Did you just see that? Arbitrary view synthesis for egocentric replay of operating room workflows from ambient sensors

Observing surgical practice has historically relied on fixed vantage points or recollections, leaving the egocentric visual perspectives that guide clinical decisions undocumented. Fixed-camera video can capture surgical workflows at the room-scale, but cannot reconstruct what each team member actually saw. Thus, these videos only provide limited insights into how decisions that affect surgical safety, training, and workflow optimization are made. Here we introduce EgoSurg, the first framework to reconstruct the dynamic, egocentric replays for any operating room (OR) staff directly from wall-mounted fixed-camera video, and thus, without intervention to clinical workflow. EgoSurg couples geometry-driven neural rendering with diffusion-based view enhancement, enabling high-visual fidelity synthesis of arbitrary and egocentric viewpoints at any moment. In evaluation across multi-site surgical cases and controlled studies, EgoSurg reconstructs person-specific visual fields and arbitrary viewpoints with high visual quality and fidelity. By transforming existing OR camera infrastructure into a navigable dynamic 3D record, EgoSurg establishes a new foundation for immersive surgical data science, enabling surgical practice to be visualized, experienced, and analyzed from every angle.

Kimi K2: Open Agentic Intelligence

We introduce Kimi K2, a Mixture-of-Experts (MoE) large language model with 32 billion activated parameters and 1 trillion total parameters. We propose the MuonClip optimizer, which improves upon Muon with a novel QK-clip technique to address training instability while enjoying the advanced token efficiency of Muon. Based on MuonClip, K2 was pre-trained on 15.5 trillion tokens with zero loss spike. During post-training, K2 undergoes a multi-stage post-training process, highlighted by a large-scale agentic data synthesis pipeline and a joint reinforcement learning (RL) stage, where the model improves its capabilities through interactions with real and synthetic environments. Kimi K2 achieves state-of-the-art performance among open-source non-thinking models, with strengths in agentic capabilities. Notably, K2 obtains 66.1 on Tau2-Bench, 76.5 on ACEBench (En), 65.8 on SWE-Bench Verified, and 47.3 on SWE-Bench Multilingual -- surpassing most open and closed-sourced baselines in non-thinking settings. It also exhibits strong capabilities in coding, mathematics, and reasoning tasks, with a score of 53.7 on LiveCodeBench v6, 49.5 on AIME 2025, 75.1 on GPQA-Diamond, and 27.1 on OJBench, all without extended thinking. These results position Kimi K2 as one of the most capable open-source large language models to date, particularly in software engineering and agentic tasks. We release our base and post-trained model checkpoints to facilitate future research and applications of agentic intelligence.

Position: Foundation Models Need Digital Twin Representations

Current foundation models (FMs) rely on token representations that directly fragment continuous real-world multimodal data into discrete tokens. They limit FMs to learning real-world knowledge and relationships purely through statistical correlation rather than leveraging explicit domain knowledge. Consequently, current FMs struggle with maintaining semantic coherence across modalities, capturing fine-grained spatial-temporal dynamics, and performing causal reasoning. These limitations cannot be overcome by simply scaling up model size or expanding datasets. This position paper argues that the machine learning community should consider digital twin (DT) representations, which are outcome-driven digital representations that serve as building blocks for creating virtual replicas of physical processes, as an alternative to the token representation for building FMs. Finally, we discuss how DT representations can address these challenges by providing physically grounded representations that explicitly encode domain knowledge and preserve the continuous nature of real-world processes.

DINOv2-powered Few-Shot Semantic Segmentation: A Unified Framework via Cross-Model Distillation and 4D Correlation Mining

Few-shot semantic segmentation has gained increasing interest due to its generalization capability, i.e., segmenting pixels of novel classes requiring only a few annotated images. Prior work has focused on meta-learning for support-query matching, with extensive development in both prototype-based and aggregation-based methods. To address data scarcity, recent approaches have turned to foundation models to enhance representation transferability for novel class segmentation. Among them, a hybrid dual-modal framework including both DINOv2 and SAM has garnered attention due to their complementary capabilities. We wonder "can we build a unified model with knowledge from both foundation models?" To this end, we propose FS-DINO, with only DINOv2's encoder and a lightweight segmenter. The segmenter features a bottleneck adapter, a meta-visual prompt generator based on dense similarities and semantic embeddings, and a decoder. Through coarse-to-fine cross-model distillation, we effectively integrate SAM's knowledge into our lightweight segmenter, which can be further enhanced by 4D correlation mining on support-query pairs. Extensive experiments on COCO-20i, PASCAL-5i, and FSS-1000 demonstrate the effectiveness and superiority of our method.

