More than Segmentation: Benchmarking SAM 3 for Segmentation, 3D Perception, and Reconstruction in Robotic Surgery

The recent SAM 3 and SAM 3D have introduced significant advancements over the predecessor, SAM 2, particularly with the integration of language-based segmentation and enhanced 3D perception capabilities. SAM 3 supports zero-shot segmentation across a wide range of prompts, including point, bounding box, and language-based prompts, allowing for more flexible and intuitive interactions with the model. In this empirical evaluation, we assess the performance of SAM 3 in robot-assisted surgery, benchmarking its zero-shot segmentation with point and bounding box prompts and exploring its effectiveness in dynamic video tracking, alongside its newly introduced language prompt segmentation. While language prompts show potential, their performance in the surgical domain is currently suboptimal, highlighting the need for further domain-specific training. Additionally, we investigate SAM 3D's depth reconstruction abilities, demonstrating its capacity to process surgical scene data and reconstruct 3D anatomical structures from 2D images. Through comprehensive testing on the MICCAI EndoVis 2017 and EndoVis 2018 benchmarks, SAM 3 shows clear improvements over SAM and SAM 2 in both image and video segmentation under spatial prompts, while the zero-shot evaluations of SAM 3D on SCARED, StereoMIS, and EndoNeRF indicate strong monocular depth estimation and realistic 3D instrument reconstruction, yet also reveal remaining limitations in complex, highly dynamic surgical scenes.

AdaTok: Adaptive Token Compression with Object-Aware Representations for Efficient Multimodal LLMs

Multimodal Large Language Models (MLLMs) have demonstrated substantial value in unified text-image understanding and reasoning, primarily by converting images into sequences of patch-level tokens that align with their architectural paradigm. However, patch-level tokenization leads to a quadratic growth in image tokens, burdening MLLMs' understanding and reasoning with enormous computation and memory. Additionally, the traditional patch-wise scanning tokenization workflow misaligns with the human vision cognition system, further leading to hallucination and computational redundancy. To address this issue, we propose an object-level token merging strategy for Adaptive Token compression, revealing the consistency with human vision system. The experiments are conducted on multiple comprehensive benchmarks, which show that our approach averagely, utilizes only 10% tokens while achieving almost 96% of the vanilla model's performance. More extensive experimental results in comparison with relevant works demonstrate the superiority of our method in balancing compression ratio and performance. Our code will be available.

MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models

Full-Duplex Speech Language Models (FD-SLMs) enable real-time, overlapping conversational interactions, offering a more dynamic user experience compared to traditional half-duplex models. However, existing benchmarks primarily focus on evaluating single-round interactions and conversational features, neglecting the complexities of multi-round communication and critical capabilities such as instruction following and safety. Evaluating FD-SLMs in multi-round settings poses significant challenges, including blurred turn boundaries in communication and context inconsistency during model inference. To address these gaps, we introduce MTR-DuplexBench, a novel benchmark that segments continuous full-duplex dialogues into discrete turns, enabling comprehensive, turn-by-turn evaluation of FD-SLMs across dialogue quality, conversational dynamics, instruction following, and safety. Experimental results reveal that current FD-SLMs face difficulties in maintaining consistent performance across multiple rounds and evaluation dimensions, highlighting the necessity and effectiveness of our proposed benchmark. The benchmark and code will be available in the future.

K-Stain: Keypoint-Driven Correspondence for H&E-to-IHC Virtual Staining

Virtual staining offers a promising method for converting Hematoxylin and Eosin (H&E) images into Immunohistochemical (IHC) images, eliminating the need for costly chemical processes. However, existing methods often struggle to utilize spatial information effectively due to misalignment in tissue slices. To overcome this challenge, we leverage keypoints as robust indicators of spatial correspondence, enabling more precise alignment and integration of structural details in synthesized IHC images. We introduce K-Stain, a novel framework that employs keypoint-based spatial and semantic relationships to enhance synthesized IHC image fidelity. K-Stain comprises three main components: (1) a Hierarchical Spatial Keypoint Detector (HSKD) for identifying keypoints in stain images, (2) a Keypoint-aware Enhancement Generator (KEG) that integrates these keypoints during image generation, and (3) a Keypoint Guided Discriminator (KGD) that improves the discriminator's sensitivity to spatial details. Our approach leverages contextual information from adjacent slices, resulting in more accurate and visually consistent IHC images. Extensive experiments show that K-Stain outperforms state-of-the-art methods in quantitative metrics and visual quality.

