让下一篇重要论文，不再错过。

High-fidelity surgical video generation holds great promise for medical training and AI development, yet precise, controllable editing of such videos remains a formidable challenge. Modifying surgical attributes such as instrument, tissue interactions or procedural phases is particularly difficult due to the strict anatomical and temporal constraints of ophthalmic procedures. We introduce OphEdit, the first training-free framework for text-guided editing of ophthalmic surgical videos. Our approach uses a deterministic second-order ODE inversion pipeline to capture attention Value tensors from the source video and selectively injects them into the conditional branch of classifier-free guidance during denoising, preserving the intricate anatomical geometry of the eye while mapping text-driven semantic modifications onto the video. Clinical evaluation by an ophthalmologist shows that OphEdit handles complex transformations, such as instrument swaps and procedural variations, with superior structural fidelity and temporal consistency compared to adapted general-domain video editors, offering a scalable route to diverse surgical training data. The code and prompts can be accessed at https://github.com/ophedit/OphEdit

A real photograph is often blurry, grainy, compressed, scratched, and low-resolution at the same time. Each defect has its own severity and its own place in the image. The corrections for these defects conflict with each other. Exist- ing models describe the whole image with one description, so they cannot say where each correction belongs. To solve this problem, we present Wonder 4, a mixture-of-experts (MoE) model for image quality enhancement. It corrects several defects of a real photograph at the same time, each in the region where it occurs. Every block of the model holds a mixture of N = 13 experts. A router, trained with the model, sends every image patch to k = 5 of them. No degradation classifier, mask, prompt, detector, or task label is used. Another issue is that standard MoE training, taken from language models, pushes every expert toward equal use. Equal use applies every correction everywhere, even where it is not needed. We replace this rule with a bias that only sets a minimum share of use. Across all patches, an expert used less than this minimum gets higher router scores until it is selected again. An expert above the minimum is not changed, so no expert is forced to be used as often as the others. The bias needs no extra loss. The method adds no extra module and no extra processing step. We evaluate Wonder 4 on DIV2K and Flickr2K, against five published methods and three open-weight pipelines. It reaches the best LPIPS, DISTS, and NIQE on all three test settings (DIV2K x4, DIV2K x8, and Flickr2K x4).

3D point cloud classification, a task in computer vision, has recently gained substantial interest due to its extensive applications across various domains such as augmented and virtual reality, robotics, and autonomous driving. However, classifying 3D point clouds becomes challenging in real-world scenarios where the density levels vary. These variations are due to limitations inherent to current sensing technologies and variable environmental conditions, which often prevent the capture of detailed and comprehensive geometric representations. Existing classification methods, which have demonstrated impressive results on dense point clouds, may be affected and could experience reduced performance when dealing with low-density point clouds. Addressing this challenge, this paper introduces LD-PointNet++, an architecture optimized for the classification of low-density point clouds. To pave the way for LD-PointNet++, we conduct the first benchmarking study that systematically evaluates state-of-the-art point cloud classification methods across varying densities, revealing significant performance declines in low-density environments. Experimental results on the ModelNet benchmark dataset demonstrate that LD-PointNet++ not only outperforms these methods in low-density scenarios but also demonstrates consistent accuracy above 90% across different density levels.

Visual place recognition (VPR) localises a camera by retrieving similar geo-tagged images, and current foundation-model VPR models are accurate across cities, seasons and illumination, but not robust to adversarial perturbations: under a white-box attack on the ranking at an imperceptible budget of 1/255, SuperVLAD and BoQ keep at most 0.2% top-1 recall (R@1) on four benchmarks. We propose anchored rank-adversarial fine-tuning (ARAFT), which fine-tunes a released model with a listwise rank loss on each adversarial query's hardest positive and an anchor to the clean descriptor of the frozen pretrained model. Checkpoints are selected under a clean-accuracy budget fixed in advance, and the full trade-off is reported. Within five validation R@1 points of clean cost, plain adversarial training has no admissible checkpoint, whereas ARAFT raises robust R@1 from zero to 47.3 on SuperVLAD and 55.3 on BoQ; plain adversarial training exceeds this only at about three times the clean cost. Against unbudgeted plain adversarial training on the test sets, ARAFT matches its robust R@1 at 2/255 with about ten more clean R@1 points. At 4/255, plain adversarial training is 6-9 robust R@1 points ahead, while ARAFT still keeps its ten-point clean advantage. Developed on SuperVLAD, ARAFT transfers to BoQ without re-tuning, and its robustness holds against stronger optimisers, with no sign of gradient masking.