Kimi-VL Technical Report

We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities - all while activating only 2.8B parameters in its language decoder (Kimi-VL-A3B). Kimi-VL demonstrates strong performance across challenging domains: as a general-purpose VLM, Kimi-VL excels in multi-turn agent tasks (e.g., OSWorld), matching flagship models. Furthermore, it exhibits remarkable capabilities across diverse challenging vision language tasks, including college-level image and video comprehension, OCR, mathematical reasoning, and multi-image understanding. In comparative evaluations, it effectively competes with cutting-edge efficient VLMs such as GPT-4o-mini, Qwen2.5-VL-7B, and Gemma-3-12B-IT, while surpassing GPT-4o in several key domains. Kimi-VL also advances in processing long contexts and perceiving clearly. With a 128K extended context window, Kimi-VL can process diverse long inputs, achieving impressive scores of 64.5 on LongVideoBench and 35.1 on MMLongBench-Doc. Its native-resolution vision encoder, MoonViT, further allows it to see and understand ultra-high-resolution visual inputs, achieving 83.2 on InfoVQA and 34.5 on ScreenSpot-Pro, while maintaining lower computational cost for common tasks. Building upon Kimi-VL, we introduce an advanced long-thinking variant: Kimi-VL-Thinking. Developed through long chain-of-thought (CoT) supervised fine-tuning (SFT) and reinforcement learning (RL), this model exhibits strong long-horizon reasoning capabilities. It achieves scores of 61.7 on MMMU, 36.8 on MathVision, and 71.3 on MathVista while maintaining the compact 2.8B activated LLM parameters, setting a new standard for efficient multimodal thinking models. Code and models are publicly accessible at https://github.com/MoonshotAI/Kimi-VL.

Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video

Reconstructing 3D scenes from monocular surgical videos can enhance surgeon's perception and therefore plays a vital role in various computer-assisted surgery tasks. However, achieving scale-consistent reconstruction remains an open challenge due to inherent issues in endoscopic videos, such as dynamic deformations and textureless surfaces. Despite recent advances, current methods either rely on calibration or instrument priors to estimate scale, or employ SfM-like multi-stage pipelines, leading to error accumulation and requiring offline optimization. In this paper, we present Endo3R, a unified 3D foundation model for online scale-consistent reconstruction from monocular surgical video, without any priors or extra optimization. Our model unifies the tasks by predicting globally aligned pointmaps, scale-consistent video depths, and camera parameters without any offline optimization. The core contribution of our method is expanding the capability of the recent pairwise reconstruction model to long-term incremental dynamic reconstruction by an uncertainty-aware dual memory mechanism. The mechanism maintains history tokens of both short-term dynamics and long-term spatial consistency. Notably, to tackle the highly dynamic nature of surgical scenes, we measure the uncertainty of tokens via Sampson distance and filter out tokens with high uncertainty. Regarding the scarcity of endoscopic datasets with ground-truth depth and camera poses, we further devise a self-supervised mechanism with a novel dynamics-aware flow loss. Abundant experiments on SCARED and Hamlyn datasets demonstrate our superior performance in zero-shot surgical video depth prediction and camera pose estimation with online efficiency. Project page: https://wrld.github.io/Endo3R/.

