Personality Prediction from Life Stories using Language Models

Natural Language Processing (NLP) offers new avenues for personality assessment by leveraging rich, open-ended text, moving beyond traditional questionnaires. In this study, we address the challenge of modeling long narrative interview where each exceeds 2000 tokens so as to predict Five-Factor Model (FFM) personality traits. We propose a two-step approach: first, we extract contextual embeddings using sliding-window fine-tuning of pretrained language models; then, we apply Recurrent Neural Networks (RNNs) with attention mechanisms to integrate long-range dependencies and enhance interpretability. This hybrid method effectively bridges the strengths of pretrained transformers and sequence modeling to handle long-context data. Through ablation studies and comparisons with state-of-the-art long-context models such as LLaMA and Longformer, we demonstrate improvements in prediction accuracy, efficiency, and interpretability. Our results highlight the potential of combining language-based features with long-context modeling to advance personality assessment from life narratives.

RATTENTION: Towards the Minimal Sliding Window Size in Local-Global Attention Models

Local-global attention models have recently emerged as compelling alternatives to standard Transformers, promising improvements in both training and inference efficiency. However, the crucial choice of window size presents a Pareto tradeoff: larger windows maintain performance akin to full attention but offer minimal efficiency gains in short-context scenarios, while smaller windows can lead to performance degradation. Current models, such as Gemma2 and Mistral, adopt conservative window sizes (e.g., 4096 out of an 8192 pretraining length) to preserve performance. This work investigates strategies to shift this Pareto frontier, enabling local-global models to achieve efficiency gains even in short-context regimes. Our core motivation is to address the intrinsic limitation of local attention -- its complete disregard for tokens outside the defined window. We explore RATTENTION, a variant of local attention integrated with a specialized linear attention mechanism designed to capture information from these out-of-window tokens. Pretraining experiments at the 3B and 12B scales demonstrate that RATTENTION achieves a superior Pareto tradeoff between performance and efficiency. As a sweet spot, RATTENTION with a window size of just 512 consistently matches the performance of full-attention models across diverse settings. Furthermore, the recurrent nature inherent in the linear attention component of RATTENTION contributes to enhanced long-context performance, as validated on the RULER benchmark. Crucially, these improvements do not compromise training efficiency; thanks to a specialized kernel implementation and the reduced window size, RATTENTION maintains training speeds comparable to existing state-of-the-art approaches.

Two heads are better than one: simulating large transformers with small ones

The quadratic complexity of self-attention prevents transformers from scaling effectively to long input sequences. On the other hand, modern GPUs and other specialized hardware accelerators are well-optimized for processing small input sequences in transformers during both training and inference. A natural question arises: can we take advantage of the efficiency of small transformers to deal with long input sequences? In this paper, we show that transformers with long input sequences (large transformers) can be efficiently simulated by transformers that can only take short input sequences (small transformers). Specifically, we prove that any transformer with input length $N$ can be efficiently simulated by only $O((N/M)^2)$ transformers with input length $M \ll N$, and that this cannot be improved in the worst case. However, we then prove that in various natural scenarios including average-case inputs, sliding window masking and attention sinks, the optimal number $O(N/M)$ of small transformers suffice.

CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model

Electroencephalography (EEG) provides real-time insights into brain activity and is widely used in neuroscience. However, variations in channel configurations, sequence lengths, and task objectives limit the transferability of traditional task-specific models. Although recent EEG foundation models (EFMs) aim to learn generalizable representations, they struggle with limited heterogeneous representation capacity and inefficiency in capturing multi-scale brain dependencies. To address these challenges, we propose CodeBrain, an efficient EFM structurally aligned with brain organization, trained in two stages. (1) We introduce a TFDual-Tokenizer that independently tokenizes heterogeneous temporal and frequency components, enabling a quadratic expansion of the discrete representation space. This also offers a degree of interpretability through cross-domain token analysis. (2) We propose the EEGSSM, which combines a structured global convolution architecture and a sliding window attention mechanism to jointly model sparse long-range and local dependencies. Unlike fully connected Transformer models, EEGSSM better reflects the brain's small-world topology and efficiently captures EEG's inherent multi-scale structure. EEGSSM is trained with a masked self-supervised learning objective to predict token indices obtained in TFDual-Tokenizer. Comprehensive experiments on 10 public EEG datasets demonstrate the generalizability of CodeBrain with linear probing. By offering biologically informed and interpretable EEG modeling, CodeBrain lays the foundation for future neuroscience research. Both code and pretraining weights will be released in the future version.

LoLA: Low-Rank Linear Attention With Sparse Caching

Transformer-based large language models suffer from quadratic complexity at inference on long sequences. Linear attention methods are efficient alternatives, however, they fail to provide an accurate approximation of softmax attention. By additionally incorporating sliding window attention into each linear attention head, this gap can be closed for short context-length tasks. Unfortunately, these approaches cannot recall important information from long contexts due to "memory collisions". In this paper , we propose LoLA: Low-rank Linear Attention with sparse caching. LoLA separately stores additional key-value pairs that would otherwise interfere with past associative memories. Moreover, LoLA further closes the gap between linear attention models and transformers by distributing past key-value pairs into three forms of memory: (i) recent pairs in a local sliding window; (ii) difficult-to-memorize pairs in a sparse, global cache; and (iii) generic pairs in the recurrent hidden state of linear attention. As an inference-only strategy, LoLA enables pass-key retrieval on up to 8K context lengths on needle-in-a-haystack tasks from RULER. It boosts the accuracy of the base subquadratic model from 0.6% to 97.4% at 4K context lengths, with a 4.6x smaller cache than that of Llama-3.1 8B. LoLA demonstrates strong performance on zero-shot commonsense reasoning tasks among 1B and 8B parameter subquadratic models. Finally, LoLA is an extremely lightweight approach: Nearly all of our results can be reproduced on a single consumer GPU.

Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction

The attention mechanism of a transformer has a quadratic complexity, leading to high inference costs and latency for long sequences. However, attention matrices are mostly sparse, which implies that many entries may be omitted from computation for efficient inference. Sparse attention inference methods aim to reduce this computational burden; however, they also come with a troublesome performance degradation. We discover that one reason for this degradation is that the sparse calculation induces a distributional shift in the attention outputs. The distributional shift causes decoding-time queries to fail to align well with the appropriate keys from the prefill stage, leading to a drop in performance. We propose a simple, novel, and effective procedure for correcting this distributional shift, bringing the distribution of sparse attention outputs closer to that of quadratic attention. Our method can be applied on top of any sparse attention method, and results in an average 36%pt performance increase, recovering 88% of quadratic attention accuracy on the 131K RULER benchmark when applied on top of sliding window attention with sink tokens while only adding a small overhead. Our method can maintain approximately 98.5% sparsity over full quadratic attention, making our model 32 times faster than Flash Attention 2 when processing 1M token prefills.

HydraNet: Momentum-Driven State Space Duality for Multi-Granularity Tennis Tournaments Analysis

In tennis tournaments, momentum, a critical yet elusive phenomenon, reflects the dynamic shifts in performance of athletes that can decisively influence match outcomes. Despite its significance, momentum in terms of effective modeling and multi-granularity analysis across points, games, sets, and matches in tennis tournaments remains underexplored. In this study, we define a novel Momentum Score (MS) metric to quantify a player's momentum level in multi-granularity tennis tournaments, and design HydraNet, a momentum-driven state-space duality-based framework, to model MS by integrating thirty-two heterogeneous dimensions of athletes performance in serve, return, psychology and fatigue. HydraNet integrates a Hydra module, which builds upon a state-space duality (SSD) framework, capturing explicit momentum with a sliding-window mechanism and implicit momentum through cross-game state propagation. It also introduces a novel Versus Learning method to better enhance the adversarial nature of momentum between the two athletes at a macro level, along with a Collaborative-Adversarial Attention Mechanism (CAAM) for capturing and integrating intra-player and inter-player dynamic momentum at a micro level. Additionally, we construct a million-level tennis cross-tournament dataset spanning from 2012-2023 Wimbledon and 2013-2023 US Open, and validate the multi-granularity modeling capability of HydraNet for the MS metric on this dataset. Extensive experimental evaluations demonstrate that the MS metric constructed by the HydraNet framework provides actionable insights into how momentum impacts outcomes at different granularities, establishing a new foundation for momentum modeling and sports analysis. To the best of our knowledge, this is the first work to explore and effectively model momentum across multiple granularities in professional tennis tournaments.

A Network Science Approach to Granular Time Series Segmentation

Time series segmentation (TSS) is one of the time series (TS) analysis techniques, that has received considerably less attention compared to other TS related tasks. In recent years, deep learning architectures have been introduced for TSS, however their reliance on sliding windows limits segmentation granularity due to fixed window sizes and strides. To overcome these challenges, we propose a new more granular TSS approach that utilizes the Weighted Dual Perspective Visbility Graph (WDPVG) TS into a graph and combines it with a Graph Attention Network (GAT). By transforming TS into graphs, we are able to capture different structural aspects of the data that would otherwise remain hidden. By utilizing the representation learning capabilities of Graph Neural Networks, our method is able to effectively identify meaningful segments within the TS. To better understand the potential of our approach, we also experimented with different TS-to-graph transformations and compared their performance. Our contributions include: a) formulating the TSS as a node classification problem on graphs; b) conducting an extensive analysis of various TS- to-graph transformations applied to TSS using benchmark datasets from the TSSB repository; c) providing the first detailed study on utilizing GNNs for analyzing graph representations of TS in the context of TSS; d) demonstrating the effectiveness of our method, which achieves an average F1 score of 0.97 across 59 diverse TSS benchmark datasets; e) outperforming the seq2point baseline method by 0.05 in terms of F1 score; and f) reducing the required training data compared to the baseline methods.

DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity Recognition

Despite recognized limitations in modeling long-range temporal dependencies, Human Activity Recognition (HAR) has traditionally relied on a sliding window approach to segment labeled datasets. Deep learning models like the DeepConvLSTM typically classify each window independently, thereby restricting learnable temporal context to within-window information. To address this constraint, we propose DeepConvContext, a multi-scale time series classification framework for HAR. Drawing inspiration from the vision-based Temporal Action Localization community, DeepConvContext models both intra- and inter-window temporal patterns by processing sequences of time-ordered windows. Unlike recent HAR models that incorporate attention mechanisms, DeepConvContext relies solely on LSTMs -- with ablation studies demonstrating the superior performance of LSTMs over attention-based variants for modeling inertial sensor data. Across six widely-used HAR benchmarks, DeepConvContext achieves an average 10% improvement in F1-score over the classic DeepConvLSTM, with gains of up to 21%. Code to reproduce our experiments is publicly available via github.com/mariusbock/context_har.

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.