Surgical Scene Segmentation using a Spike-Driven Video Transformer with Real-Time Potential

Modern surgical systems increasingly rely on intelligent scene understanding to provide timely situational awareness for enhanced intra-operative safety. Within this pipeline, surgical scene segmentation plays a central role in accurately perceiving operative events. Although recent deep learning models, particularly large-scale foundation models, achieve remarkable segmentation accuracy, their substantial computational demands and power consumption hinder real-time deployment in resource-constrained surgical environments. To address this limitation, we explore the emerging SNN as a promising paradigm for highly efficient surgical intelligence. However, their performance is still constrained by the scarcity of labeled surgical data and the inherently sparse nature of surgical video representations. To this end, we propose \textit{SpikeSurgSeg}, the first spike-driven video Transformer framework tailored for surgical scene segmentation with real-time potential on non-GPU platforms. To address the limited availability of surgical annotations, we introduce a surgical-scene masked autoencoding pretraining strategy for SNNs that enables robust spatiotemporal representation learning via layer-wise tube masking. Building on this pretrained backbone, we further adopt a lightweight spike-driven segmentation head that produces temporally consistent predictions while preserving the low-latency characteristics of SNNs. Extensive experiments on EndoVis18 and our in-house SurgBleed dataset demonstrate that SpikeSurgSeg achieves mIoU comparable to SOTA ANN-based models while reducing inference latency by at least $8\times$. Notably, it delivers over $20\times$ acceleration relative to most foundation-model baselines, underscoring its potential for time-critical surgical scene segmentation.

Step-DeepResearch Technical Report

As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands for open-ended research, which requires robust skills in intent recognition, long-horizon decision-making, and cross-source verification. To address this, we introduce Step-DeepResearch, a cost-effective, end-to-end agent. We propose a Data Synthesis Strategy Based on Atomic Capabilities to reinforce planning and report writing, combined with a progressive training path from agentic mid-training to SFT and RL. Enhanced by a Checklist-style Judger, this approach significantly improves robustness. Furthermore, to bridge the evaluation gap in the Chinese domain, we establish ADR-Bench for realistic deep research scenarios. Experimental results show that Step-DeepResearch (32B) scores 61.4% on Scale AI Research Rubrics. On ADR-Bench, it significantly outperforms comparable models and rivals SOTA closed-source models like OpenAI and Gemini DeepResearch. These findings prove that refined training enables medium-sized models to achieve expert-level capabilities at industry-leading cost-efficiency.

MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs

The advent of Multimodal Large Language Models (MLLMs) has expanded AI capabilities to visual modalities, yet existing evaluation benchmarks remain limited to single-video understanding, overlooking the critical need for multi-video understanding in real-world scenarios (e.g., sports analytics and autonomous driving). To address this significant gap, we introduce MVU-Eval, the first comprehensive benchmark for evaluating Multi-Video Understanding for MLLMs. Specifically, our MVU-Eval mainly assesses eight core competencies through 1,824 meticulously curated question-answer pairs spanning 4,959 videos from diverse domains, addressing both fundamental perception tasks and high-order reasoning tasks. These capabilities are rigorously aligned with real-world applications such as multi-sensor synthesis in autonomous systems and cross-angle sports analytics. Through extensive evaluation of state-of-the-art open-source and closed-source models, we reveal significant performance discrepancies and limitations in current MLLMs' ability to perform understanding across multiple videos. The benchmark will be made publicly available to foster future research.

Step-Audio 2 Technical Report

This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent audio encoder and reasoning-centric reinforcement learning (RL), Step-Audio 2 achieves promising performance in automatic speech recognition (ASR) and audio understanding. To facilitate genuine end-to-end speech conversation, Step-Audio 2 incorporates the generation of discrete audio tokens into language modeling, significantly enhancing its responsiveness to paralinguistic information such as speaking styles and emotions. To effectively leverage the rich textual and acoustic knowledge in real-world data, Step-Audio 2 integrates retrieval-augmented generation (RAG) and is able to call external tools such as web search to mitigate hallucination and audio search to switch timbres. Trained on millions of hours of speech and audio data, Step-Audio 2 delivers intelligence and expressiveness across diverse conversational scenarios. Evaluation results demonstrate that Step-Audio 2 achieves state-of-the-art performance on various audio understanding and conversational benchmarks compared to other open-source and commercial solutions. Please visit https://github.com/stepfun-ai/Step-Audio2 for more information.

What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities

As multimodal large language models (MLLMs) advance, MLLM-based virtual agents have demonstrated remarkable performance. However, existing benchmarks face significant limitations, including uncontrollable task complexity, extensive manual annotation with limited scenarios, and a lack of multidimensional evaluation. In response to these challenges, we introduce OmniBench, a self-generating, cross-platform, graph-based benchmark with an automated pipeline for synthesizing tasks of controllable complexity through subtask composition. To evaluate the diverse capabilities of virtual agents on the graph, we further present OmniEval, a multidimensional evaluation framework that includes subtask-level evaluation, graph-based metrics, and comprehensive tests across 10 capabilities. Our synthesized dataset contains 36k graph-structured tasks across 20 scenarios, achieving a 91\% human acceptance rate. Training on our graph-structured data shows that it can more efficiently guide agents compared to manually annotated data. We conduct multidimensional evaluations for various open-source and closed-source models, revealing their performance across various capabilities and paving the way for future advancements. Our project is available at https://omni-bench.github.io/.

SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity

Spiking Neural Networks (SNNs) have shown competitive performance to Artificial Neural Networks (ANNs) in various vision tasks, while offering superior energy efficiency. However, existing SNN-based Transformers primarily focus on single-image tasks, emphasizing spatial features while not effectively leveraging SNNs' efficiency in video-based vision tasks. In this paper, we introduce SpikeVideoFormer, an efficient spike-driven video Transformer, featuring linear temporal complexity $\mathcal{O}(T)$. Specifically, we design a spike-driven Hamming attention (SDHA) which provides a theoretically guided adaptation from traditional real-valued attention to spike-driven attention. Building on SDHA, we further analyze various spike-driven space-time attention designs and identify an optimal scheme that delivers appealing performance for video tasks, while maintaining only linear temporal complexity. The generalization ability and efficiency of our model are demonstrated across diverse downstream video tasks, including classification, human pose tracking, and semantic segmentation. Empirical results show our method achieves state-of-the-art (SOTA) performance compared to existing SNN approaches, with over 15\% improvement on the latter two tasks. Additionally, it matches the performance of recent ANN-based methods while offering significant efficiency gains, achieving $\times 16$, $\times 10$ and $\times 5$ improvements on the three tasks. https://github.com/JimmyZou/SpikeVideoFormer

DGFamba: Learning Flow Factorized State Space for Visual Domain Generalization

Domain generalization aims to learn a representation from the source domain, which can be generalized to arbitrary unseen target domains. A fundamental challenge for visual domain generalization is the domain gap caused by the dramatic style variation whereas the image content is stable. The realm of selective state space, exemplified by VMamba, demonstrates its global receptive field in representing the content. However, the way exploiting the domain-invariant property for selective state space is rarely explored. In this paper, we propose a novel Flow Factorized State Space model, dubbed as DG-Famba, for visual domain generalization. To maintain domain consistency, we innovatively map the style-augmented and the original state embeddings by flow factorization. In this latent flow space, each state embedding from a certain style is specified by a latent probability path. By aligning these probability paths in the latent space, the state embeddings are able to represent the same content distribution regardless of the style differences. Extensive experiments conducted on various visual domain generalization settings show its state-of-the-art performance.

Learning Fine-grained Domain Generalization via Hyperbolic State Space Hallucination

Fine-grained domain generalization (FGDG) aims to learn a fine-grained representation that can be well generalized to unseen target domains when only trained on the source domain data. Compared with generic domain generalization, FGDG is particularly challenging in that the fine-grained category can be only discerned by some subtle and tiny patterns. Such patterns are particularly fragile under the cross-domain style shifts caused by illumination, color and etc. To push this frontier, this paper presents a novel Hyperbolic State Space Hallucination (HSSH) method. It consists of two key components, namely, state space hallucination (SSH) and hyperbolic manifold consistency (HMC). SSH enriches the style diversity for the state embeddings by firstly extrapolating and then hallucinating the source images. Then, the pre- and post- style hallucinate state embeddings are projected into the hyperbolic manifold. The hyperbolic state space models the high-order statistics, and allows a better discernment of the fine-grained patterns. Finally, the hyperbolic distance is minimized, so that the impact of style variation on fine-grained patterns can be eliminated. Experiments on three FGDG benchmarks demonstrate its state-of-the-art performance.

DefMamba: Deformable Visual State Space Model

Recently, state space models (SSM), particularly Mamba, have attracted significant attention from scholars due to their ability to effectively balance computational efficiency and performance. However, most existing visual Mamba methods flatten images into 1D sequences using predefined scan orders, which results the model being less capable of utilizing the spatial structural information of the image during the feature extraction process. To address this issue, we proposed a novel visual foundation model called DefMamba. This model includes a multi-scale backbone structure and deformable mamba (DM) blocks, which dynamically adjust the scanning path to prioritize important information, thus enhancing the capture and processing of relevant input features. By combining a deformable scanning(DS) strategy, this model significantly improves its ability to learn image structures and detects changes in object details. Numerous experiments have shown that DefMamba achieves state-of-the-art performance in various visual tasks, including image classification, object detection, instance segmentation, and semantic segmentation. The code is open source on DefMamba.

Anatomically and Metabolically Informed Diffusion for Unified Denoising and Segmentation in Low-Count PET Imaging

Positron emission tomography (PET) image denoising, along with lesion and organ segmentation, are critical steps in PET-aided diagnosis. However, existing methods typically treat these tasks independently, overlooking inherent synergies between them as correlated steps in the analysis pipeline. In this work, we present the anatomically and metabolically informed diffusion (AMDiff) model, a unified framework for denoising and lesion/organ segmentation in low-count PET imaging. By integrating multi-task functionality and exploiting the mutual benefits of these tasks, AMDiff enables direct quantification of clinical metrics, such as total lesion glycolysis (TLG), from low-count inputs. The AMDiff model incorporates a semantic-informed denoiser based on diffusion strategy and a denoising-informed segmenter utilizing nnMamba architecture. The segmenter constrains denoised outputs via a lesion-organ-specific regularizer, while the denoiser enhances the segmenter by providing enriched image information through a denoising revision module. These components are connected via a warming-up mechanism to optimize multitask interactions. Experiments on multi-vendor, multi-center, and multi-noise-level datasets demonstrate the superior performance of AMDiff. For test cases below 20% of the clinical count levels from participating sites, AMDiff achieves TLG quantification biases of -26.98%, outperforming its ablated versions which yield biases of -35.85% (without the lesion-organ-specific regularizer) and -40.79% (without the denoising revision module).