3D Deep-learning-based Segmentation of Human Skin Sweat Glands and Their 3D Morphological Response to Temperature Variations

Skin, the primary regulator of heat exchange, relies on sweat glands for thermoregulation. Alterations in sweat gland morphology play a crucial role in various pathological conditions and clinical diagnoses. Current methods for observing sweat gland morphology are limited by their two-dimensional, in vitro, and destructive nature, underscoring the urgent need for real-time, non-invasive, quantifiable technologies. We proposed a novel three-dimensional (3D) transformer-based multi-object segmentation framework, integrating a sliding window approach, joint spatial-channel attention mechanism, and architectural heterogeneity between shallow and deep layers. Our proposed network enables precise 3D sweat gland segmentation from skin volume data captured by optical coherence tomography (OCT). For the first time, subtle variations of sweat gland 3D morphology in response to temperature changes, have been visualized and quantified. Our approach establishes a benchmark for normal sweat gland morphology and provides a real-time, non-invasive tool for quantifying 3D structural parameters. This enables the study of individual variability and pathological changes in sweat gland structure, advancing dermatological research and clinical applications, including thermoregulation and bromhidrosis treatment.

Generalized Neighborhood Attention: Multi-dimensional Sparse Attention at the Speed of Light

Many sparse attention mechanisms such as Neighborhood Attention have typically failed to consistently deliver speedup over the self attention baseline. This is largely due to the level of complexity in attention infrastructure, and the rapid evolution of AI hardware architecture. At the same time, many state-of-the-art foundational models, particularly in computer vision, are heavily bound by attention, and need reliable sparsity to escape the O(n^2) complexity. In this paper, we study a class of promising sparse attention mechanisms that focus on locality, and aim to develop a better analytical model of their performance improvements. We first introduce Generalized Neighborhood Attention (GNA), which can describe sliding window, strided sliding window, and blocked attention. We then consider possible design choices in implementing these approaches, and create a simulator that can provide much more realistic speedup upper bounds for any given setting. Finally, we implement GNA on top of a state-of-the-art fused multi-headed attention (FMHA) kernel designed for the NVIDIA Blackwell architecture in CUTLASS. Our implementation can fully realize the maximum speedup theoretically possible in many perfectly block-sparse cases, and achieves an effective utilization of 1.3 petaFLOPs/second in FP16. In addition, we plug various GNA configurations into off-the-shelf generative models, such as Cosmos-7B, HunyuanVideo, and FLUX, and show that it can deliver 28% to 46% end-to-end speedup on B200 without any fine-tuning. We will open source our simulator and Blackwell kernels directly through the NATTEN project.

Efficient Pretraining Length Scaling

Recent advances in large language models have demonstrated the effectiveness of length scaling during post-training, yet its potential in pre-training remains underexplored. We present the Parallel Hidden Decoding Transformer (\textit{PHD}-Transformer), a novel framework that enables efficient length scaling during pre-training while maintaining inference efficiency. \textit{PHD}-Transformer achieves this through an innovative KV cache management strategy that distinguishes between original tokens and hidden decoding tokens. By retaining only the KV cache of original tokens for long-range dependencies while immediately discarding hidden decoding tokens after use, our approach maintains the same KV cache size as the vanilla transformer while enabling effective length scaling. To further enhance performance, we introduce two optimized variants: \textit{PHD-SWA} employs sliding window attention to preserve local dependencies, while \textit{PHD-CSWA} implements chunk-wise sliding window attention to eliminate linear growth in pre-filling time. Extensive experiments demonstrate consistent improvements across multiple benchmarks.

CacheFormer: High Attention-Based Segment Caching

Efficiently handling long contexts in transformer-based language models with low perplexity is an active area of research. Numerous recent approaches like Linformer, Longformer, Performer, and Structured state space models (SSMs)., have not fully resolved this problem. All these models strive to reduce the quadratic time complexity of the attention mechanism while minimizing the loss in quality due to the effective compression of the long context. Inspired by the cache and virtual memory principle in computers, where in case of a cache miss, not only the needed data is retrieved from the memory, but the adjacent data is also obtained, we apply this concept to handling long contexts by dividing it into small segments. In our design, we retrieve the nearby segments in an uncompressed form when high segment-level attention occurs at the compressed level. Our en-hancements for handling long context include aggregating four attention mechanisms consisting of short sliding window attention, long compressed segmented attention, dynamically retrieving top k high attention uncompressed segments, and overlapping segments in long segment attention to avoid segment fragmentation. These enhancements result in an architecture that outperforms ex-isting SOTA architectures with an average perplexity improvement of 8.5% over similar model sizes.

SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling

We present a decoder-only Transformer architecture that robustly generalizes to sequence lengths substantially longer than those seen during training. Our model, SWAN-GPT, interleaves layers without positional encodings (NoPE) and sliding-window attention layers equipped with rotary positional encodings (SWA-RoPE). Experiments demonstrate strong performance on sequence lengths significantly longer than the training length without the need for additional long-context training. This robust length extrapolation is achieved through our novel architecture, enhanced by a straightforward dynamic scaling of attention scores during inference. In addition, SWAN-GPT is more computationally efficient than standard GPT architectures, resulting in cheaper training and higher throughput. Further, we demonstrate that existing pre-trained decoder-only models can be efficiently converted to the SWAN architecture with minimal continued training, enabling longer contexts. Overall, our work presents an effective approach for scaling language models to longer contexts in a robust and efficient manner.

