Room impulse responses (RIRs) are essential for many acoustic signal processing tasks, yet measuring them densely across space is often impractical. In this work, we propose RIR-Former, a grid-free, one-step feed-forward model for RIR reconstruction. By introducing a sinusoidal encoding module into a transformer backbone, our method effectively incorporates microphone position information, enabling interpolation at arbitrary array locations. Furthermore, a segmented multi-branch decoder is designed to separately handle early reflections and late reverberation, improving reconstruction across the entire RIR. Experiments on diverse simulated acoustic environments demonstrate that RIR-Former consistently outperforms state-of-the-art baselines in terms of normalized mean square error (NMSE) and cosine distance (CD), under varying missing rates and array configurations. These results highlight the potential of our approach for practical deployment and motivate future work on scaling from randomly spaced linear arrays to complex array geometries, dynamic acoustic scenes, and real-world environments.
Polyp segmentation is a key aspect of colorectal cancer prevention, enabling early detection and guiding subsequent treatments. Intelligent diagnostic tools, including deep learning solutions, are widely explored to streamline and potentially automate this process. However, even with many powerful network architectures, there still comes the problem of producing accurate edge segmentation. In this paper, we introduce a novel network, namely RTA-Former, that employs a transformer model as the encoder backbone and innovatively adapts Reverse Attention (RA) with a transformer stage in the decoder for enhanced edge segmentation. The results of the experiments illustrate that RTA-Former achieves state-of-the-art (SOTA) performance in five polyp segmentation datasets. The strong capability of RTA-Former holds promise in improving the accuracy of Transformer-based polyp segmentation, potentially leading to better clinical decisions and patient outcomes. Our code is publicly available on GitHub.
Graph Transformers (GTs) have demonstrated superior performance compared to traditional message-passing graph neural networks in many studies, especially in processing graph data with long-range dependencies. However, GTs tend to suffer from weak inductive bias, overfitting and over-globalizing problems due to the dense attention. In this paper, we introduce SFi-attention, a novel attention mechanism designed to learn sparse pattern by minimizing an energy function based on network flows with l1-norm regularization, to relieve those issues caused by dense attention. Furthermore, SFi-Former is accordingly devised which can leverage the sparse attention pattern of SFi-attention to generate sparse network flows beyond adjacency matrix of graph data. Specifically, SFi-Former aggregates features selectively from other nodes through flexible adaptation of the sparse attention, leading to a more robust model. We validate our SFi-Former on various graph datasets, especially those graph data exhibiting long-range dependencies. Experimental results show that our SFi-Former obtains competitive performance on GNN Benchmark datasets and SOTA performance on LongRange Graph Benchmark (LRGB) datas
Recent advances in deep learning have significantly improved facial landmark detection. However, existing facial landmark detection datasets often define different numbers of landmarks, and most mainstream methods can only be trained on a single dataset. This limits the model generalization to different datasets and hinders the development of a unified model. To address this issue, we propose Proto-Former, a unified, adaptive, end-to-end facial landmark detection framework that explicitly enhances dataset-specific facial structural representations (i.e., prototype). Proto-Former overcomes the limitations of single-dataset training by enabling joint training across multiple datasets within a unified architecture. Specifically, Proto-Former comprises two key components: an Adaptive Prototype-Aware Encoder (APAE) that performs adaptive feature extraction and learns prototype representations, and a Progressive Prototype-Aware Decoder (PPAD) that refines these prototypes to generate prompts that guide the model's attention to key facial regions. Furthermore, we introduce a novel Prototype-Aware (PA) loss, which achieves optimal path finding by constraining the selection weights of proto
We present SLAM-Former, a novel neural approach that integrates full SLAM capabilities into a single transformer. Similar to traditional SLAM systems, SLAM-Former comprises both a frontend and a backend that operate in tandem. The frontend processes sequential monocular images in real-time for incremental mapping and tracking, while the backend performs global refinement to ensure a geometrically consistent result. This alternating execution allows the frontend and backend to mutually promote one another, enhancing overall system performance. Comprehensive experimental results demonstrate that SLAM-Former achieves superior or highly competitive performance compared to state-of-the-art dense SLAM methods.
