive user study, and the results demonstrate that Prompt-to-Product significantly lowers the barrier and reduces manual effort in creating assembly products from imaginative ideas.

We present Any4D, a scalable multi-view transformer for metric-scale, dense feed-forward 4D reconstruction. Any4D directly generates per-pixel motion and geometry predictions for N frames, in contrast to prior work that typically focuses on either 2-view dense scene flow or sparse 3D point tracking. Moreover, unlike other recent methods for 4D reconstruction from monocular RGB videos, Any4D can process additional modalities and sensors such as RGB-D frames, IMU-based egomotion, and Radar Doppler measurements, when available. One of the key innovations that allows for such a flexible framework is a modular representation of a 4D scene; specifically, per-view 4D predictions are encoded using a variety of egocentric factors (depthmaps and camera intrinsics) represented in local camera coordinates, and allocentric factors (camera extrinsics and scene flow) represented in global world coordinates. We achieve superior performance across diverse setups - both in terms of accuracy (2-3X lower error) and compute efficiency (15X faster), opening avenues for multiple downstream applications.

Radars are an ideal complement to cameras: both are inexpensive, solid-state sensors, with cameras offering fine angular resolution, while radars provide metric depth and robustness under adverse weather. However, radar data is more difficult to interpret than camera images and varies significantly between sensors, necessitating increased reliance on simulation for prototyping sensors and processing pipelines. Recent work treating radar reconstruction as a novel view synthesis problem has shown great promise in reconstructing radar-relevant geometry and simulating low-level radar data. However, such methods are constrained by the low spatial resolution of the underlying radar. To address this, we propose a unified differentiable renderer, RadarSim, which leverages the high angular resolution of RGB cameras to generate Doppler radar range images from a camera-initialized neural field. Using a novel data set of calibrated radar camera recordings from a custom hand-held rig, we demonstrate that RadarSim produces sharper geometry and Doppler range frames than radar-only reconstructions.

Aligning Large Language Models (LLMs) and Large Multimodal Models (LMMs) to human preferences is a central challenge in improving the quality of the models' generative outputs for real-world applications. A common approach is to use reward modeling to encode preferences, enabling alignment via post-training using reinforcement learning. However, traditional reward modeling is not easily adaptable to new preferences because it requires a separate reward model, commonly trained on large preference datasets. To address this, we introduce Activation Reward Models (Activation RMs) – a novel few-shot reward modeling method that leverages activation steering to construct well-aligned reward signals using minimal supervision and no additional model finetuning. Activation RMs outperform existing few-shot reward modeling approaches such as LLM-as-a-judge with in-context learning, voting-based scoring, and token probability scoring on standard reward modeling benchmarks. Furthermore, we demonstrate the effectiveness of Activation RMs in mitigating reward hacking behaviors, highlighting their utility for safety-critical applications. Toward this end, we propose PreferenceHack, a novel few-shot setting benchmark, the first to test reward models on reward hacking in a paired preference format. Finally, we show that Activation RM achieves state-of-the-art performance on this benchmark, surpassing even GPT-4o.

We tackle the problem of sparse novel view synthesis (NVS) using video diffusion models; given K (≈ 5) multi-view images of a scene and their camera poses, we predict the view from a target camera pose. Many prior approaches leverage generative image priors encoded via diffusion models. However, models trained on single images lack multi-view knowledge. We instead argue that video models already contain implicit multi-view knowledge and so should be easier to adapt for NVS. Our key insight is to formulate sparse NVS as a low frame-rate video completion task. However, one challenge is that sparse NVS is defined over an unordered set of inputs, often too sparse to admit a meaningful order, so the models should be invariant to permutations of that input set. To this end, we present FrameCrafter, which adapts video models (naturally trained with coherent frame orderings) to permutation-invariant NVS through several architectural modifications, including per-frame latent encodings and removal of temporal positional embeddings. Our results suggest that video models can be easily trained to "forget" about time with minimal supervision, producing competitive performance on sparse-view NVS benchmarks. Project page: https://frame-crafter.github.io/

We introduce MapAnything, a unified transformer-based feed-forward model that ingests one or more images along with optional geometric inputs such as camera intrinsics, poses, depth, or partial reconstructions, and directly regresses the metric 3D scene geometry and cameras. MapAnything lever-ages a factored representation of multi-view scene geome-try, i.e., a collection of depth maps, local raymaps, camera poses, and a metric scale factor that effectively upgrades local reconstructions into a globally consistent metric frame. Standardizing the supervision and training across diverse datasets, along with flexible input augmentation, enables MapAnything to address a broad range of 3D vision tasks in a single feed-forward pass, including uncalibrated structure-from-motion, calibrated multi-view stereo, monocular depth estimation, camera localization, depth completion, and more. We provide extensive experimental analyses and model ab-lations demonstrating that MapAnything We provide extensive experimental analyses and model ab-lations demonstrating that MapAnything outperforms or matches specialist feed-forward models while offering more efficient joint training behavior, thus paving the way toward a universal 3D reconstruction backbone.