LucidFlux: Caption-Free Universal Image Restoration via a Large-Scale Diffusion Transformer

Universal image restoration (UIR) aims to recover images degraded by unknown mixtures while preserving semantics -- conditions under which discriminative restorers and UNet-based diffusion priors often oversmooth, hallucinate, or drift. We present LucidFlux, a caption-free UIR framework that adapts a large diffusion transformer (Flux.1) without image captions. LucidFlux introduces a lightweight dual-branch conditioner that injects signals from the degraded input and a lightly restored proxy to respectively anchor geometry and suppress artifacts. Then, a timestep- and layer-adaptive modulation schedule is designed to route these cues across the backbone's hierarchy, in order to yield coarse-to-fine and context-aware updates that protect the global structure while recovering texture. After that, to avoid the latency and instability of text prompts or MLLM captions, we enforce caption-free semantic alignment via SigLIP features extracted from the proxy. A scalable curation pipeline further filters large-scale data for structure-rich supervision. Across synthetic and in-the-wild benchmarks, LucidFlux consistently outperforms strong open-source and commercial baselines, and ablation studies verify the necessity of each component. LucidFlux shows that, for large DiTs, when, where, and what to condition on -- rather than adding parameters or relying on text prompts -- is the governing lever for robust and caption-free universal image restoration in the wild.

Toward Medical Deepfake Detection: A Comprehensive Dataset and Novel Method

The rapid advancement of generative AI in medical imaging has introduced both significant opportunities and serious challenges, especially the risk that fake medical images could undermine healthcare systems. These synthetic images pose serious risks, such as diagnostic deception, financial fraud, and misinformation. However, research on medical forensics to counter these threats remains limited, and there is a critical lack of comprehensive datasets specifically tailored for this field. Additionally, existing media forensic methods, which are primarily designed for natural or facial images, are inadequate for capturing the distinct characteristics and subtle artifacts of AI-generated medical images. To tackle these challenges, we introduce \textbf{MedForensics}, a large-scale medical forensics dataset encompassing six medical modalities and twelve state-of-the-art medical generative models. We also propose \textbf{DSKI}, a novel \textbf{D}ual-\textbf{S}tage \textbf{K}nowledge \textbf{I}nfusing detector that constructs a vision-language feature space tailored for the detection of AI-generated medical images. DSKI comprises two core components: 1) a cross-domain fine-trace adapter (CDFA) for extracting subtle forgery clues from both spatial and noise domains during training, and 2) a medical forensic retrieval module (MFRM) that boosts detection accuracy through few-shot retrieval during testing. Experimental results demonstrate that DSKI significantly outperforms both existing methods and human experts, achieving superior accuracy across multiple medical modalities.

HybridMamba: A Dual-domain Mamba for 3D Medical Image Segmentation

In the domain of 3D biomedical image segmentation, Mamba exhibits the superior performance for it addresses the limitations in modeling long-range dependencies inherent to CNNs and mitigates the abundant computational overhead associated with Transformer-based frameworks when processing high-resolution medical volumes. However, attaching undue importance to global context modeling may inadvertently compromise critical local structural information, thus leading to boundary ambiguity and regional distortion in segmentation outputs. Therefore, we propose the HybridMamba, an architecture employing dual complementary mechanisms: 1) a feature scanning strategy that progressively integrates representations both axial-traversal and local-adaptive pathways to harmonize the relationship between local and global representations, and 2) a gated module combining spatial-frequency analysis for comprehensive contextual modeling. Besides, we collect a multi-center CT dataset related to lung cancer. Experiments on MRI and CT datasets demonstrate that HybridMamba significantly outperforms the state-of-the-art methods in 3D medical image segmentation.

