Overview

Temporal attention studies how models select and combine information from different moments, helping them track change, use long-range context, and focus on relevant events. Common approaches include Transformer self- and cross-attention with temporal or relative-time encodings, local-window attention, and efficient variants that combine attention with recurrent or gated aggregation. These methods are used in video action recognition and grounding, video generation, time-series forecasting, and irregular clinical records, and are evaluated on task-specific video and forecasting benchmarks. A central challenge is balancing long-range context and computational cost, while attention weights may not reliably explain which moments drove a prediction.

Latest papers

67 papers4 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Nov 8, 2026

An Adaptive, Context-Aware, and Stacked Attention Network-Based Recommendation System to Capture Users' Temporal Preference

Recommendation systems have become more important since the widespread use of the Internet. The large amount of information means that it is difficult for users to discover they really need. However, users' preferences can change over time because of the age and the impact of social networks. Recommendation systems must capture users' preferences and recommend suitable items, which is a difficult challenge. This study proposes a novel recommendation system that adapts to the changing preferences of users. By learning and adapting to users' changing preferences better recommendations are provided. This study uses context factors as additional information to model users' preferences more precisely. For the proposed recommendation system, the context is based on users' interaction items within each defined time interval. This study proposes two novel attention mechanisms for the recommendation system. The contextual item attention module captures contextual information, changing pattern in users' preference and the importance of items. The multi-head attention module extends the diversity of users' preferences and adapts to changing preferences. The recommendation performance is improved using additional item's temporal information to model the contextual item's representation. Experiments compare the proposed algorithm with several state-of-the-art recommendation methods using three real-world datasets. The experimental results demonstrate that the proposed context-aware recommendation model outperforms traditional methods and demonstrate the effectiveness with which contextual information is captured by the attention mechanism.
Nov 1, 2026

Tracing How Language Models Integrate Temporal Anchors into Factual Recall

Factual recall in language models is typically framed as retrieving a factual association: a subject--relation pair maps to a single object. However, many facts are context-dependent: the same pair maps to different objects depending on a condition such as time. We introduce anchored factual recall, in which the model receives an explicit conditioning expression, an anchor, and must select the object valid under it. This raises questions that single-object recall does not: where the anchor enters the computation, what it changes, and how that change selects the answer. Focusing on temporal anchors, we answer them with causal interventions on four open-weight models on English prompts and identify two routes. In a subject-mediated route, the anchor resolves the final subject-token representation to the queried year, and the relation redistributes the readout of this state across attention heads. In a direct route] the final position attends to the anchor, and upper-layer MLPs turn this signal into a preference for the time-appropriate object. The two routes are parallel channels: their contributions add up, most queries use both, and their balance depends on the query, e.g., on the relation, consistently across models. This reframes mechanistic accounts of factual recall from retrieving a single stored object to selecting among context-dependent alternatives.
Oct 21, 2026

Multi-Scale Latent Temporal Compression Attention and Video-Text Cross Attention Fusion for Video Action Detection

In video action detection, modeling the temporal dependencies in continuous video streams is crucial. Previous methods based on deep neural networks can perform frame-level video recognition tasks. However, these methods struggle to model dynamic temporal patterns, facing challenges such as redundant frame information, difficulty balancing global and local features, and insufficient fusion of visual and textual features. To address these issues, we propose a video temporal attention module based on the Multi-Scale Latent Temporal Compression Attention, which aggregates continuous temporal sequences into feature representations across diverse temporal scales while efficiently reducing redundancy. We also introduce a Video-Text Cross Attention Fusion module that leverages cross-attention at both latent and standard feature levels, achieving fine-grained fusion between video and textual features to enhance semantic alignment and feature interaction. Experimental results across multiple video recognition benchmarks demonstrate that our proposed methods achieve superior performance compared to existing methods, validating the effectiveness and generalization capability.
Oct 20, 2026

Timing-Aware and Interpretable Self-Attention for Event-Based Wearable Task Transition Detection

Task transition detection aims to identify when a person shifts from one task to another, providing a foundation for continuous health monitoring and timely context-aware interventions. While statistical and deep feature representations have demonstrated strong classification performance, they often rely on aggregated or latent features that are difficult to interpret in behavioural terms. Event-based features provide a compact and interpretable alternative by encoding behavioural and physiological patterns as discrete tokens with explicit semantic meaning, making them well suited for behavioural analysis in health informatics. Self-attention offers a mechanism for modelling interactions among such tokens; however, conventional self-attention classifiers primarily rely on token order and do not explicitly incorporate timing or duration information. As a result, informative temporal cues in event representations may not be fully exploited for task transition detection. This study proposes an event-based time-aware self-attention framework that represents behavioural signals as sequences of discrete events augmented with onset timestamps and durations. Event timing is encoded using a parameter-efficient kernel-based representation, while a novel type-aware duration embedding modulates information propagation according to event persistence. Experiments on a semi-naturalistic wearable dataset show that the proposed model outperforms existing event-based approaches, achieves performance beyond or comparable with statistical and deep-learning models with a more compact input representation, and provides improved interpretability through integrated-gradient-based analysis. These results indicate that explicit modelling of event timing and duration enhances both classification performance and interpretability, supporting reliable deployment in biomedical and health informatics applications.
Oct 9, 2026