dARt Vinci: Egocentric Data Collection for Surgical Robot Learning at Scale

Data scarcity has long been an issue in the robot learning community. Particularly, in safety-critical domains like surgical applications, obtaining high-quality data can be especially difficult. It poses challenges to researchers seeking to exploit recent advancements in reinforcement learning and imitation learning, which have greatly improved generalizability and enabled robots to conduct tasks autonomously. We introduce dARt Vinci, a scalable data collection platform for robot learning in surgical settings. The system uses Augmented Reality (AR) hand tracking and a high-fidelity physics engine to capture subtle maneuvers in primitive surgical tasks: By eliminating the need for a physical robot setup and providing flexibility in terms of time, space, and hardware resources-such as multiview sensors and actuators-specialized simulation is a viable alternative. At the same time, AR allows the robot data collection to be more egocentric, supported by its body tracking and content overlaying capabilities. Our user study confirms the proposed system's efficiency and usability, where we use widely-used primitive tasks for training teleoperation with da Vinci surgical robots. Data throughput improves across all tasks compared to real robot settings by 41% on average. The total experiment time is reduced by an average of 10%. The temporal demand in the task load survey is improved. These gains are statistically significant. Additionally, the collected data is over 400 times smaller in size, requiring far less storage while achieving double the frequency.

OPG-Policy: Occluded Push-Grasp Policy Learning with Amodal Segmentation

Goal-oriented grasping in dense clutter, a fundamental challenge in robotics, demands an adaptive policy to handle occluded target objects and diverse configurations. Previous methods typically learn policies based on partially observable segments of the occluded target to generate motions. However, these policies often struggle to generate optimal motions due to uncertainties regarding the invisible portions of different occluded target objects across various scenes, resulting in low motion efficiency. To this end, we propose OPG-Policy, a novel framework that leverages amodal segmentation to predict occluded portions of the target and develop an adaptive push-grasp policy for cluttered scenarios where the target object is partially observed. Specifically, our approach trains a dedicated amodal segmentation module for diverse target objects to generate amodal masks. These masks and scene observations are mapped to the future rewards of grasp and push motion primitives via deep Q-learning to learn the motion critic. Afterward, the push and grasp motion candidates predicted by the critic, along with the relevant domain knowledge, are fed into the coordinator to generate the optimal motion implemented by the robot. Extensive experiments conducted in both simulated and real-world environments demonstrate the effectiveness of our approach in generating motion sequences for retrieving occluded targets, outperforming other baseline methods in success rate and motion efficiency.

Neural Finite-State Machines for Surgical Phase Recognition

Surgical phase recognition is essential for analyzing procedure-specific surgical videos. While recent transformer-based architectures have advanced sequence processing capabilities, they struggle with maintaining consistency across lengthy surgical procedures. Drawing inspiration from classical hidden Markov models' finite-state interpretations, we introduce the neural finite-state machine (NFSM) module, which bridges procedural understanding with deep learning approaches. NFSM combines procedure-level understanding with neural networks through global state embeddings, attention-based dynamic transition tables, and transition-aware training and inference mechanisms for offline and online applications. When integrated into our future-aware architecture, NFSM improves video-level accuracy, phase-level precision, recall, and Jaccard indices on Cholec80 datasets by 2.3, 3.2, 3.0, and 4.8 percentage points respectively. As an add-on module to existing state-of-the-art models like Surgformer, NFSM further enhances performance, demonstrating its complementary value. Extended experiments on non-surgical datasets validate NFSM's generalizability beyond surgical domains. Comprehensive experiments demonstrate that incorporating NSFM into deep learning frameworks enables more robust and consistent phase recognition across long procedural videos.

Language-Model Prior Overcomes Cold-Start Items

The growth of recommender systems (RecSys) is driven by digitization and the need for personalized content in areas such as e-commerce and video streaming. The content in these systems often changes rapidly and therefore they constantly face the ongoing cold-start problem, where new items lack interaction data and are hard to value. Existing solutions for the cold-start problem, such as content-based recommenders and hybrid methods, leverage item metadata to determine item similarities. The main challenge with these methods is their reliance on structured and informative metadata to capture detailed item similarities, which may not always be available. This paper introduces a novel approach for cold-start item recommendation that utilizes the language model (LM) to estimate item similarities, which are further integrated as a Bayesian prior with classic recommender systems. This approach is generic and able to boost the performance of various recommenders. Specifically, our experiments integrate it with both sequential and collaborative filtering-based recommender and evaluate it on two real-world datasets, demonstrating the enhanced performance of the proposed approach.