Think Before You Talk: Enhancing Meaningful Dialogue Generation in Full-Duplex Speech Language Models with Planning-Inspired Text Guidance

Full-Duplex Speech Language Models (FD-SLMs) are specialized foundation models designed to enable natural, real-time spoken interactions by modeling complex conversational dynamics such as interruptions, backchannels, and overlapping speech, and End-to-end (e2e) FD-SLMs leverage real-world double-channel conversational data to capture nuanced two-speaker dialogue patterns for human-like interactions. However, they face a critical challenge -- their conversational abilities often degrade compared to pure-text conversation due to prolonged speech sequences and limited high-quality spoken dialogue data. While text-guided speech generation could mitigate these issues, it suffers from timing and length issues when integrating textual guidance into double-channel audio streams, disrupting the precise time alignment essential for natural interactions. To address these challenges, we propose TurnGuide, a novel planning-inspired approach that mimics human conversational planning by dynamically segmenting assistant speech into dialogue turns and generating turn-level text guidance before speech output, which effectively resolves both insertion timing and length challenges. Extensive experiments demonstrate our approach significantly improves e2e FD-SLMs' conversational abilities, enabling them to generate semantically meaningful and coherent speech while maintaining natural conversational flow. Demos are available at https://dreamtheater123.github.io/TurnGuide-Demo/. Code will be available at https://github.com/dreamtheater123/TurnGuide.

EventRR: Event Referential Reasoning for Referring Video Object Segmentation

Referring Video Object Segmentation (RVOS) aims to segment out the object in a video referred by an expression. Current RVOS methods view referring expressions as unstructured sequences, neglecting their crucial semantic structure essential for referent reasoning. Besides, in contrast to image-referring expressions whose semantics focus only on object attributes and object-object relations, video-referring expressions also encompass event attributes and event-event temporal relations. This complexity challenges traditional structured reasoning image approaches. In this paper, we propose the Event Referential Reasoning (EventRR) framework. EventRR decouples RVOS into object summarization part and referent reasoning part. The summarization phase begins by summarizing each frame into a set of bottleneck tokens, which are then efficiently aggregated in the video-level summarization step to exchange the global cross-modal temporal context. For reasoning part, EventRR extracts semantic eventful structure of a video-referring expression into highly expressive Referential Event Graph (REG), which is a single-rooted directed acyclic graph. Guided by topological traversal of REG, we propose Temporal Concept-Role Reasoning (TCRR) to accumulate the referring score of each temporal query from REG leaf nodes to root node. Each reasoning step can be interpreted as a question-answer pair derived from the concept-role relations in REG. Extensive experiments across four widely recognized benchmark datasets, show that EventRR quantitatively and qualitatively outperforms state-of-the-art RVOS methods. Code is available at https://github.com/bio-mlhui/EventRR

S2-UniSeg: Fast Universal Agglomerative Pooling for Scalable Segment Anything without Supervision

Recent self-supervised image segmentation models have achieved promising performance on semantic segmentation and class-agnostic instance segmentation. However, their pretraining schedule is multi-stage, requiring a time-consuming pseudo-masks generation process between each training epoch. This time-consuming offline process not only makes it difficult to scale with training dataset size, but also leads to sub-optimal solutions due to its discontinuous optimization routine. To solve these, we first present a novel pseudo-mask algorithm, Fast Universal Agglomerative Pooling (UniAP). Each layer of UniAP can identify groups of similar nodes in parallel, allowing to generate both semantic-level and instance-level and multi-granular pseudo-masks within ens of milliseconds for one image. Based on the fast UniAP, we propose the Scalable Self-Supervised Universal Segmentation (S2-UniSeg), which employs a student and a momentum teacher for continuous pretraining. A novel segmentation-oriented pretext task, Query-wise Self-Distillation (QuerySD), is proposed to pretrain S2-UniSeg to learn the local-to-global correspondences. Under the same setting, S2-UniSeg outperforms the SOTA UnSAM model, achieving notable improvements of AP+6.9 on COCO, AR+11.1 on UVO, PixelAcc+4.5 on COCOStuff-27, RQ+8.0 on Cityscapes. After scaling up to a larger 2M-image subset of SA-1B, S2-UniSeg further achieves performance gains on all four benchmarks. Our code and pretrained models are available at https://github.com/bio-mlhui/S2-UniSeg