Time Delay System for Sequence Modeling

Existing sequence models share a critical limitation: they lack an explicit, interpretable mechanism for content-aware temporal recall. LSTMs compress everything into a single hidden state, thereby losing information about specific past events. Transformers attend to all tokens indiscriminately at quadratic cost, while state-space models like Mamba compress history into a fixed-dimensional state without explicit content-addressable memory. To address this gap, we introduce a novel framework grounded in nonlinear time-delay systems, in which the effective delay is dynamically estimated based on the semantic similarity between current and historical inputs. Our approach features three key innovations: (i) a differentiable semantic lag estimator that computes content-aware soft attention weights over history, producing a weighted historical context and similarity score; (ii) a diagonal state space with closed-form cumulative sum solution, achieving O(1) per-step complexity with no sequential loops; and (iii) an interpretable fuzzy semantic modulation mechanism that learns context-dependent rules for balancing instantaneous processing versus historical recall, where rule centers correspond to prototypical semantic contexts. Experimental results on text classification and generation outperform state-of-the-art methods.
Oct 5, 2026

When Attention Does Not Explain the Peak: Temporal Reference vs. Forecast Output in Attention-Based Time-Series Forecasting

Attention maps are often interpreted as evidence of what a forecasting model uses when making predictions. In our load-forecasting model, a CLS representation of historical demand queries 24 future exogenous horizon tokens through cross-attention, inviting a temporal interpretation in which highly attended horizons may appear to explain forecast peak timing. We test this interpretation using a horizon-level attention descriptor, ΨoutΨ_{\mathrm{out}}. Across 31 day-aligned windows of the Panama load dataset, the forecast achieves a median peak-time error of 0 h and a 51.6% exact-match rate, whereas the argmax of ΨoutΨ_{\mathrm{out}} has a median error of 5 h and 0% exact match. The forecast peak is closer to the observed peak in 27 of 31 windows. This dissociation is not merely an argmax artifact: within ±1\pm1 h, attention reaches only 1.16×1.16\times, 1.11×1.11\times, and 1.14×1.14\times the uniform baseline around observed, predicted, and weekly-naive peaks, respectively, indicating weak and non-selective concentration. Yet the attention profile is structured, with cross-window consistency of 0.83. Replacing 12 future weather features with their training-set means makes the profile nearly uniform, showing sensitivity to future weather variation rather than fixed horizon position alone. The dissociation is also reproduced across three random-seed runs. These results show that structured, input-sensitive, and reproducible horizon-level cross-attention need not provide a valid peak-selective explanation of forecast behavior. The observed behavior is instead consistent with an internal horizon-reference role for integrating future exogenous information, although this functional role is not causally established.
Oct 2, 2026

Parallel Time-Aligned Spiking Self-Attention for Consistent Integer-Valued Training and Spike-Driven Inference

Integer-valued leaky integrate-and-fire (I-LIF) neurons and spike firing approximation (SFA) reduce temporal training cost by representing spike trains as firing counts and normalized firing rates, respectively. However, applying spiking self-attention (SSA) directly to these compressed query, key, and value representations introduces cross-time interactions that are absent during spike-driven inference. We term this operator-level discrepancy Temporal Interaction Mismatch (TIM). We propose Parallel Time-Aligned Spiking Self-Attention (PT-SSA), which reconstructs consecutive virtual spike slices from either I-LIF counts or SFA firing rates, computes attention only between time-aligned slices in parallel, and sums the per-step outputs. To accommodate the reduced attention output scale under SFA, we further introduce Adaptive PT-SSA, which learns a positive per-block rescaling before the output SFA neuron to improve firing-level utilization. Experiments on CIFAR-10, CIFAR-100, and ImageNet-1K show that the proposed methods substantially reduce train--inference mismatch. On CIFAR-100 with I-LIF, PT-SSA reduces the mean Top-1 gap from 1.85 to 0.29 percentage points. On ImageNet-1K, Adaptive PT-SSA reduces the Top-1 gap from 27.78 to 0.06 percentage points and achieves 74.53% spike-driven Top-1 accuracy. A Triton-fused PT-SSA training kernel retains a 2.91×2.91\times throughput advantage over recurrent LIF SSA.
Sep 28, 2026