Unified Multimodal Models (UMMs) integrate visual understanding, generation, and editing within a single unified framework. However, existing unified multimodal datasets and benchmarks remain dominated by single-turn tasks. Even in recent multi-turn datasets, many turns can be solved independently without tracking information across turns. Consequently, they provide limited supervision and evaluation for multimodal stateful interaction, which requires models to understand, maintain, update, and faithfully realize evolving dialogue states across turns. To address this gap, we introduce YANAMI, the first large-scale multimodal dialogue dataset and benchmark for stateful interaction, comprising YANAMI-400K and YANAMI-Bench. YANAMI-400K contains 400K multi-turn multimodal dialogues, with more than 2M images and 2.6M dialogue turns. The dialogues span four representative scenarios: Multi-Image Fusion, Image Editing, World Modeling, and Visual Reasoning, and require models to continuously track, preserve, and revise evolving multimodal dialogue states across turns. YANAMI-Bench comprises 400 multi-turn dialogues for systematically evaluating multimodal stateful interaction. It jointly evaluates Dialogue State Understanding and Visual Realization, characterizing the gap between models' ability to understand evolving dialogue states and their ability to faithfully realize them in visual outputs. Experiments show that fine-tuning BAGEL on YANAMI-400K improves image editing, generation, and multimodal stateful interaction by 10.3%, 2.0%, and 13.23%, respectively, while preserving its general visual understanding capabilities. Evaluations on YANAMI-Bench further reveal that existing UMMs still struggle to maintain, update, and visually realize evolving multimodal dialogue states.

We aim to build a truly unified motion model that can understand, generate, and edit human motion within a single framework. Existing motion UMMs remain only partially unified: motion understanding is handled by a language model, while generation is often delegated to a separate diffusion module operating over learned motion latents. We introduce Möbius, which brings the entire diffusion process into the same multimodal representation space used for motion understanding. Clean motion, noisy motion, and text jointly participate in shared attention, while role-specific parameters process understanding and generation streams. Importantly, Möbius operates directly on continuous frame-level raw motion, requiring neither discrete tokenization nor a pretrained motion VAE. This simple formulation naturally supports motion captioning, text-to-motion generation, temporal completion, and instruction-guided editing within a single model. On HumanML3D, Möbius achieves state-of-the-art performance among unified motion models. Scaling to 1.7B parameters and 1,700 hours of motion data further demonstrates that our framework is both effective and scalable.

Artificial general intelligence (AGI) requires a method that can understand, generate, reason, and act across diverse domains and modalities. Rather than relying on a single model to master every capability, a promising path toward AGI now is to orchestrate a heterogeneous ecosystem of specialized models, tools, and policies (candidates) into a unified AI system. At the heart of this vision lies a fundamental question: how can an AI system dynamically select and coordinate the most capable candidate for each task while balancing performance and computational cost? In this work, we present Route Anything, a unified framework for studying model and policy routing across general-purpose AI systems. We develop a unified theoretical foundation that characterizes optimal routing under quality--cost trade-offs and establishes how the information available to a router determines its attainable performance. To systematically investigate routing across diverse capabilities, we first construct an omni-modal trajectory matrix spanning 25 benchmarks across language understanding, image, video, and speech generation, coding and workplace agents, and robotic manipulation, comprising 374,401 scored runs from 452 candidate configurations. Building on this framework, we train and test different routers to investigate the potential of omni-modal model routing, the capabilities of learned routers, and the conditions under which routing improves efficiency. Our results reveal substantial opportunities for capability orchestration: per-input oracle routing outperforms the best fixed candidate by 5.4 points, and learned routers outperform it by 0.3 points across 16 benchmarks, by 2.1 points on video generation, and by 1.1 points on robot manipulation while using 24% less policy time. More importantly, routing raises efficiency by 8.82x on average compared with the reference model.