We study the effect of the fragility of glass formers on the yielding transition under oscillatory shear via extensive computer simulations. Employing sphere assemblies interacting with a harmonic potential as our model glass former, we tune fragility by changing the system's density - higher density corresponds to large fragility. Our study reveals significant differences in the yielding transition between strong and fragile glass formers. While both glass formers exhibit similar behaviour under poorly annealed initial conditions, the yielding transition shifts to larger values with increased annealing for fragile glasses while remaining relatively constant for strong glasses. We rationalize our results by introducing a new elastoplastic model, which qualitatively reproduces the simulation results and offers valuable insight into the physics of yielding transition under oscillatory shear deformation.
We present Mobile-Former, a parallel design of MobileNet and transformer with a two-way bridge in between. This structure leverages the advantages of MobileNet at local processing and transformer at global interaction. And the bridge enables bidirectional fusion of local and global features. Different from recent works on vision transformer, the transformer in Mobile-Former contains very few tokens (e.g. 6 or fewer tokens) that are randomly initialized to learn global priors, resulting in low computational cost. Combining with the proposed light-weight cross attention to model the bridge, Mobile-Former is not only computationally efficient, but also has more representation power. It outperforms MobileNetV3 at low FLOP regime from 25M to 500M FLOPs on ImageNet classification. For instance, Mobile-Former achieves 77.9\% top-1 accuracy at 294M FLOPs, gaining 1.3\% over MobileNetV3 but saving 17\% of computations. When transferring to object detection, Mobile-Former outperforms MobileNetV3 by 8.6 AP in RetinaNet framework. Furthermore, we build an efficient end-to-end detector by replacing backbone, encoder and decoder in DETR with Mobile-Former, which outperforms DETR by 1.1 AP but sa
We address the challenging task of identifying, segmenting, and tracking hand-held objects, which is crucial for applications such as human action segmentation and performance evaluation. This task is particularly challenging due to heavy occlusion, rapid motion, and the transitory nature of objects being hand-held, where an object may be held, released, and subsequently picked up again. To tackle these challenges, we have developed a novel transformer-based architecture called HOIST-Former. HOIST-Former is adept at spatially and temporally segmenting hands and objects by iteratively pooling features from each other, ensuring that the processes of identification, segmentation, and tracking of hand-held objects depend on the hands' positions and their contextual appearance. We further refine HOIST-Former with a contact loss that focuses on areas where hands are in contact with objects. Moreover, we also contribute an in-the-wild video dataset called HOIST, which comprises 4,125 videos complete with bounding boxes, segmentation masks, and tracking IDs for hand-held objects. Through experiments on the HOIST dataset and two additional public datasets, we demonstrate the efficacy of HOI
Semantic segmentation of microscopy cell images by deep learning is a significant technique. We considered that the Transformers, which have recently outperformed CNNs in image recognition, could also be improved and developed for cell image segmentation. Transformers tend to focus more on contextual information than on detailed information. This tendency leads to a lack of detailed information for segmentation. Therefore, to supplement or reinforce the missing detailed information, we hypothesized that feedback processing in the human visual cortex should be effective. Our proposed Feedback Former is a novel architecture for semantic segmentation, in which Transformers is used as an encoder and has a feedback processing mechanism. Feature maps with detailed information are fed back to the lower layers from near the output of the model to compensate for the lack of detailed information which is the weakness of Transformers and improve the segmentation accuracy. By experiments on three cell image datasets, we confirmed that our method surpasses methods without feedback, demonstrating its superior accuracy in cell image segmentation. Our method achieved higher segmentation accuracy w
In complex transportation systems, accurately sensing the surrounding environment and predicting the risk of potential accidents is crucial. Most existing accident prediction methods are based on temporal neural networks, such as RNN and LSTM. Recent multimodal fusion approaches improve vehicle localization through 3D target detection and assess potential risks by calculating inter-vehicle distances. However, these temporal networks and multimodal fusion methods suffer from limited detection robustness and high economic costs. To address these challenges, we propose AccidentBlip, a vision-only framework that employs our self-designed Motion Accident Transformer (MA-former) to process each frame of video. Unlike conventional self-attention mechanisms, MA-former replaces Q-former's self-attention with temporal attention, allowing the query corresponding to the previous frame to generate the query input for the next frame. Additionally, we introduce a residual module connection between queries of consecutive frames to enhance the model's temporal processing capabilities. For complex V2V and V2X scenarios, AccidentBlip adapts by concatenating queries from multiple cameras, effectively
