Sufficiently modeling the correlations among variables (aka channels) is crucial for achieving accurate multivariate time series forecasting (MTSF). In this paper, we propose a novel technique called Temporal Query (TQ) to more effectively capture multivariate correlations, thereby improving model performance in MTSF tasks. Technically, the TQ technique employs periodically shifted learnable vectors as queries in the attention mechanism to capture global inter-variable patterns, while the keys and values are derived from the raw input data to encode local, sample-level correlations. Building upon the TQ technique, we develop a simple yet efficient model named Temporal Query Network (TQNet), which employs only a single-layer attention mechanism and a lightweight multi-layer perceptron (MLP). Extensive experiments demonstrate that TQNet learns more robust multivariate correlations, achieving state-of-the-art forecasting accuracy across 12 challenging real-world datasets. Furthermore, TQNet achieves high efficiency comparable to linear-based methods even on high-dimensional datasets, balancing performance and computational cost. The code is available at: https://github.com/ACAT-SCUT/TQNet.
Despite recent advances in text-to-image generation, using synthetically generated data seldom brings a significant boost in performance for supervised learning. Oftentimes, synthetic datasets do not faithfully recreate the data distribution of real data, i.e., they lack the fidelity or diversity needed for effective downstream model training. While previous work has employed few-shot guidance to address this issue, existing methods still fail to capture and generate features unique to specific real images. In this paper, we introduce a novel dataset generation framework named LoFT, LoRA-Fused Training-data Generation with Few-shot Guidance. Our method fine-tunes LoRA weights on individual real images and fuses them at inference time, producing synthetic images that combine the features of real images for improved diversity and fidelity of generated data. We evaluate the synthetic data produced by LoFT on 10 datasets, using 8 to 64 real images per class as guidance and scaling up to 1000 images per class. Our experiments show that training on LoFT-generated data consistently outperforms other synthetic dataset methods, significantly increasing accuracy as the dataset size increases. Additionally, our analysis demonstrates that LoFT generates datasets with high fidelity and sufficient diversity, which contribute to the performance improvement. The code is available at https://github.com/ExplainableML/LoFT.
The efficiency of attention is important due to its quadratic time complexity. We enhance the efficiency of attention through two key contributions: First, we leverage the new FP4 Tensor Cores in Blackwell GPUs to accelerate attention computation. Our implementation achieves 1038 TOPS on RTX5090, which is a 5x speedup over the fastest FlashAttention on RTX5090. Experiments show that our FP4 attention can accelerate inference of various models in a plug-and-play way. Second, we pioneer low-bit attention to training tasks. Existing low-bit attention works like FlashAttention3 and SageAttention focus only on inference. However, the efficiency of training large models is also important. To explore whether low-bit attention can be effectively applied to training tasks, we design an accurate and efficient 8-bit attention for both forward and backward propagation. Experiments indicate that 8-bit attention achieves lossless performance in fine-tuning tasks but exhibits slower convergence in pretraining tasks. The code will be available at https://github.com/thu-ml/SageAttention.
Global tree species mapping using remote sensing data is vital for biodiversity monitoring, forest management, and ecological research. However, progress in this field has been constrained by the scarcity of large-scale, labeled datasets. To address this, we introduce GlobalGeoTree, a comprehensive global dataset for tree species classification. GlobalGeoTree comprises 6.3 million geolocated tree occurrences, spanning 275 families, 2,734 genera, and 21,001 species across the hierarchical taxonomic levels. Each sample is paired with Sentinel-2 image time series and 27 auxiliary environmental variables, encompassing bioclimatic, geographic, and soil data. The dataset is partitioned into GlobalGeoTree-6M for model pretraining and curated evaluation subsets, primarily GlobalGeoTree-10kEval for zero-shot and few-shot benchmarking. To demonstrate the utility of the dataset, we introduce a baseline model, GeoTreeCLIP, which leverages paired remote sensing data and taxonomic text labels within a vision-language framework pretrained on GlobalGeoTree-6M. Experimental results show that GeoTreeCLIP achieves substantial improvements in zero- and few-shot classification on GlobalGeoTree-10kEval over existing advanced models. By making the dataset, models, and code publicly available, we aim to establish a benchmark to advance tree species classification and foster innovation in biodiversity research and ecological applications.
