Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction

Hyperspectral image classification is challenged by high spectral dimensionality, complex spectral-spatial correlations, and limited training samples with severe class imbalance. Traditional CNNs excel at local feature extraction, while transformers capture long-range dependencies. However, their isolated use results in suboptimal outcomes due to quadratic complexity and insufficient inductive biases. CLAReSNet, a hybrid architecture, integrates multi-scale convolutional extraction with transformer-style attention through an adaptive latent bottleneck, enhancing classification performance.

The paper titled 'Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning' introduces a new method called Bias-REstrained Prefix Representation FineTuning (BREP ReFT). This approach aims to enhance the mathematical reasoning capabilities of models by addressing the limitations of existing Representation finetuning (ReFT) methods, which struggle with mathematical tasks. The study demonstrates that BREP ReFT outperforms both standard ReFT and weight-based Parameter-Efficient finetuning (PEFT) methods through extensive experiments.

The study investigates the ability of transformer models to predict long steps in the Collatz sequence, a complex arithmetic function that maps odd integers to their successors. The accuracy of the models varies significantly depending on the base used for encoding, achieving up to 99.7% accuracy for bases 24 and 32, while dropping to 37% and 25% for bases 11 and 3. Despite these variations, all models exhibit a common learning pattern, accurately predicting inputs with similar residuals modulo 2^p.

The paper titled 'Multistability of Self-Attention Dynamics in Transformers' explores a continuous-time multiagent model of self-attention mechanisms in transformers. It establishes a connection between self-attention dynamics and a multiagent version of the Oja flow, which computes the principal eigenvector of a matrix related to the value matrix in transformers. The study classifies the equilibria of the single-head self-attention system into four categories: consensus, bipartite consensus, clustering, and polygonal equilibria, noting that multiple stable equilibria can coexist.

Higher-order Neural Additive Models (HONAMs) have been introduced as an advancement over Neural Additive Models (NAMs), which are known for their predictive performance and interpretability. HONAMs address the limitation of NAMs by effectively capturing feature interactions of arbitrary orders, enhancing predictive accuracy while maintaining interpretability, crucial for high-stakes applications. The source code for HONAM is publicly available on GitHub.

Vision-Language Models (VLMs) are emerging models that integrate visual content with natural language. Current methods typically fuse data either early in the encoding process or late through pooled embeddings. This paper introduces a lightweight fusion module utilizing cross-only, bidirectional attention layers to align hidden states from both modalities, enhancing understanding while keeping encoders non-causal. The proposed method aims to improve the performance of VLMs by leveraging the inherent structure of visual and textual data.

RiverScope is a newly developed high-resolution dataset aimed at improving the monitoring of rivers and surface water dynamics, which are crucial for understanding Earth's climate system. The dataset includes 1,145 high-resolution images covering 2,577 square kilometers, with expert-labeled river and surface water masks. This initiative addresses the challenges of monitoring narrow or sediment-rich rivers that are often inadequately represented in low-resolution satellite data.