End-to-End Facial Expression Detection in Long Videos

Facial expression detection involves two interrelated tasks: spotting, which identifies the onset and offset of expressions, and recognition, which classifies them into emotional categories. Most existing methods treat these tasks separately using a two-step training pipelines. A spotting model first detects expression intervals. A recognition model then classifies the detected segments. However, this sequential approach leads to error propagation, inefficient feature learning, and suboptimal performance due to the lack of joint optimization of the two tasks. We propose FEDN, an end-to-end Facial Expression Detection Network that jointly optimizes spotting and recognition. Our model introduces a novel attention-based feature extraction module, incorporating segment attention and sliding window attention to improve facial feature learning. By unifying two tasks within a single network, we greatly reduce error propagation and enhance overall performance. Experiments on CASME}^2 and CASME^3 demonstrate state-of-the-art accuracy for both spotting and detection, underscoring the benefits of joint optimization for robust facial expression detection in long videos.

MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer

Generative masked transformers have demonstrated remarkable success across various content generation tasks, primarily due to their ability to effectively model large-scale dataset distributions with high consistency. However, in the animation domain, large datasets are not always available. Applying generative masked modeling to generate diverse instances from a single MoCap reference may lead to overfitting, a challenge that remains unexplored. In this work, we present MotionDreamer, a localized masked modeling paradigm designed to learn internal motion patterns from a given motion with arbitrary topology and duration. By embedding the given motion into quantized tokens with a novel distribution regularization method, MotionDreamer constructs a robust and informative codebook for local motion patterns. Moreover, a sliding window local attention is introduced in our masked transformer, enabling the generation of natural yet diverse animations that closely resemble the reference motion patterns. As demonstrated through comprehensive experiments, MotionDreamer outperforms the state-of-the-art methods that are typically GAN or Diffusion-based in both faithfulness and diversity. Thanks to the consistency and robustness of the quantization-based approach, MotionDreamer can also effectively perform downstream tasks such as temporal motion editing, \textcolor{update}{crowd animation}, and beat-aligned dance generation, all using a single reference motion. Visit our project page: https://motiondreamer.github.io/

One-Minute Video Generation with Test-Time Training

Transformers today still struggle to generate one-minute videos because self-attention layers are inefficient for long context. Alternatives such as Mamba layers struggle with complex multi-scene stories because their hidden states are less expressive. We experiment with Test-Time Training (TTT) layers, whose hidden states themselves can be neural networks, therefore more expressive. Adding TTT layers into a pre-trained Transformer enables it to generate one-minute videos from text storyboards. For proof of concept, we curate a dataset based on Tom and Jerry cartoons. Compared to baselines such as Mamba~2, Gated DeltaNet, and sliding-window attention layers, TTT layers generate much more coherent videos that tell complex stories, leading by 34 Elo points in a human evaluation of 100 videos per method. Although promising, results still contain artifacts, likely due to the limited capability of the pre-trained 5B model. The efficiency of our implementation can also be improved. We have only experimented with one-minute videos due to resource constraints, but the approach can be extended to longer videos and more complex stories. Sample videos, code and annotations are available at: https://test-time-training.github.io/video-dit

Content-Aware Transformer for All-in-one Image Restoration

Image restoration has witnessed significant advancements with the development of deep learning models. Although Transformer architectures have progressed considerably in recent years, challenges remain, particularly the limited receptive field in window-based self-attention. In this work, we propose DSwinIR, a Deformable Sliding window Transformer for Image Restoration. DSwinIR introduces a novel deformable sliding window self-attention that adaptively adjusts receptive fields based on image content, enabling the attention mechanism to focus on important regions and enhance feature extraction aligned with salient features. Additionally, we introduce a central ensemble pattern to reduce the inclusion of irrelevant content within attention windows. In this way, the proposed DSwinIR model integrates the deformable sliding window Transformer and central ensemble pattern to amplify the strengths of both CNNs and Transformers while mitigating their limitations. Extensive experiments on various image restoration tasks demonstrate that DSwinIR achieves state-of-the-art performance. For example, in image deraining, compared to DRSformer on the SPA dataset, DSwinIR achieves a 0.66 dB PSNR improvement. In all-in-one image restoration, compared to PromptIR, DSwinIR achieves over a 0.66 dB and 1.04 dB improvement on three-task and five-task settings, respectively. Pretrained models and code are available at our project https://github.com/Aitical/DSwinIR.

A Deep Learning Approach to Anomaly Detection in High-Frequency Trading Data

This paper proposes an algorithm based on a staged sliding window Transformer architecture to detect abnormal behaviors in the microstructure of the foreign exchange market, focusing on high-frequency EUR/USD trading data. The method captures multi-scale temporal features through a staged sliding window, extracts global and local dependencies by combining the self-attention mechanism and weighted attention mechanism of the Transformer, and uses a classifier to identify abnormal events. Experimental results on a real high-frequency dataset containing order book depth, spread, and trading volume show that the proposed method significantly outperforms traditional machine learning (such as decision trees and random forests) and deep learning methods (such as MLP, CNN, RNN, LSTM) in terms of accuracy (0.93), F1-Score (0.91), and AUC-ROC (0.95). Ablation experiments verify the contribution of each component, and the visualization of order book depth and anomaly detection further reveals the effectiveness of the model under complex market dynamics. Despite the false positive problem, the model still provides important support for market supervision. In the future, noise processing can be optimized and extended to other markets to improve generalization and real-time performance.