Cross-attention encoding models reveal dynamic spatiotemporal routing across human higher visual cortex

Understanding how the brain parses actions and events from time-varying natural inputs is a central challenge in neuroscience. Recent work has used deep neural network (DNN) models to build stimulus-computable fMRI encoding models that predict single-voxel responses to complex natural videos. However, the majority of video-computable encoding models predict responses using simple linear mappings from model tokens, overlooking the spatiotemporal structure shared by video representations and neural responses. Recent cross-attention encoding models address this limitation for static images, enabling flexible stimulus-dependent weighting of image content across space. Here, we extend this framework to naturalistic video, using per-parcel cross-attention to dynamically route features from a self-supervised video model (V-JEPA-2) across both space and time, fitting this model to fMRI responses to short video clips. We compare joint spatiotemporal attention with factorized and selectively constrained alternatives, and find that joint routing improves predictions of brain responses to held-out videos across higher visual regions, most consistently in lateral and dorsal visual areas associated with dynamic motion perception. Moreover, our method provides interpretable, stimulus-specific attention maps that dynamically follow moving objects, revealing which locations and temporal moments contribute to each neural response. We further show that attention maps from parcels in different category-selective networks (face-, body-, scene-selective) differentially weight content in accordance with expected semantic selectivity. Together, this work provides a new computational framework for understanding how visual information is adaptively weighted by cortical populations during dynamic visual perception.
Sep 28, 2026

Counterfactual Attention Policy Distillation for Temporal Video Grounding

Temporal video grounding is a key capability of advanced Multimodal Large Language Models (MLLMs) for the thorough understanding of video events, which is however often limited by repeated actions and visually similar contexts in long videos. In this paper, we study this issue from the perspective of On-policy distillation (OPD) and propose a new training regime for MLLMs termed Counterfactual Attention Policy Distillation (CAPD). In particular, OPD is a viable solution for MLLMs via providing dense teacher supervision on student-generated trajectories. But its next-token based teacher-student distillation is hard to identify the specific video segments supporting each predicted timestamp, which is critical for temporal grounding. In this case, CAPD measures how masking each temporal group changes the teacher's output distribution. The resulting counterfactual influence calibrates the teacher's attention and weights token-level distillation, allowing the student to learn the temporal evidence that affects boundary prediction. To validate CAPD, we trained it on Qwen3-VL-8B-Instruct using only 2,500 samples for one epoch, and evaluated it on the TimeLens and multiple general video benchmarks. Experimental results show that CAPD improves average recall by 12.0% relative to GRPO on TimeLens while preserving general video understanding, achieving comparable accuracy to the base model.
Sep 14, 2026

Temporal-Attention Head Specialization During Video Diffusion Training

Video diffusion transformers depend on temporal attention to coordinate information across frames, yet nearly everything known about this mechanism comes from analyzing trained models, so when and where temporal-attention structure forms during training remains poorly characterized. Population averages can also hide it, since a few specializing heads and a diffusing majority cancel in the mean. We therefore conduct a checkpoint-resolved census of every temporal-attention head across nine Open-Sora STDiT training runs spanning three model scales (306M to 1.03B parameters), scoring each head with an entropy-normalized measure of cross-frame attention concentration (CFAC) under a preregistered change-point and effect-size selection rule. The census reveals the sparse picture that averages obscure. Aggregate CFAC is flat or decreasing in every run, while a small minority of heads, roughly 4--13% in full-grid runs, develops pronounced concentration. Across seeds, the reproducible signal is positional but block-level. Selected heads repeatedly arise in the first temporal block, whereas individual head coordinates do not reproduce once block membership is accounted for. Among the analyzed 760M selected heads, attention maps converge to a small repertoire of local frame-routing motifs, self-frame diagonals and adjacent-frame bands, even when the responsible coordinates differ across runs. Correlation and ablation analyses do not establish a causal link to generated video quality, and we bound our claims accordingly. Beyond this STDiT family, the study contributes a transferable methodology. Checkpoint-resolved, per-head analysis under fixed selection rules can expose sparse temporal organization in other factorized video diffusion transformers and, with adapted routing metrics, in joint spatio-temporal architectures.
Sep 9, 2026

Reliable Egocentric Action Anticipation via Temporal Reliability Suppression and Compositional Graph Decoding