Recent advances in text-video retrieval have been largely driven by contrastive learning frameworks. However, existing methods overlook a key source of optimization tension: the separation between text and video distributions in the representation space (referred to as the modality gap), and the prevalence of false negatives in batch sampling. These factors lead to conflicting gradients under the InfoNCE loss, impeding stable alignment. To mitigate this, we propose GARE, a Gap-Aware Retrieval framework that introduces a learnable, pair-specific increment Delta_ij between text t_i and video v_j to offload the tension from the global anchor representation. We first derive the ideal form of Delta_ij via a coupled multivariate first-order Taylor approximation of the InfoNCE loss under a trust-region constraint, revealing it as a mechanism for resolving gradient conflicts by guiding updates along a locally optimal descent direction. Due to the high cost of directly computing Delta_ij, we introduce a lightweight neural module conditioned on the semantic gap between each video-text pair, enabling structure-aware correction guided by gradient supervision. To further stabilize learning and promote interpretability, we regularize Delta using three components: a trust-region constraint to prevent oscillation, a directional diversity term to promote semantic coverage, and an information bottleneck to limit redundancy. Experiments across four retrieval benchmarks show that GARE consistently improves alignment accuracy and robustness to noisy supervision, confirming the effectiveness of gap-aware tension mitigation.
Few-shot classification of hyperspectral images (HSI) faces the challenge of scarce labeled samples. Self-Supervised learning (SSL) and Few-Shot Learning (FSL) offer promising avenues to address this issue. However, existing methods often struggle to adapt to the spatial geometric diversity of HSIs and lack sufficient spectral prior knowledge. To tackle these challenges, we propose a method, Spectral-Spatial Self-Supervised Learning for Few-Shot Hyperspectral Image Classification (S4L-FSC), aimed at improving the performance of few-shot HSI classification. Specifically, we first leverage heterogeneous datasets to pretrain a spatial feature extractor using a designed Rotation-Mirror Self-Supervised Learning (RM-SSL) method, combined with FSL. This approach enables the model to learn the spatial geometric diversity of HSIs using rotation and mirroring labels as supervisory signals, while acquiring transferable spatial meta-knowledge through few-shot learning. Subsequently, homogeneous datasets are utilized to pretrain a spectral feature extractor via a combination of FSL and Masked Reconstruction Self-Supervised Learning (MR-SSL). The model learns to reconstruct original spectral information from randomly masked spectral vectors, inferring spectral dependencies. In parallel, FSL guides the model to extract pixel-level discriminative features, thereby embedding rich spectral priors into the model. This spectral-spatial pretraining method, along with the integration of knowledge from heterogeneous and homogeneous sources, significantly enhances model performance. Extensive experiments on four HSI datasets demonstrate the effectiveness and superiority of the proposed S4L-FSC approach for few-shot HSI classification.
Reinforcement fine-tuning (RFT) has shown great promise in achieving humanlevel reasoning capabilities of Large Language Models (LLMs), and has recently been extended to MLLMs. Nevertheless, reasoning about videos, which is a fundamental aspect of human intelligence, remains a persistent challenge due to the complex logic, temporal and causal structures inherent in video data. To fill this gap, we propose VIDEORFT, a novel approach that extends the RFT paradigm to cultivate human-like video reasoning capabilities in MLLMs. VIDEORFT follows the standard two-stage scheme in RFT: supervised fine-tuning (SFT) with chain-of-thought (CoT) annotations, followed by reinforcement learning (RL) to improve generalization. A central challenge to achieve this in the video domain lies in the scarcity of large-scale, high-quality video CoT datasets. We address this by building a fully automatic CoT curation pipeline. First, we devise a cognitioninspired prompting strategy to elicit a reasoning LLM to generate preliminary CoTs based solely on rich, structured, and literal representations of video content. Subsequently, these CoTs are revised by a visual-language model conditioned on the actual video, ensuring visual consistency and reducing visual hallucinations. This pipeline results in two new datasets - VideoRFT-CoT-102K for SFT and VideoRFT-RL-310K for RL. To further strength the RL phase, we introduce a novel semantic-consistency reward that explicitly promotes the alignment between textual reasoning with visual evidence. This reward encourages the model to produce coherent, context-aware reasoning outputs grounded in visual input. Extensive experiments show that VIDEORFT achieves state-of-the-art performance on six video reasoning benchmarks.