With the rising popularity of Transformer-based large language models (LLMs), reducing their high inference costs has become a significant research focus. One effective approach is to compress the long input contexts. Existing methods typically leverage the self-attention mechanism of the LLM itself for context compression. While these methods have achieved notable results, the compression process still involves quadratic time complexity, which limits their applicability. To mitigate this limitation, we propose the In-Context Former (IC-Former). Unlike previous methods, IC-Former does not depend on the target LLMs. Instead, it leverages the cross-attention mechanism and a small number of learnable digest tokens to directly condense information from the contextual word embeddings. This approach significantly reduces inference time, which achieves linear growth in time complexity within the compression range. Experimental results indicate that our method requires only 1/32 of the floating-point operations of the baseline during compression and improves processing speed by 68 to 112 times while achieving over 90% of the baseline performance on evaluation metrics. Overall, our model ef
We investigate the long-term impact of civil war on subnational economic growth across 78 regions in five former Yugoslav republics from 1950 to 2015. Leveraging the outbreak of ethnic tensions and the onset of conflict, we construct counterfactual growth trajectories using a robust region-level donor pool from 28 conflict-free countries. Applying a hybrid synthetic control and difference-in-differences approach, we find that the war in former Yugoslavia inflicted unprecedented regional per capita GDP losses estimated at 38 percent, with substantial regional heterogeneity. The most war-affected regions suffered prolonged and permanent economic declines, while capital cities experienced more transitory effects. Our results are robust to extensive variety of specification tests, placebo analyses, and falsification exercises. Notably, ethnic tensions between Serbs and Croats explain up to 40 percent of the observed variation in economic losses, underscoring the deep and lasting influence of ethnic divisions on economic impacts of the armed conflicts.
Transformers have achieved great success in a wide variety of natural language processing (NLP) tasks due to the attention mechanism, which assigns an importance score for every word relative to other words in a sequence. However, these models are very large, often reaching hundreds of billions of parameters, and therefore require a large number of DRAM accesses. Hence, traditional deep neural network (DNN) accelerators such as GPUs and TPUs face limitations in processing Transformers efficiently. In-memory accelerators based on non-volatile memory promise to be an effective solution to this challenge, since they provide high storage density while performing massively parallel matrix vector multiplications within memory arrays. However, attention score computations, which are frequently used in Transformers (unlike CNNs and RNNs), require matrix vector multiplications (MVM) where both operands change dynamically for each input. As a result, conventional NVM-based accelerators incur high write latency and write energy when used for Transformers, and further suffer from the low endurance of most NVM technologies. To address these challenges, we present X-Former, a hybrid in-memory ha
Recent advances in portable imaging have made camera-based screen capture ubiquitous. Unfortunately, frequency aliasing between the camera's color filter array (CFA) and the display's sub-pixels induces moiré patterns that severely degrade captured photos and videos. Although various demoiréing models have been proposed to remove such moiré patterns, these approaches still suffer from several limitations: (i) spatially varying artifact strength within a frame, (ii) large-scale and globally spreading structures, (iii) channel-dependent statistics and (iv) rapid temporal fluctuations across frames. We address these issues with the Moiré Conditioned Hybrid Adaptive Transformer (MoCHA-former), which comprises two key components: Decoupled Moiré Adaptive Demoiréing (DMAD) and Spatio-Temporal Adaptive Demoiréing (STAD). DMAD separates moiré and content via a Moiré Decoupling Block (MDB) and a Detail Decoupling Block (DDB), then produces moiré-adaptive features using a Moiré Conditioning Block (MCB) for targeted restoration. STAD introduces a Spatial Fusion Block (SFB) with window attention to capture large-scale structures, and a Feature Channel Attention (FCA) to model channel dependenc
Recent advancements in Multimodal Large Language Models (MLLMs) have revolutionized the field of vision-language understanding by integrating visual perception capabilities into Large Language Models (LLMs). The prevailing trend in this field involves the utilization of a vision encoder derived from vision-language contrastive learning (CL), showing expertise in capturing overall representations while facing difficulties in capturing detailed local patterns. In this work, we focus on enhancing the visual representations for MLLMs by combining high-frequency and detailed visual representations, obtained through masked image modeling (MIM), with semantically-enriched low-frequency representations captured by CL. To achieve this goal, we introduce X-Former which is a lightweight transformer module designed to exploit the complementary strengths of CL and MIM through an innovative interaction mechanism. Specifically, X-Former first bootstraps vision-language representation learning and multimodal-to-multimodal generative learning from two frozen vision encoders, i.e., CLIP-ViT (CL-based) and MAE-ViT (MIM-based). It further bootstraps vision-to-language generative learning from a frozen