Wearable action anticipation systems must remain reliable despite missing frames, masking, and sensor noise, yet existing egocentric anticipation methods largely assume clean observations. We identify two complementary failure modes under temporal corruption: unreliable temporal evidence during encoding and implausible, low-support verb-noun compositions during decoding. We address them with a lightweight framework combining Temporal Reliability Suppression (TRS) and Robust Verb-Noun Graph (RVG) decoding. TRS predicts a per-frame suppression score from the projected input embedding and uses it as a learned key-side attention penalty at every encoder block and to derive reliability-weighted temporal pooling. RVG re-ranks verb-noun pairs using a PMI-based compatibility graph constructed from training labels. Under corruption-augmented training, TRS+CA+RVG reaches 29.1% average corrupted accuracy and 88.2% relative robustness across six corruptions, including three mechanisms absent during training, while reducing rare verb-noun predictions from 15.4% to 1.1%. Multi-seed and diagnostic experiments show that TRS responds to synthetic masking; shuffled-graph and frequency-only controls further indicate that RVG gains depend on genuine pairwise compatibility rather than marginal-frequency effects alone.
Sep 8, 2026

Adaptive Anisotropic Attention for Axis-Structured Signals

Dense self-attention treats all token pairs as equally plausible before learning, an interaction-isotropic prior that can be mismatched to structured signals. For structured, low signal-to-noise ratio (SNR) signals such as EEG, dependencies are organized along the electrode and time axes, and this uniform prior exposes each token to many irrelevant interactions. We introduce Adaptive Anisotropic Attention (AAA), which splits attention into two paths: a temporal path, where each token attends to the tokens of its own electrode across time, and a spatial path, where it attends to the tokens of the other electrodes at the same time step. A small gate predicts, for every token, a convex combination of the two path outputs: two non-negative weights that sum to one. On six EEG downstream tasks, the resulting model, AXON (AXis-factorized Operator Network), improves mean balanced accuracy over a dense baseline under both linear probing and full fine-tuning. We show that both paths (temporal and spatial) are necessary and that the weighted sum beats a hard choice of one path; most of the benefit comes from the gate learning a different temporal/spatial balance at each layer of the network. Controlled audio spectrogram experiments show that axis factorization transfers beyond EEG. These results suggest that aligning attention with the natural axes of structured signals provides a useful inductive bias.
Sep 7, 2026

Continuous Token-Level Spatio-Temporal Context Modeling for Visual Object Tracking

Spatio-temporal context has become increasingly crucial for visual tracking. However, most existing approaches extract spatio-temporal cues via discrete sampling strategies, which inherently deviate from the continuity of spatio-temporal context, thereby deteriorating tracking performance. To address this challenge, we propose TLCTrack, a novel tracking framework that models token-level spatio-temporal context through continuously updated salient tokens, enabling more accurate target representation. Specifically, TLCTrack incorporates three components: Masked Unidirectional Attention (MUA), Spatial Salient Token Collection (SSTC), and Temporal Salient Token Bank (TSTB) modules. By explicitly integrating spatio-temporal context, MUA extracts discriminative targetaware spatial features in the search region. To avoid the negative impact of background on feature learning, SSTC progressively suppresses background interference, thereby enhancing target spatial representation. Finally, TSTB captures high-quality spatio-temporal information through continuous salient token updates. Extensive experiments on five benchmarks demonstrate that our method achieves superior performance over state-of-the-art trackers. Code and models are available at https://github.com/xiading123/TLCTrack.
Sep 4, 2026

Intrinsic Temporal Adaptation of CLIP for Partially Relevant Video Retrieval

Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos that contain moments relevant to a text query. Since the target moment occupies only a portion of the video, PRVR requires retrieval based on fine-grained understanding beyond coarse video-level matching. However, existing methods often rely on frozen CLIP frame features, which lack temporal understanding. Even with recent progress in parameter-efficient CLIP adaptation, video-level predictions can still be supported by imprecise frame-level evidence. In this paper, we propose an Intrinsic Temporal Adaptation (ITA) framework for PRVR. First, our Backbone-Internal Temporal Adaptation allows the last few visual transformer layers to attend over groups of neighboring frames. This provides temporally aware frame embeddings while keeping CLIP frozen and training only adaptation parameters. Second, we introduce Affinity-Weighted Gradient Propagation to address the weakly supervised nature of PRVR, softly aggregating top-kk frames based on text-frame affinities and propagating learning signals to multiple query-relevant frames. Our method achieves state-of-the-art performance on PRVR benchmarks, demonstrates robust cross-dataset transfer, and retrieves substantially more accurate frame-level evidence within ground-truth query-relevant moments. Our code is available at github.com/hynnsk/ITA.
Aug 31, 2026