Drag-based editing within pretrained diffusion model provides a precise and flexible way to manipulate foreground objects. Traditional methods optimize the input feature obtained from DDIM inversion directly, adjusting them iteratively to guide handle points towards target locations. However, these approaches often suffer from limited accuracy due to the low representation ability of the feature in motion supervision, as well as inefficiencies caused by the large search space required for point tracking. To address these limitations, we present DragLoRA, a novel framework that integrates LoRA (Low-Rank Adaptation) adapters into the drag-based editing pipeline. To enhance the training of LoRA adapters, we introduce an additional denoising score distillation loss which regularizes the online model by aligning its output with that of the original model. Additionally, we improve the consistency of motion supervision by adapting the input features using the updated LoRA, giving a more stable and accurate input feature for subsequent operations. Building on this, we design an adaptive optimization scheme that dynamically toggles between two modes, prioritizing efficiency without compromising precision. Extensive experiments demonstrate that DragLoRA significantly enhances the control precision and computational efficiency for drag-based image editing. The Codes of DragLoRA are available at: https://github.com/Sylvie-X/DragLoRA.
We present \textit{kornia-rs}, a high-performance 3D computer vision library written entirely in native Rust, designed for safety-critical and real-time applications. Unlike C++-based libraries like OpenCV or wrapper-based solutions like OpenCV-Rust, \textit{kornia-rs} is built from the ground up to leverage Rust's ownership model and type system for memory and thread safety. \textit{kornia-rs} adopts a statically-typed tensor system and a modular set of crates, providing efficient image I/O, image processing and 3D operations. To aid cross-platform compatibility, \textit{kornia-rs} offers Python bindings, enabling seamless and efficient integration with Rust code. Empirical results show that \textit{kornia-rs} achieves a 3~ 5 times speedup in image transformation tasks over native Rust alternatives, while offering comparable performance to C++ wrapper-based libraries. In addition to 2D vision capabilities, \textit{kornia-rs} addresses a significant gap in the Rust ecosystem by providing a set of 3D computer vision operators. This paper presents the architecture and performance characteristics of \textit{kornia-rs}, demonstrating its effectiveness in real-world computer vision applications.
The rapid advancement of generative models, such as GANs and Diffusion models, has enabled the creation of highly realistic synthetic images, raising serious concerns about misinformation, deepfakes, and copyright infringement. Although numerous Artificial Intelligence Generated Image (AIGI) detectors have been proposed, often reporting high accuracy, their effectiveness in real-world scenarios remains questionable. To bridge this gap, we introduce AIGIBench, a comprehensive benchmark designed to rigorously evaluate the robustness and generalization capabilities of state-of-the-art AIGI detectors. AIGIBench simulates real-world challenges through four core tasks: multi-source generalization, robustness to image degradation, sensitivity to data augmentation, and impact of test-time pre-processing. It includes 23 diverse fake image subsets that span both advanced and widely adopted image generation techniques, along with real-world samples collected from social media and AI art platforms. Extensive experiments on 11 advanced detectors demonstrate that, despite their high reported accuracy in controlled settings, these detectors suffer significant performance drops on real-world data, limited benefits from common augmentations, and nuanced effects of pre-processing, highlighting the need for more robust detection strategies. By providing a unified and realistic evaluation framework, AIGIBench offers valuable insights to guide future research toward dependable and generalizable AIGI detection.