Text-to-image (T2I) models contain rich spatial priors. Synthesizing photorealistic, cluttered scenes requires an understanding of geometry, including perspective and relative scale. Prior works adapt T2I models to leverage this prior for depth prediction, but they require dense depth data and involve complex recipes. We propose Modality Forcing, a simple, scalable post-training recipe for joint image-depth generation using a single DiT trained on sparse depth data. Modality Forcing enables conditional and joint generation of image and depth in any permutation by assigning separate noise levels per modality. Per-modality decoders let us train on sparse, real-world depth and achieve strong, generalizable depth prediction. We further show that Modality Forcing inherits the scalability of T2I pre-training: by training a set of T2I models from scratch (370M to 3.3B parameters), we find that larger models trained on more image data produce more accurate depth. Our strongest model is competitive with state-of-the-art monocular depth estimators and reduces AbsRel by 57

Autonomous Vehicles (AVs) collect and pseudo-label terabytes of multi-modal data localized to HD maps during normal fleet testing. However, identifying interesting and safety-critical scenarios from uncurated driving logs remains a significant challenge. Traditional scenario mining techniques are error-prone and prohibitively time-consuming, often relying on hand-crafted structured queries. In this work, we revisit spatio-temporal scenario mining through the lens of recent vision-language models (VLMs) to detect whether a described scenario occurs in a driving log and, if so, precisely localize it in both time and space. To address this problem, we introduce RefAV, a large-scale dataset of 10,000 diverse natural language queries that describe complex multi-agent interactions relevant to motion planning derived from 1000 driving logs in the Argoverse 2 Sensor dataset. We evaluate several referential multi-object trackers and present an empirical analysis of our baselines. Notably, we find that naively repurposing off-the-shelf VLMs yields poor performance, suggesting that scenario mining presents unique challenges. Lastly, we discuss our recent CVPR 2025 competition and share insights from the community. Our code and dataset are available at https://github.com/CainanD/RefAV/ and https://argoverse.github.io/user-guide/tasks/scenario_mining.html

Open-vocabulary detectors achieve impressive performance on COCO, but often fail to generalize to real-world datasets with out-of-distribution classes not typically found in their pre-training. Rather than simply fine-tuning a heavy-weight vision-language model (VLM) for new domains, we introduce RF-DETR, a light-weight specialist detection transformer that discovers accuracy-latency Pareto curves for any target dataset with weight-sharing neural architecture search (NAS). Our approach fine-tunes a pre-trained base network on a target dataset and evaluates thousands of network configurations with different accuracy-latency tradeoffs without re-training. Further, we revisit the "tunable knobs" for NAS to improve the transferability of DETRs to diverse target domains. Notably, RF-DETR significantly improves on prior state-of-the-art real-time methods on COCO and Roboflow100-VL. RF-DETR (nano) achieves 48.0 AP on COCO, beating D-FINE (nano) by 5.3 AP at similar latency, and RF-DETR (2x-large) outperforms GroundingDINO (tiny) by 1.2 AP on Roboflow100-VL while running 20 times as fast. To the best of our knowledge, RF-DETR (2x-large) is the first real-time detector to surpass 60 AP on COCO.

Lung ultrasound (LUS) offers rapid, radiation-free bedside imaging, yet automated interpretation remains constrained by the opacity of end-to-end deep learning models. We propose a framework that explicitly aligns learned representations with human clinical reasoning by supervising models to predict interpretable visual biomarkers - clinician-recognized patterns such as A-lines, B-lines, and pleural irregularities - prior to diagnostic inference. This biomarker-aligned representation serves as a compact, semantically meaningful intermediate space for downstream tasks including lungseverity scoring, S/F ratio estimation, and disease classification. On a dataset of 189 patients (718 LUS videos), models trained via biomarker alignment outperform conventional task-specific networks while maintaining interpretability. A complementary user study demonstrates that decision tree explanations derived from biomarker features enhance clinicians' ability to identify incorrect model predictions compared to conventional saliency maps, underscoring the value of human-aligned representations in achieving both accuracy and transparency in diagnostic AI.

Vision-Language Action (VLAs) models promise to extend the remarkable success of vision-language models (VLMs) to robotics. Yet, unlike VLMs in the vision-language domain, VLAs for robotics require finetuning to contend with varying physical factors like robot embodiment, environment characteristics, and spatial relationships of each task. Existing fine-tuning methods lack specificity, adapting the same set of parameters regardless of a task's visual, linguistic, and physical characteristics. Inspired by functional specificity in neuroscience, we hypothesize that it is more effective to finetune sparse model representations specific to a given task. In this work, we introduce Robotic Steering, a finetuning approach grounded in mechanistic interpretability that leverages few-shot demonstrations to identify and selectively finetune task-specific attention heads aligned with the physical, visual, and linguistic requirements of robotic tasks. Through comprehensive on-robot evaluations with a Franka Emika robot arm, we demonstrate that Robotic Steering outperforms LoRA while achieving superior robustness under task variation, reduced computational cost, and enhanced interpretability for adapting VLAs to diverse robotic tasks.