Liquid Gated Attention

Real-world time series often exhibit irregular sampling and extended temporal horizons, requiring models to capture continuous-time dynamics across arbitrary intervals without prohibitive scaling costs. Discrete-time methods collapse variable time intervals into static positional steps; solver-dependent continuous-time models preserve temporal structure but rely on sequential integration, precluding parallelization; and solver-free approximations avoid this cost yet none couples observed time intervals with input-driven state modulation. We propose Liquid Gated Attention (LGA), a solver-free parallel temporal operator. By parameterizing an input-driven gating mechanism with observed time intervals, LGA introduces a continuous-time inductive bias and formulates hidden state evolution as a fast-weight associative memory, enabling parallel computation across the temporal dimension. Using matrix associativity in non-causal encoding and a prefix scan in causal encoding, LGA attains linear temporal complexity in sequence length in both modes. A sequence-level normalization bounds cumulative temporal decay for stable long-horizon optimization. Building on LGA, we instantiate LFormer, a modular backbone for continuous-time representation learning. Across six tasks and sixteen datasets spanning up to 17,984 steps, LFormer demonstrates long-range dependency modeling, fine-grained state tracking, and trajectory reconstruction from sparse and noisy observations, while delivering competitive performance against state-of-the-art discrete-time and continuous-time baselines with linear scaling efficiency.
Aug 18, 2026

MotoSafety: Edge-AI with Learned Temporal Importance for Two-Wheeler Collision Risk Assessment Under Time Pressure

Powered two-wheeler riders face critical safety challenges in low- and middle-income countries, yet limited studies exist on how cognitive stressors such as Time Pressure influence collision risk. We address this gap by introducing a comprehensive dataset consisting of over 129,000 labeled multivariate time-series feature windows, gathered across 153 simulator rides from 51 participants under No, Low, and High TP scenarios. Across each sequence, we capture 64 distinct attributes covering vehicle motion, rider control actions, spatial proximity, and rule compliance indicators. Using this dataset, we introduce MotoSafety, a new edge-AI framework built on the Learned Temporal Importance (LTI) concept. MotoSafety achieves 94.97% accuracy and 99.33% ROC AUC, outperforming ten baselines, including TimesNet and LLM4TS, and achieves 0.039 MSE and 0.094 MAE for forecasting (4.4x lower error than Time-LLM and iTransformer). With only 1.15M parameters and 0.135 ms latency, it is suitable for edge deployment on low-cost CPU hardware. Using ground truth TP as an inductive bias improves accuracy from 94.09% to 94.97%, while predicted TP achieves 94.82%. Using only 21 IMU+GPS features, it achieves 93.91% accuracy, indicating practical deployment. Beyond PTW safety, the architecture shows better transferability to human activity (97.66%) and clinical (99.65%) domains. This lightweight framework advances PTW collision risk assessment, supporting the Safe System Approach for Intelligent Transportation Systems.
Aug 10, 2026

End-to-End Visual Odometry with RNNs and Attention

Video Odometry (VO) is the process of estimating the ego-motion of an object by analyzing visual information such as a sequence of frames from one or multiple cameras. It has been a popular research topic in computer vision and robotics, and its applications include mobile robotic systems as well as autonomous driving. In this project, we investigate existing end-to-end deep-learning approaches to VO, and propose a novel temporal attention-based model to improve upon the baseline. In addition, while the vast majority of existing deep-learning-based approaches to VO are trained on driving data, we investigate the performance of deep-learning-based VO to the more dynamic and complex problem of hand-held cameras.
Aug 5, 2026

TRCoRSurg: Temporal-Relational Co-Reasoning for Surgical Video Triplet Recognition

Understanding complex surgical scenes requires recognizing multiple interdependent entities, such as instruments, actions, and targets, while maintaining their relational consistency across time. Existing surgical triplet recognition methods struggle to jointly model intra-frame label dependencies and inter-frame temporal semantics in a unified manner. To address these limitations, we propose a unified framework that integrates spatial, relational, and temporal cues for robust surgical triplet recognition. Specifically, class-specific spatial priors are first extracted through a multi-scale encoder. These priors are then refined by a Label Correlation Modeling module with multi-scale class activation map-guided relational extraction (MS-CAMRE), enabling the model to capture both static co-occurrence patterns and dynamic contextual dependencies among triplet components. Furthermore, a Bidirectional Temporal-Relational Fusion Attention (BTRFA) module harmonizes temporal and relational representations to achieve coherent temporal reasoning. We also introduce a new evaluation metric, the Triplet Consistency Error Rate (TCER), which quantitatively measures the model's ability to preserve causal and semantic consistency across triplets. Extensive experiments on the CholecT45 and ProstaTD datasets show that our method achieves state-of-the-art performance, improving AP_IVT by 5.1 percent and 7.8 percent, respectively. Moreover, according to TCER, our approach achieves relative reductions of more than 36 percent and 25 percent on the two datasets, respectively, demonstrating the effectiveness of our framework in temporal-relational co-reasoning.
Jul 29, 2026

THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model

Temporal heterogeneous graphs offer a natural abstraction for dynamic relational systems in which diverse node and relation types co-exist and evolve over time. Learning on such graphs requires jointly modeling cross-type structural heterogeneity and the temporal dynamics of interactions, yet existing methods still struggle to reconcile parameter-efficient cross-type transfer with relation-aware specialization, and typically inject time only as additive features outside the attention kernel. We propose THGFM, a web-scale temporal heterogeneous graph fusion model that addresses both limitations within a unified dual-path architecture. THGFM couples a Shared-Space Temporal Attention branch for parameter-efficient cross-type transfer with a Relational Type-Partitioned Temporal Attention branch for relation-aware specialization, and integrates them through Dual-Path Relational--Shared Fusion, instantiated with Type-Conditioned Non-Competitive Gated Sum Fusion: a adaptive mechanism that assigns independent, type-conditioned feature-wise gates to the shared and specialized branches, allowing both to be amplified or suppressed without zero-sum competition. To directly incorporate relative time into the attention score, THGFM further introduces Rotary Temporal Attention, which rotates queries and keys by half-phases of relative time before matching. THGFM consistently outperforms baseline graph transformer models on academic graphs benchmarks, delivering a +3.25%+3.25\% six-task mean gain, with peak relative gains of +12.37%+12.37\% on OAG-CS PV, +4.87%+4.87\% on PF-L2L_2, and +1.18%+1.18\% on PF-L1L_1, and +4.24%+4.24\%, +3.73%+3.73\%, and +4.61%+4.61\% on OGBN-MAG, HTAG-ArXiv, and HTAG-DBLP, respectively.
Jul 29, 2026

ClockRoPE: Random Fourier Rotations for Temporal Routine Modeling

Rotary Position Embedding (RoPE) has been widely adopted in transformer-based large language models. However, its log-linear frequency schedule, originally designed to produce long-term attention decay, limits its adoption in domains with more complex distance-correlation patterns, such as temporal periodicity in sequential recommendation. We investigate the expressiveness of general query/key rotations and find that any normalized continuous positive-definite attention modulation function can be approximated by random rotations induced by its own Fourier transform, which we term Random Fourier Rotations. Building on this theory, we propose ClockRoPE for routine modeling in sequential recommendation, where rotation frequencies are derived from periodic attention modulation functions. In online A/B tests, ClockRoPE demonstrates consistent improvements in valued engagement metrics, and has been successfully deployed in production-scale generative retrieval system at a major video-sharing platform.
Jul 25, 2026

Structure over Depth: A Single-Block Spatio-Temporal Transformer for Multi-Entity Reasoning

Modeling multi-entity temporal data requires capturing dependencies across entities, time, and their interactions. Transformer-based approaches perform well but often rely on deep stacks of layers to learn these heterogeneous dependencies implicitly, increasing computational cost. We revisit this problem from a structural perspective and decompose multi-entity temporal dynamics into three interaction types: spatial interactions among entities, temporal interactions across time, and cross interactions coupling the two domains. We propose a structured spatio-temporal transformer block that explicitly models all three within a single stage. It uses parallel spatial and temporal self-attention, followed by bidirectional cross-attention, and combines the outputs through learnable gated fusion. By directly encoding these complementary views, the model reduces the need for deep stacking. We evaluate the approach on video-based group activity recognition, skeleton-based human interaction analysis, and wearable sensor-based activity recognition. Despite its simplicity, the single structured Transformer block matches or outperforms deeper architectures with only 1.76M parameters. The results suggest that depth in prior models partly compensates for implicit and entangled interaction modeling, whereas explicit factorization offers a more efficient and transparent alternative. More broadly, this work supports a structure-first design principle: expressive multi-entity temporal reasoning can emerge by exposing interaction structure rather than relying on depth.
Jul 11, 2026

GRATE: Temporal Extensions for Inductive KG Foundation Models via Gated Rotary Attention

Knowledge graph foundation models such as Ultra and Trix achieve strong inductive transfer by learning relation-graph representations that generalise to unseen entities and relations. Extending this transferability to temporal knowledge graphs (TKGs) remains challenging: existing temporal models tie their parameters to dataset-specific entities, relations, or timestamps and are not designed to transfer to TKGs with disjoint vocabularies. We propose GRATE (Gated Rotary Attention for Temporal Encoding), an entity-side message function that adds no learnable parameters and encodes time through relative time differences by rotating each edge message according to its time gap to the query and applying a query-conditioned gate to select temporally relevant signals. GRATE integrates into NBFNet-style KG foundation models while preserving structural transferability. Existing TKG benchmarks evaluate within shared train/test vocabularies and cannot directly test cross-dataset temporal transfer; we therefore construct GDELTIndT and WIKIIndT, inductive transfer benchmark suites with disjoint entities, relations, and timestamps spanning both interpolation and extrapolation. Across these benchmarks and held-out forecasting datasets, a single jointly pretrained GRATE checkpoint improves over the static base model in most settings.
Jul 8, 2026