Recent advances in Large Multimodal Models (LMMs) have significantly improved their reasoning and Optical Character Recognition (OCR) capabilities. However, their performance on complex logical reasoning tasks involving text-rich images remains underexplored. To bridge this gap, we introduce LogicOCR, a benchmark comprising 1,100 multiple-choice questions designed to evaluate LMMs' logical reasoning abilities on text-rich images, while minimizing reliance on domain-specific knowledge (e.g., mathematics). We construct LogicOCR by curating a text corpus from the Chinese National Civil Servant Examination and develop a scalable, automated pipeline to convert it into multimodal samples. First, we design prompt templates to steer GPT-Image-1 to generate images with diverse backgrounds, interleaved text-illustration layouts, and varied fonts, ensuring contextual relevance and visual realism. Then, the generated images are manually verified, with low-quality examples discarded. We evaluate a range of representative open-source and proprietary LMMs under both Chain-of-Thought (CoT) and direct-answer settings. Our multi-dimensional analysis reveals key insights, such as the impact of test-time scaling, input modality differences, and sensitivity to visual-text orientation. Notably, LMMs still lag in multimodal reasoning compared to text-only inputs, indicating that they have not fully bridged visual reading with reasoning. We hope LogicOCR will serve as a valuable resource for advancing multimodal reasoning research. The dataset is available at https://github.com/MiliLab/LogicOCR.
The proliferation of diverse remote sensing data has spurred advancements in dense prediction tasks, yet significant challenges remain in handling data heterogeneity. Remote sensing imagery exhibits substantial variability across temporal, spectral, and spatial (TSS) dimensions, complicating unified data processing. Current deep learning models for dense prediction tasks, such as semantic segmentation and change detection, are typically tailored to specific input-output configurations. Consequently, variations in data dimensionality or task requirements often lead to significant performance degradation or model incompatibility, necessitating costly retraining or fine-tuning efforts for different application scenarios. This paper introduces the Temporal-Spectral-Spatial Unified Network (TSSUN), a novel architecture designed for unified representation and modeling of remote sensing data across diverse TSS characteristics and task types. TSSUN employs a Temporal-Spectral-Spatial Unified Strategy that leverages meta-information to decouple and standardize input representations from varied temporal, spectral, and spatial configurations, and similarly unifies output structures for different dense prediction tasks and class numbers. Furthermore, a Local-Global Window Attention mechanism is proposed to efficiently capture both local contextual details and global dependencies, enhancing the model's adaptability and feature extraction capabilities. Extensive experiments on multiple datasets demonstrate that a single TSSUN model effectively adapts to heterogeneous inputs and unifies various dense prediction tasks. The proposed approach consistently achieves or surpasses state-of-the-art performance, highlighting its robustness and generalizability for complex remote sensing applications without requiring task-specific modifications.
Multi-frame video enhancement tasks aim to improve the spatial and temporal resolution and quality of video sequences by leveraging temporal information from multiple frames, which are widely used in streaming video processing, surveillance, and generation. Although numerous Transformer-based enhancement methods have achieved impressive performance, their computational and memory demands hinder deployment on edge devices. Quantization offers a practical solution by reducing the bit-width of weights and activations to improve efficiency. However, directly applying existing quantization methods to video enhancement tasks often leads to significant performance degradation and loss of fine details. This stems from two limitations: (a) inability to allocate varying representational capacity across frames, which results in suboptimal dynamic range adaptation; (b) over-reliance on full-precision teachers, which limits the learning of low-bit student models. To tackle these challenges, we propose a novel quantization method for video enhancement: Progressive Multi-Frame Quantization for Video Enhancement (PMQ-VE). This framework features a coarse-to-fine two-stage process: Backtracking-based Multi-Frame Quantization (BMFQ) and Progressive Multi-Teacher Distillation (PMTD). BMFQ utilizes a percentile-based initialization and iterative search with pruning and backtracking for robust clipping bounds. PMTD employs a progressive distillation strategy with both full-precision and multiple high-bit (INT) teachers to enhance low-bit models' capacity and quality. Extensive experiments demonstrate that our method outperforms existing approaches, achieving state-of-the-art performance across multiple tasks and benchmarks.The code will be made publicly available at: https://github.com/xiaoBIGfeng/PMQ-VE.
