MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrieval

We introduce MRMR, the first expert-level multidisciplinary multimodal retrieval benchmark requiring intensive reasoning. MRMR contains 1,502 queries spanning 23 domains, with positive documents carefully verified by human experts. Compared to prior benchmarks, MRMR introduces three key advancements. First, it challenges retrieval systems across diverse areas of expertise, enabling fine-grained model comparison across domains. Second, queries are reasoning-intensive, with images requiring deeper interpretation such as diagnosing microscopic slides. We further introduce Contradiction Retrieval, a novel task requiring models to identify conflicting concepts. Finally, queries and documents are constructed as image-text interleaved sequences. Unlike earlier benchmarks restricted to single images or unimodal documents, MRMR offers a realistic setting with multi-image queries and mixed-modality corpus documents. We conduct an extensive evaluation of 4 categories of multimodal retrieval systems and 14 frontier models on MRMR. The text embedding model Qwen3-Embedding with LLM-generated image captions achieves the highest performance, highlighting substantial room for improving multimodal retrieval models. Although latest multimodal models such as Ops-MM-Embedding perform competitively on expert-domain queries, they fall short on reasoning-intensive tasks. We believe that MRMR paves the way for advancing multimodal retrieval in more realistic and challenging scenarios.

SFD-Mamba2Net: Strcture-Guided Frequency-Enhanced Dual-Stream Mamba2 Network for Coronary Artery Segmentation

Background: Coronary Artery Disease (CAD) is one of the leading causes of death worldwide. Invasive Coronary Angiography (ICA), regarded as the gold standard for CAD diagnosis, necessitates precise vessel segmentation and stenosis detection. However, ICA images are typically characterized by low contrast, high noise levels, and complex, fine-grained vascular structures, which pose significant challenges to the clinical adoption of existing segmentation and detection methods. Objective: This study aims to improve the accuracy of coronary artery segmentation and stenosis detection in ICA images by integrating multi-scale structural priors, state-space-based long-range dependency modeling, and frequency-domain detail enhancement strategies. Methods: We propose SFD-Mamba2Net, an end-to-end framework tailored for ICA-based vascular segmentation and stenosis detection. In the encoder, a Curvature-Aware Structural Enhancement (CASE) module is embedded to leverage multi-scale responses for highlighting slender tubular vascular structures, suppressing background interference, and directing attention toward vascular regions. In the decoder, we introduce a Progressive High-Frequency Perception (PHFP) module that employs multi-level wavelet decomposition to progressively refine high-frequency details while integrating low-frequency global structures. Results and Conclusions: SFD-Mamba2Net consistently outperformed state-of-the-art methods across eight segmentation metrics, and achieved the highest true positive rate and positive predictive value in stenosis detection.

Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation

To enhance group robustness to spurious correlations, prior work often relies on auxiliary annotations for groups or spurious features and assumes identical sets of groups across source and target domains. These two requirements are both unnatural and impractical in real-world settings. To overcome these limitations, we propose a method that leverages the semantic structure inherent in class labels--specifically, superclass information--to naturally reduce reliance on spurious features. Our model employs gradient-based attention guided by a pre-trained vision-language model to disentangle superclass-relevant and irrelevant features. Then, by promoting the use of all superclass-relevant features for prediction, our approach achieves robustness to more complex spurious correlations without the need to annotate any source samples. Experiments across diverse datasets demonstrate that our method significantly outperforms baselines in domain generalization tasks, with clear improvements in both quantitative metrics and qualitative visualizations.

SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks

We present SciArena, an open and collaborative platform for evaluating foundation models on scientific literature tasks. Unlike traditional benchmarks for scientific literature understanding and synthesis, SciArena engages the research community directly, following the Chatbot Arena evaluation approach of community voting on model comparisons. By leveraging collective intelligence, SciArena offers a community-driven evaluation of model performance on open-ended scientific tasks that demand literature-grounded, long-form responses. The platform currently supports 23 open-source and proprietary foundation models and has collected over 13,000 votes from trusted researchers across diverse scientific domains. We analyze the data collected so far and confirm that the submitted questions are diverse, aligned with real-world literature needs, and that participating researchers demonstrate strong self-consistency and inter-annotator agreement in their evaluations. We discuss the results and insights based on the model ranking leaderboard. To further promote research in building model-based automated evaluation systems for literature tasks, we release SciArena-Eval, a meta-evaluation benchmark based on our collected preference data. The benchmark measures the accuracy of models in judging answer quality by comparing their pairwise assessments with human votes. Our experiments highlight the benchmark's challenges and emphasize the need for more reliable automated evaluation methods.

A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools

Foundation models (FMs) are catalyzing a transformative shift in materials science (MatSci) by enabling scalable, general-purpose, and multimodal AI systems for scientific discovery. Unlike traditional machine learning models, which are typically narrow in scope and require task-specific engineering, FMs offer cross-domain generalization and exhibit emergent capabilities. Their versatility is especially well-suited to materials science, where research challenges span diverse data types and scales. This survey provides a comprehensive overview of foundation models, agentic systems, datasets, and computational tools supporting this growing field. We introduce a task-driven taxonomy encompassing six broad application areas: data extraction, interpretation and Q\&A; atomistic simulation; property prediction; materials structure, design and discovery; process planning, discovery, and optimization; and multiscale modeling. We discuss recent advances in both unimodal and multimodal FMs, as well as emerging large language model (LLM) agents. Furthermore, we review standardized datasets, open-source tools, and autonomous experimental platforms that collectively fuel the development and integration of FMs into research workflows. We assess the early successes of foundation models and identify persistent limitations, including challenges in generalizability, interpretability, data imbalance, safety concerns, and limited multimodal fusion. Finally, we articulate future research directions centered on scalable pretraining, continual learning, data governance, and trustworthiness.

iDiT-HOI: Inpainting-based Hand Object Interaction Reenactment via Video Diffusion Transformer

Digital human video generation is gaining traction in fields like education and e-commerce, driven by advancements in head-body animation and lip-syncing technologies. However, realistic Hand-Object Interaction (HOI) - the complex dynamics between human hands and objects - continues to pose challenges. Generating natural and believable HOI reenactments is difficult due to issues such as occlusion between hands and objects, variations in object shapes and orientations, and the necessity for precise physical interactions, and importantly, the ability to generalize to unseen humans and objects. This paper presents a novel framework iDiT-HOI that enables in-the-wild HOI reenactment generation. Specifically, we propose a unified inpainting-based token process method, called Inp-TPU, with a two-stage video diffusion transformer (DiT) model. The first stage generates a key frame by inserting the designated object into the hand region, providing a reference for subsequent frames. The second stage ensures temporal coherence and fluidity in hand-object interactions. The key contribution of our method is to reuse the pretrained model's context perception capabilities without introducing additional parameters, enabling strong generalization to unseen objects and scenarios, and our proposed paradigm naturally supports long video generation. Comprehensive evaluations demonstrate that our approach outperforms existing methods, particularly in challenging real-world scenes, offering enhanced realism and more seamless hand-object interactions.

QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm

The attention operator remains a critical performance bottleneck in large language models (LLMs), particularly for long-context scenarios. While FlashAttention is the most widely used and effective GPU-aware acceleration algorithm, it must require time-consuming and hardware-specific manual implementation, limiting adaptability across GPU architectures. Existing LLMs have shown a lot of promise in code generation tasks, but struggle to generate high-performance attention code. The key challenge is it cannot comprehend the complex data flow and computation process of the attention operator and utilize low-level primitive to exploit GPU performance. To address the above challenge, we propose an LLM-friendly Thinking Language (LLM-TL) to help LLMs decouple the generation of high-level optimization logic and low-level implementation on GPU, and enhance LLMs' understanding of attention operator. Along with a 2-stage reasoning workflow, TL-Code generation and translation, the LLMs can automatically generate FlashAttention implementation on diverse GPUs, establishing a self-optimizing paradigm for generating high-performance attention operators in attention-centric algorithms. Verified on A100, RTX8000, and T4 GPUs, the performance of our methods significantly outshines that of vanilla LLMs, achieving a speed-up of up to 35.16x. Besides, our method not only surpasses human-optimized libraries (cuDNN and official library) in most scenarios but also extends support to unsupported hardware and data types, reducing development time from months to minutes compared with human experts.