AT-Attn: Temporal-Aware Cross-Attention for Longitudinal Multimodal Alzheimer's Disease Diagnosis

In longitudinal Alzheimer's disease (AD) diagnosis support, clinical and imaging information is often collected at irregular visits. Integrating these multimodal observations may improve diagnostic assessment, but naive fusion can degrade performance when MRI is noisy or intermittently unavailable. We propose AT-Attn, a temporal-aware multimodal framework that combines Change-and-Time encoding, time-biased asymmetric cross-attention, and gated fusion to integrate MRI with longitudinal clinical information. We evaluate AT-Attn on an MRI-retained ADNI cohort of 1,520 patients using structural MRI, six cognitive-scale trajectories, and seven static clinical variables under patient-level five-fold cross-validation. The main asymmetric AT-Attn model achieves accuracy 0.719+/-0.024, macro F1 0.721+/-0.023, ROC-AUC 0.873+/-0.013, and PR-AUC 0.783+/-0.018, outperforming unimodal and naive multimodal fusion baselines while remaining competitive with strong tabular baselines. These results suggest that a temporal-aware and constrained fusion strategy can help structural MRI contribute clinically relevant complementary information for patient-level AD diagnosis support.
Jul 2, 2026

MVFusion-GS: Motion-Variance Guided Temporal Attention for High-Quality Dynamic Gaussian Splatting

3D Gaussian Splatting (3DGS) enables real-time novel view synthesis for static scenes. Extending it to dynamic scenes via deformation fields has recently attracted significant attention, particularly for dynamic scene reconstructionband distractor-free. However, existing deformation networks lack explicit motion awareness: they neither capture long-term motion intensity nor exploit short-term temporal coherence, leading to inaccurate foreground deformation and pseudo-static residuals in the background. We present MVFusion-GS, a method that enhances deformation networks with two complementary motion-aware mechanisms. The Motion-Variance Guided Refinement aggregates per-Gaussian deformation statistics across time to estimate motion variance and uses it to guide dynamic-static separation during deformation prediction. The MotionFormer Temporal Attention module applies Transformer self-attention over neighboring timesteps to model local motion dependencies and improve temporal consistency. Extensive experiments on both dynamic scene reconstruction and distractor-free reconstruction benchmarks demonstrate state-of-the-art performance, showing that explicit motion awareness improves both foreground motion modeling and static background reconstruction.
Jun 29, 2026

Reweighting Framewise Attention in Video Transformers for Facial Expression Understanding

Understanding facial expressions in videos requires modeling subtle and localized facial dynamics under unconstrained conditions. Although recent Vision Transformer (ViT)-based video models have shown strong performance through large-scale self-supervised pretraining, their attention mechanisms often emphasize dominant global motions and coarse temporal dynamics, limiting sensitivity to fine-grained facial variations. To address this limitation, we propose MiRA (Marginal-induced Attention Redistribution), a plug-in frame-marginal attention redistribution framework for ViT backbones that enhances spatio-temporal selectivity toward subtle facial dynamics without introducing additional trainable parameters. MiRA derives frame-level confidence and intra-frame concentration statistics from self-attention maps to estimate frame-wise marginal importance and redistribute attention toward spatiotemporally localized facial cues. We first introduce a principled exact mode based on post-softmax attention redistribution. To further improve efficiency, we propose flashLite mode, a lightweight pre-softmax approximation that integrates frame-marginal redistribution into FlashAttention kernels while preserving the effectiveness of the exact formulation. Experimental results on challenging Facial Expression Recognition (FER) benchmarks demonstrate consistent improvements over strong ViT baselines.
Jun 26, 2026

A Study of Temporal Fusion Strategies for Named Entity Recognition in Historical Texts

Temporal variation poses a unique challenge for named entity recognition (NER) in historical texts, where entities drift in surface form and salience across time. While language models (LMs) have made progress in various NLP tasks, their ability to reason about temporality, especially in diachronic contexts, remains limited or at least, questionable. In this paper, we systematically study how temporal metadata can be structurally embedded into NER models using a range of lightweight fusion strategies. We experiment with both absolute and relative temporal representations, injected into Transformer-based architectures via early or late fusion mechanisms such as cross-attention, adapters, and concatenation. Our evaluations on French and German historical datasets reveal that late fusion strategies yield more robust and temporally generalisable performance, particularly in early and noisy periods.
Jun 22, 2026

Interpretable Kolmogorov-Arnold Network with Feature-Isolated Temporal Attention Mechanism for Electricity Load Forecasting