Prostate cancer is one of the most common and lethal cancers among men, making its early detection critically important. Although ultrasound imaging offers greater accessibility and cost-effectiveness compared to MRI, traditional transrectal ultrasound methods suffer from low sensitivity, especially in detecting anteriorly located tumors. Ultrasound computed tomography provides quantitative tissue characterization, but its clinical implementation faces significant challenges, particularly under anatomically constrained limited-angle acquisition conditions specific to prostate imaging. To address these unmet needs, we introduce OpenPros, the first large-scale benchmark dataset explicitly developed for limited-view prostate USCT. Our dataset includes over 280,000 paired samples of realistic 2D speed-of-sound (SOS) phantoms and corresponding ultrasound full-waveform data, generated from anatomically accurate 3D digital prostate models derived from real clinical MRI/CT scans and ex vivo ultrasound measurements, annotated by medical experts. Simulations are conducted under clinically realistic configurations using advanced finite-difference time-domain and Runge-Kutta acoustic wave solvers, both provided as open-source components. Through comprehensive baseline experiments, we demonstrate that state-of-the-art deep learning methods surpass traditional physics-based approaches in both inference efficiency and reconstruction accuracy. Nevertheless, current deep learning models still fall short of delivering clinically acceptable high-resolution images with sufficient accuracy. By publicly releasing OpenPros, we aim to encourage the development of advanced machine learning algorithms capable of bridging this performance gap and producing clinically usable, high-resolution, and highly accurate prostate ultrasound images. The dataset is publicly accessible at https://open-pros.github.io/.
We introduce HyperCap, the first large-scale hyperspectral captioning dataset designed to enhance model performance and effectiveness in remote sensing applications. Unlike traditional hyperspectral imaging (HSI) datasets that focus solely on classification tasks, HyperCap integrates spectral data with pixel-wise textual annotations, enabling deeper semantic understanding of hyperspectral imagery. This dataset enhances model performance in tasks like classification and feature extraction, providing a valuable resource for advanced remote sensing applications. HyperCap is constructed from four benchmark datasets and annotated through a hybrid approach combining automated and manual methods to ensure accuracy and consistency. Empirical evaluations using state-of-the-art encoders and diverse fusion techniques demonstrate significant improvements in classification performance. These results underscore the potential of vision-language learning in HSI and position HyperCap as a foundational dataset for future research in the field.
Recent advancements in Digital Pathology (DP), particularly through artificial intelligence and Foundation Models, have underscored the importance of large-scale, diverse, and richly annotated datasets. Despite their critical role, publicly available Whole Slide Image (WSI) datasets often lack sufficient scale, tissue diversity, and comprehensive clinical metadata, limiting the robustness and generalizability of AI models. In response, we introduce the HISTAI dataset, a large, multimodal, open-access WSI collection comprising over 60,000 slides from various tissue types. Each case in the HISTAI dataset is accompanied by extensive clinical metadata, including diagnosis, demographic information, detailed pathological annotations, and standardized diagnostic coding. The dataset aims to fill gaps identified in existing resources, promoting innovation, reproducibility, and the development of clinically relevant computational pathology solutions. The dataset can be accessed at https://github.com/HistAI/HISTAI.
Recent advancements in large multimodal models (LMMs) have driven substantial progress in both text-to-video (T2V) generation and video-to-text (V2T) interpretation tasks. However, current AI-generated videos (AIGVs) still exhibit limitations in terms of perceptual quality and text-video alignment. Therefore, a reliable and scalable automatic model for AIGV evaluation is desirable, which heavily relies on the scale and quality of human annotations. To this end, we present AIGVE-60K, a comprehensive dataset and benchmark for AI-Generated Video Evaluation, which features (i) comprehensive tasks, encompassing 3,050 extensive prompts across 20 fine-grained task dimensions, (ii) the largest human annotations, including 120K mean-opinion scores (MOSs) and 60K question-answering (QA) pairs annotated on 58,500 videos generated from 30 T2V models, and (iii) bidirectional benchmarking and evaluating for both T2V generation and V2T interpretation capabilities. Based on AIGVE-60K, we propose LOVE, a LMM-based metric for AIGV Evaluation from multiple dimensions including perceptual preference, text-video correspondence, and task-specific accuracy in terms of both instance level and model level. Comprehensive experiments demonstrate that LOVE not only achieves state-of-the-art performance on the AIGVE-60K dataset, but also generalizes effectively to a wide range of other AIGV evaluation benchmarks. These findings highlight the significance of the AIGVE-60K dataset. Database and codes are anonymously available at https://github.com/IntMeGroup/LOVE.