Controlling the motion of multiple objects in image-to-video (I2V) generation requires preserving object identities while enforcing adherence to distinct target trajectories. This becomes particularly challenging as the number of objects increases and their paths intersect or occlude one another. Existing approaches entangle multiple trajectories within a shared, dense conditioning signal, making object-level correspondence difficult to preserve in crowded scenes. We depart from this paradigm and enforce a strict, per object spatial constraint that isolates instances independently. Our method, TrajLoc, achieves this directly within the attention layers by substituting the cross-attention weights of each object token with a Gaussian heatmap centered on its target location at every frame. The same per object token interface carries trajectory and depth through a learned embedding and preserves identity by encoding first frame appearance in place of an object token. Evaluations across six datasets, featuring up to 20 simultaneously controlled objects and out of distribution real world scenes, demonstrate that our method consistently improves both visual fidelity and trajectory adherence. Applied to two architecturally distinct backbones (CogVideoX 5B and WaN 2.1 14B), our approach achieves average gains of +4.3 dB PSNR and a 51% reduction in trajectory end point error compared to the strongest baselines. Project page: https://sela-omer.github.io/traj-loc/

The goal of Sign Language Production (SLP) is to translate natural language text into corresponding sign language movements performed by a virtual avatar. The quality of the generated motion is typically evaluated by a motion-space Frechet distance (FID) and back-translation BLEU score on benchmarks such as How2Sign. The existing approaches can improve both metrics substantially while the underlying generator fails to represent the input sentence, a failure we call conditional collapse. In this work we propose to evaluate the generated motion at three independent levels: (tau1) initial-pose conditioning, (tau2) output diversity, and (tau3) target faithfulness. We compute these as pairwise-distance ratios using latent representations of a frozen motion autoencoder (MoAE), judged against each dataset's own GT-vs-GT reference. We evaluate diffusion and regression SLP models on How2Sign, including a re-implemented Neural Sign Actors, and show that tau3 faithfulness is never attained, while FID varies by nearly two orders of magnitude and is uncorrelated with faithfulness. We then apply the same models and diagnostic to Phoenix-2014T, CSL-Daily, and gloss-level ASL3DWord and show that faithfulness varies proportionally to how densely the training sentences cover the test conditions (conditioning coverage) and not corpus size. The smaller but densely covered Phoenix-2014T and ASL3DWord datasets generate faithful sign motion, while CSL-Daily follows the input text yet falls short of sign language faithfulness. Using the largest, open-domain How2Sign dataset, the models collapse at every scale. We introduce two measurements of the text data that rank the corpora in the order of how densely the training sentences fill the embedding space, and how close each test sentence lies to its nearest training sentence.

Deep models for radiological diagnosis are typically trained to predict disease labels directly from images, which limits them to diseases seen during training and makes their decisions hard to interpret in radiologists' terms. Radiology, however, proceeds from visual findings to disease through published guidelines that make this decision rule explicit, interpretable, and reproducible. We introduce diagnosis by composition (DbC), a representation learning framework that encodes this findings-first logic. DbC learns a vocabulary of radiological findings by aligning image features with the text embeddings of the findings, each finding represented as a dense map over the scan. A disease is defined by a set of required findings derived from its guidelines, and its diagnosis map is a fixed, parameter-free composition of the corresponding finding maps. Because the finding-to-disease mapping is derived from guidelines rather than learned, DbC is interpretable and auditable by design, can extend to new diseases by specifying their findings without retraining, and can diagnose unseen diseases by composing their findings. On multi-phase liver CT, DbC detects and localizes unseen diseases, rare diseases from a different institution, and an external cohort significantly better than all comparators, including models that align images with disease names. DbC also improves detection and localization in the fully supervised setting and remains superior across training-set sizes. Although demonstrated on liver CT, DbC applies wherever radiological guidelines define diseases through findings.