Hospital readmission within 30 days of discharge is a leading driver of morbidity, mortality, and avoidable healthcare expenditure in congestive heart failure (CHF). Current clinical risk stratification tools rely primarily on non-imaging data and exhibit limited predictive performance. Point-of-care lung ultrasound (LUS) offers a sensitive, noninvasive window into the pulmonary congestion that characterizes CHF decompensation, yet its prognostic utility for readmission prediction remains largely unexplored. We present a pilot feasibility study, the first systematic machine learning study using B-mode LUS acquired during hospitalization to predict 30-day CHF readmission. Quantitative spatiotemporal embeddings are extracted from a pretrained Temporal Shift Module (TSM) ResNet-18 encoder, and interpretable biomarker features are separately evaluated. Through structured ablations over lung view, temporal representation, multi-view fusion, and cross-lung augmentation, we identify the key imaging factors driving readmission risk. Our findings reveal that (1) dependent lower-lung regions (Left-3, Right-3) carry the strongest prognostic signal, consistent with their greater susceptibility to hydrostatic congestion; (2) temporal difference features between sequential examinations substantially outperform single-timepoint representations, highlighting the importance of capturing disease trajectory; and (3) multi-view feature concatenation yields the best overall performance, with our top MLP model achieving an F1 score of 0.80 (95

Video–language models (VLMs) learn to reason about the dynamic visual world through natural language. We introduce a suite of open datasets, benchmarks, and recipes for scalable oversight that enable precise video captioning. First, we define a structured specification for describing subjects, scenes, motion, spatial, and camera dynamics, supported by hundreds of carefully defined visual primitives developed with professional video creators such as filmmakers. Next, to curate high-quality captions, we introduce a critique-based human–AI (CHAI) oversight framework, where trained human experts provide correctional critiques to revise model-generated pre-captions into improved post-captions. This division of labor improves annotation accuracy and efficiency by offloading text generation to models, allowing humans to better focus on verification. Additionally, these critiques and preferences between pre- and post-captions provide rich supervision for fine-tuning, improving open-source models (Qwen3-VL) on caption generation, reward modeling, and critique generation through standard SFT, offline RL (DPO), online RL (GSPO), and inference-time scaling. With modest expert supervision, the resulting system outperforms even closed-source models such as Gemini-2.5-Pro. Finally, we apply our approach to re-caption large-scale professional videos (e.g., films, commercials, games) and fine-tune video generation models such as Wan to better follow detailed prompts of over 400 words, achieving finer control over camera motion, angle, lens, perspectives, and shot composition. Overall, our results show that precise specification and human–AI oversight are key to achieving professional-level video understanding and generation.

Video-language models (VLMs) learn to reason about the dynamic visual world through natural language. We introduce a suite of open datasets, benchmarks, and recipes for scalable oversight that enable precise video captioning. First, we define a structured specification for describing subjects, scenes, motion, spatial, and camera dynamics, grounded by hundreds of carefully defined visual primitives developed with professional video creators such as filmmakers. Next, to curate high-quality captions, we introduce CHAI (Critique-based Human-AI Oversight), a framework where trained experts critique and revise model-generated pre-captions into improved post-captions. This division of labor improves annotation accuracy and efficiency by offloading text generation to models, allowing humans to better focus on verification. Additionally, these critiques and preferences between pre- and post-captions provide rich supervision for improving open-source models (Qwen3-VL) on caption generation, reward modeling, and critique generation through SFT, DPO, and inference-time scaling. Our ablations show that critique quality in precision, recall, and constructiveness, ensured by our oversight framework, directly governs downstream performance. With modest expert supervision, the resulting model outperforms closed-source models such as Gemini-3.1-Pro. Finally, we apply our approach to re-caption large-scale professional videos (e.g., films, commercials, games) and fine-tune video generation models such as Wan to better follow detailed prompts of up to 400 words, achieving finer control over cinematography including camera motion, angle, lens, focus, point of view, and framing. Our results show that precise specification and human-AI oversight are key to professional-level video understanding and generation. Data and code are available on our project page: https://linzhiqiu.github.io/papers/chai/

Physical AI aims to develop models that can perceive and predict real-world dynamics; yet, the extent to which current multi-modal large language models and video generative models support these abilities is insufficiently understood. We introduce Physical AI Bench (PAI-Bench), a unified and comprehensive benchmark that evaluates perception and prediction capabilities across video generation, conditional video generation, and video understanding, comprising 2,808 real-world cases with task-aligned metrics designed to capture physical plausibility and domain-specific reasoning. Our study provides a systematic assessment of recent models and shows that video generative models, despite strong visual fidelity, often struggle to maintain physically coherent dynamics, while multi-modal large language models exhibit limited performance in forecasting and causal interpretation. These observations suggest that current systems are still at an early stage in handling the perceptual and predictive demands of Physical AI. In summary, PAI-Bench establishes a realistic foundation for evaluating Physical AI and highlights key gaps that future systems must address.