Very high-resolution (VHR) satellite imagery has emerged as a powerful tool for monitoring marine animals on a large scale. However, existing deep learning-based whale detection methods usually require manually created, high-quality bounding box annotations, which are labor-intensive to produce. Moreover, existing studies often exclude ``uncertain whales'', individuals that have ambiguous appearances in satellite imagery, limiting the applicability of these models in real-world scenarios. To address these limitations, this study introduces an automated pipeline for detecting beluga whales and harp seals in VHR satellite imagery. The pipeline leverages point annotations and the Segment Anything Model (SAM) to generate precise bounding box annotations, which are used to train YOLOv8 for multiclass detection of certain whales, uncertain whales, and harp seals. Experimental results demonstrated that SAM-generated annotations significantly improved detection performance, achieving higher $\text{F}_\text{1}$-scores compared to traditional buffer-based annotations. YOLOv8 trained on SAM-labeled boxes achieved an overall $\text{F}_\text{1}$-score of 72.2% for whales overall and 70.3% for harp seals, with superior performance in dense scenes. The proposed approach not only reduces the manual effort required for annotation but also enhances the detection of uncertain whales, offering a more comprehensive solution for marine animal monitoring. This method holds great potential for extending to other species, habitats, and remote sensing platforms, as well as for estimating whale biometrics, thereby advancing ecological monitoring and conservation efforts. The codes for our label and detection pipeline are publicly available at http://github.com/voyagerxvoyagerx/beluga-seeker .
Task arithmetic enables efficient model editing by representing task-specific changes as vectors in parameter space. Task arithmetic typically assumes that the source and target models are initialized from the same pre-trained parameters. This assumption limits its applicability in cross-model transfer settings, where models are independently pre-trained on different datasets. To address this challenge, we propose a method based on few-shot orthogonal alignment, which aligns task vectors to the parameter space of a differently pre-trained target model. These transformations preserve key properties of task vectors, such as norm and rank, and are learned using only a small number of labeled examples. We evaluate the method using two Vision Transformers pre-trained on YFCC100M and LAION400M, and test on eight classification datasets. Experimental results show that our method improves transfer accuracy over direct task vector application and achieves performance comparable to few-shot fine-tuning, while maintaining the modularity and reusability of task vectors. Our code is available at https://github.com/kawakera-lab/CrossModelTransfer.
In this paper, we proposed a Multi-modal Collaborative Optimization and Expansion Network (MCO-E Net), to use event modalities to resist challenges such as low light, high exposure, and high dynamic range in single-eye expression recognition tasks. The MCO-E Net introduces two innovative designs: Multi-modal Collaborative Optimization Mamba (MCO-Mamba) and Heterogeneous Collaborative and Expansion Mixture-of-Experts (HCE-MoE). MCO-Mamba, building upon Mamba, leverages dual-modal information to jointly optimize the model, facilitating collaborative interaction and fusion of modal semantics. This approach encourages the model to balance the learning of both modalities and harness their respective strengths. HCE-MoE, on the other hand, employs a dynamic routing mechanism to distribute structurally varied experts (deep, attention, and focal), fostering collaborative learning of complementary semantics. This heterogeneous architecture systematically integrates diverse feature extraction paradigms to comprehensively capture expression semantics. Extensive experiments demonstrate that our proposed network achieves competitive performance in the task of single-eye expression recognition, especially under poor lighting conditions.