In this paper, we propose an end-to-end SpA-Former to recover a shadow-free image from a single shaded image. Unlike traditional methods that require two steps for shadow detection and then shadow removal, the SpA-Former unifies these steps into one, which is a one-stage network capable of directly learning the mapping function between shadows and no shadows, it does not require a separate shadow detection. Thus, SpA-former is adaptable to real image de-shadowing for shadows projected on different semantic regions. SpA-Former consists of transformer layer and a series of joint Fourier transform residual blocks and two-wheel joint spatial attention. The network in this paper is able to handle the task while achieving a very fast processing efficiency. Our code is relased on https://github.com/zhangbaijin/SpA-Former-shadow-removal
As more deep learning models are being applied in real-world applications, there is a growing need for modeling and learning the representations of neural networks themselves. An efficient representation can be used to predict target attributes of networks without the need for actual training and deployment procedures, facilitating efficient network deployment and design. Recently, inspired by the success of Transformer, some Transformer-based representation learning frameworks have been proposed and achieved promising performance in handling cell-structured models. However, graph neural network (GNN) based approaches still dominate the field of learning representation for the entire network. In this paper, we revisit Transformer and compare it with GNN to analyse their different architecture characteristics. We then propose a modified Transformer-based universal neural network representation learning model NAR-Former V2. It can learn efficient representations from both cell-structured networks and entire networks. Specifically, we first take the network as a graph and design a straightforward tokenizer to encode the network into a sequence. Then, we incorporate the inductive repre
Transformers are unable to model long-term memories effectively, since the amount of computation they need to perform grows with the context length. While variations of efficient transformers have been proposed, they all have a finite memory capacity and are forced to drop old information. In this paper, we propose the $\infty$-former, which extends the vanilla transformer with an unbounded long-term memory. By making use of a continuous-space attention mechanism to attend over the long-term memory, the $\infty$-former's attention complexity becomes independent of the context length, trading off memory length with precision. In order to control where precision is more important, $\infty$-former maintains "sticky memories" being able to model arbitrarily long contexts while keeping the computation budget fixed. Experiments on a synthetic sorting task, language modeling, and document grounded dialogue generation demonstrate the $\infty$-former's ability to retain information from long sequences.
New metallic glasses containing La or Ce have been introduced that have dynamic properties bordering on extremes of conventional metallic glasses. This provides opportunity to test trends or correlations established before in molecular and polymeric glass-formers if exist the same exist in the broader family of metallic glasses. Due to the drastically different chemical and physical structure of metallic glass-formers than soft matter, there is no guarantee that any correlation found in the latter will hold in the former. If found, the result brings metallic glasses closer to the much wider classes of glass-formers by the similarity in properties, and possibly have the same explanation. In non-metallic glass-formers, a general and fundamental connection has been established between the non-exponentiality parameter of the structural alpha-relaxation and the separation between its relaxation time and the beta-relaxation time. In this paper we explore the experimental data of metallic glass-formers and show the correlation applies. An explanation of this correlation is given. The establishment of the correlation may facilitate the understanding of the roles played by the beta-relaxati
Real structural glasses form through various out-of-equilibrium processes, including temperature quenches, rapid compression, shear, and aging. Each of these processes should be formally understandable within the recently formulated dynamical mean-field theory of glasses, but many of the numerical tools needed to solve the relevant equations for sufficiently long timescales do not yet exist. Numerical simulations of structureless (and therefore mean-field-like) model glass formers can nevertheless aid searching for and understanding such solutions, thanks to their ability to disentangle structural from dimensional effects. We here study the infinite-range Mari-Kurchan model under simple non-equilibrium processes and compare the results with those from the random Lorentz gas [J. Phys. A: Math. Theor. 55 334001, (2022)], which are both mean-field-like and become formally equivalent in the limit of infinite spatial dimensions. Of particular interest are jamming from crunching and under instantaneous temperature quenches. The study allows for an algorithmic understanding of the jamming density and of its approach to the infinite-dimensional limit. The results provide important insight