We introduce PLANTEUR, a benchmark for crop-type mapping from satellite images in the French overseas territories. Building on the PASTIS design, PLANTEUR provides georeferenced and aligned Sentinel-2, Sentinel-1, and Landsat-8 sequences with parcel-derived labels spanning six tropical regions and an 8-class label space. We define both a standard test split and a leave-one-island-out protocol to measure cross-territory generalization, and evaluate fully supervised models, linear probes, and fine-tuned foundation models. The benchmark code and data are open source and available on GitHub and Hugging Face.

Sign language processing advances rapidly for high-resource languages such as American Sign Language (ASL), yet most of the world's sign languages lack the phonological annotations new methods require. We present the first zero-shot cross-lingual framework for handshape recognition, transferring from ASL to Catalan Sign Language (LSC). Our approach leverages the decomposition of handshapes into five phonological features -- selected fingers, flexion, spread, thumb position, and thumb contact -- shared across both languages, to decode LSC handshapes from predicted features via a composite phonological distance metric. We evaluate three architectures (MLP, SL-GCN, SHuBERT) trained on two ASL corpora (PopSign, Sem-Lex) against a 37-handshape, single-signer LSC benchmark. Zero-shot transfer proves viable once recording-format disparities are harmonized, reaching 80.0% phonological feature accuracy and 54.5% expected handshape accuracy. Phonological decomposition thus offers a bridge for extending sign language technologies to low-resource languages without any target-language video training labels.

Automatic Target Recognition (ATR) in Synthetic Aperture Sonar (SAS) is often underpinned by deep neural networks (DNNs). Recent research has focused on relatively low-capacity DNNs (i.e., relatively fewer trainable parameters) to avoid overfitting on the small training datasets that are typically available for SAS. However, recent research has found that increasing DNN capacity often improves performance, even when training data is scarce. Motivated by this emerging finding - termed the double descent phenomenon - this work investigates the use of especially high-capacity DNNs for SAS-ATR. We evaluate the performance of several state-of-the-art DNN architectures as we increase their model capacity. We examine performance in a realistic leave-one-geo-location-out cross-validation scheme. We find that increasing model capacity often increases performance substantially, and is never harmful. All of our large models significantly outperform two baseline models from recent publications. Training high-capacity models on small dataset however requires careful regularization, and we also perform systematic experiments showing the impact of several regularization strategies: pretraining on other imaging modalities, data augmentation (including some new to SAS), DropPath, and weight decay. We show that each of these strategies independently improves the performance of the large models.

Intraductal papillary mucinous neoplasms (IPMNs) are pancreatic cancer precursors, and guideline-based risk stratification both over-treats indolent lesions and misses progression. We present Cyst-X, a public benchmark of 1,461 T1-weighted (T1W) and T2-weighted (T2W) MRI volumes from 764 patients at seven centers, with expert pancreas masks, risk labels, splits and reference AI risk-prediction models. PanSegNet segmented the pancreas with Dice of 86.34% (T1W) and 89.26% (T2W) on held-out centers. For the primary task, high-risk versus low-risk IPMN, a 3D DenseNet-121 achieved cross-validated AUCs of 74.59% and 73.45%; complementary broad binary and three-class tasks reached 78.67--81.28% and 73.47--75.76%. Because patient images often cannot be pooled across institutions, we also simulated federated learning across the seven centers. On T2W MRI, FedProx was similar to centralized training in center-averaged external AUC (71.00% versus 71.18%) but not in pooled AUC (62.35% versus 77.49%). Radiologist comparisons showed cohort-dependent sensitivity--specificity tradeoffs. Cyst-X supports reproducible method development and identifies within-IPMN risk discrimination and cross-center score comparability as open challenges.