Accurate electricity load forecasting is a crucial prerequisite for stable power system operations. While prevalent deep learning models present competitive performance, they often operate as black boxes and lack interpretability. While the Kolmogorov-Arnold network (KAN) has emerged as a promising alternative because of its learnable activation function design, its direct application to time-series forecasting faces challenges in modeling complex temporal data patterns. Also, simple integration into existing architectures, such as serving as replacement of neural modules, cannot fully leverage KAN's interpretability strengths. To address these gaps, this study develops LoadKAN, a novel hybrid and interpretable framework for load forecasting that synergistically combines a specifically-designed feature-isolated temporal attention mechanism with a KAN module. The attention stage aims to extract temporal dynamics from each input feature independently, such as historical load and human mobility, providing distilled feature representations to the KAN module for interpretable predictions. When evaluated on datasets from three representative U.S. electricity markets, our LoadKAN remains highly competitive when compared to extensively-tuned, state-of-the-art, black-box deep learning benchmarks. More importantly, LoadKAN's interpretability enables a granular analysis of the learned non-linear relationships between six distinct mobility patterns and electricity load. Through KAN-learned activation functions, our quantitative sensitivity analyses on mobility features reveal complex and market-specific dependencies. These findings further demonstrate the ability of our LoadKAN to generate insights often obscured by opaque black-box neural forecasting models.
Jun 9, 2026

Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Models

Large Audio-Language Models (LALMs) excel at audio understanding but expose little about where in an audio signal they attend. We introduce instruction-based vector steering, which constructs a steering vector by contrasting activations from differently instructed prompts while keeping the audio fixed. Through a systematic probe of LALM attention, we find that - unlike standard prompting or audio-based steering - this intervention significantly redistributes the temporal attention allocated to audio tokens, concentrating it on acoustically relevant regions. We then show that this attention shift is behaviorally meaningful: in a controlled three-event setting, reading out the temporal position of maximal steering-induced attention change recovers the location of a queried sound event without any training, attaining 60.87% and 68.72% overlap with ground-truth intervals on Qwen2-Audio and Audio Flamingo 3, far above direct prompting (31.84%, 46.75%) and random baselines (27.74%). Our results characterize a mechanistic property of instruction-based steering in LALMs and provide a training-free probe for the latent temporal structure these models encode.
Jun 9, 2026

Transformer Based Model for Spatiotemporal Feature Learning in EEG Emotion Recognition

Electroencephalography (EEG) is a widely adopted technique for monitoring brain activity, offering valuable insights into neurological states due to its high temporal resolution and cost-effectiveness. To enhance the analysis of complex EEG data, we propose EEG-TransNet, an architecture designed to capture temporal, regional, and synchronous features of EEG signals. EEG-TransNet introduces three key modules: 1) a preprocessing and feature extraction module leveraging ResNet and wavelet-based denoising, 2) a Local Self-Attention Block for regional feature learning, and 3) a Fuzzy-Attention Synchronous Transformer (FAST) to model spatiotemporal dependencies. Through extensive experiments on three EEG datasets (BETA, SEED, and DepEEG), the proposed model consistently outperforms other methods in terms of classification accuracy and robustness across varying signal lengths. Ablation studies confirm the contribution of the Local Self-Attention Block in improving performance, and the inclusion of depthwise separable convolutions in the decoder reduces computational complexity while maintaining high accuracy. EEG-TransNet's ability to generalize across subjects with minimal performance variation highlights its potential as a robust tool for EEG-based brain activity classification and emotion recognition tasks.
Jun 1, 2026

Physics-Guided Attention in a Lightweight TCN for Efficient WiFi CSI-Based Human Activity Recognition

Human Action Recognition (HAR) using WiFi Channel State Information (CSI) has gained increasing attention due to its non-contact, low-cost, and privacy-preserving nature. However, existing learning-based approaches largely rely on deep, computationally intensive architectures to implicitly capture motion dynamics from CSI measurements, thereby increasing model complexity and reducing efficiency. Instead, we argue that incorporating appropriate inductive biases tailored to the physical characteristics of CSI signals enables more efficient and effective learning. In this work, we propose a compact temporal convolutional network (TCN)-based framework that explicitly incorporates motion-aware inductive biases into feature learning. Specifically, we introduce a Doppler-energy-guided temporal attention mechanism in feature space to emphasize motion-salient time segments, and a variance-driven channel attention module to weight informative subcarriers based on temporal motion statistics adaptively. By integrating these domain-specific priors, the proposed model effectively captures motion dynamics without increasing architectural depth. Extensive experiments on multiple benchmark datasets demonstrate that our approach achieves superior performance compared to deeper baselines, while significantly reducing parameter count and computational cost.