FAD-Net: Frequency-Domain Attention-Guided Diffusion Network for Coronary Artery Segmentation using Invasive Coronary Angiography

Background: Coronary artery disease (CAD) remains one of the leading causes of mortality worldwide. Precise segmentation of coronary arteries from invasive coronary angiography (ICA) is critical for effective clinical decision-making. Objective: This study aims to propose a novel deep learning model based on frequency-domain analysis to enhance the accuracy of coronary artery segmentation and stenosis detection in ICA, thereby offering robust support for the stenosis detection and treatment of CAD. Methods: We propose the Frequency-Domain Attention-Guided Diffusion Network (FAD-Net), which integrates a frequency-domain-based attention mechanism and a cascading diffusion strategy to fully exploit frequency-domain information for improved segmentation accuracy. Specifically, FAD-Net employs a Multi-Level Self-Attention (MLSA) mechanism in the frequency domain, computing the similarity between queries and keys across high- and low-frequency components in ICAs. Furthermore, a Low-Frequency Diffusion Module (LFDM) is incorporated to decompose ICAs into low- and high-frequency components via multi-level wavelet transformation. Subsequently, it refines fine-grained arterial branches and edges by reintegrating high-frequency details via inverse fusion, enabling continuous enhancement of anatomical precision. Results and Conclusions: Extensive experiments demonstrate that FAD-Net achieves a mean Dice coefficient of 0.8717 in coronary artery segmentation, outperforming existing state-of-the-art methods. In addition, it attains a true positive rate of 0.6140 and a positive predictive value of 0.6398 in stenosis detection, underscoring its clinical applicability. These findings suggest that FAD-Net holds significant potential to assist in the accurate diagnosis and treatment planning of CAD.

Drive Any Mesh: 4D Latent Diffusion for Mesh Deformation from Video

We propose DriveAnyMesh, a method for driving mesh guided by monocular video. Current 4D generation techniques encounter challenges with modern rendering engines. Implicit methods have low rendering efficiency and are unfriendly to rasterization-based engines, while skeletal methods demand significant manual effort and lack cross-category generalization. Animating existing 3D assets, instead of creating 4D assets from scratch, demands a deep understanding of the input's 3D structure. To tackle these challenges, we present a 4D diffusion model that denoises sequences of latent sets, which are then decoded to produce mesh animations from point cloud trajectory sequences. These latent sets leverage a transformer-based variational autoencoder, simultaneously capturing 3D shape and motion information. By employing a spatiotemporal, transformer-based diffusion model, information is exchanged across multiple latent frames, enhancing the efficiency and generalization of the generated results. Our experimental results demonstrate that DriveAnyMesh can rapidly produce high-quality animations for complex motions and is compatible with modern rendering engines. This method holds potential for applications in both the gaming and filming industries.

SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing

Automatic fact-checking has recently received more attention as a means of combating misinformation. Despite significant advancements, fact-checking systems based on retrieval-augmented language models still struggle to tackle adversarial claims, which are intentionally designed by humans to challenge fact-checking systems. To address these challenges, we propose a training-free method designed to rephrase the original claim, making it easier to locate supporting evidence. Our modular framework, SUCEA, decomposes the task into three steps: 1) Claim Segmentation and Decontextualization that segments adversarial claims into independent sub-claims; 2) Iterative Evidence Retrieval and Claim Editing that iteratively retrieves evidence and edits the subclaim based on the retrieved evidence; 3) Evidence Aggregation and Label Prediction that aggregates all retrieved evidence and predicts the entailment label. Experiments on two challenging fact-checking datasets demonstrate that our framework significantly improves on both retrieval and entailment label accuracy, outperforming four strong claim-decomposition-based baselines.