The paper introduces Higher-Order Modular Attention (HOMA), a new attention mechanism that combines standard pairwise self‑attention with an explicit triadic attention pathway. HOMA uses overlapping blocks, local windows, and a low‑rank projection to make triadic interactions tractable. Experiments on controlled PARITY and MATCH3 tasks, as well as TAPE benchmarks, show that HOMA matches or outperforms matched pairwise and purely triadic baselines, especially when dependencies extend beyond triadic order, and it often converges faster and uses parameters more efficiently.
arXiv:2505. 15548v2 Announce Type: replace Abstract: Autoregressive transformer language models frequently exhibit training instability when trained on long sequences, particularly under low-precision arithmetic.
The paper investigates how attention dynamics evolve across recurrent depth in language models, finding that attention support stabilizes early while hidden states and outputs take longer. It proposes WISE, a training‑free method that uses full attention in early steps and then reuses the discovered sparse working set for later steps, preserving performance on multi‑hop QA tasks. Experiments show that WISE maintains quality up to 2K context, offers measurable speedups, and highlights the importance of recurrent discovery of attention support.
InfoMamba is an attention‑free hybrid model that combines a minimal‑bandwidth global interface with a selective recurrent stream. The architecture replaces token‑level self‑attention with a concept bottleneck linear filtering layer and integrates it via an information‑maximizing fusion (IMF) that injects global context into the state‑space dynamics. Experiments across classification, dense prediction, and non‑vision tasks show that InfoMamba outperforms strong Transformer and SSM baselines while maintaining near‑linear scaling and competitive accuracy‑efficiency trade‑offs.
Switching Linear Attention (SwiLA) is a new sequence layer that improves upon standard softmax attention by maintaining a fixed-size recurrent state while enhancing representational capacity. It derives its recurrence from a test-time regression framework, using online expectation-maximization in a mixture of linear regressions model. In various benchmarks—including associative recall, in-context language learning, and language modeling—SwiLA achieves strong performance, narrowing the gap to softmax attention and even surpassing it in some settings.
arXiv:2509. 07963v2 Announce Type: replace Abstract: The core component of attention is the scoring function, which transforms the inputs into low-dimensional queries and keys and takes the dot product of each pair.
arXiv:2608. 15459v1 Announce Type: cross Abstract: Attention mechanisms have driven machine learning for a decade, from neural machine translation to language models that do general-purpose reasoning.
RAVE (Re-Allocating Visual Attention) is a lightweight pair‑gating mechanism that adds a learned query‑key bias to pre‑softmax attention scores over visual keys, derived from pre‑RoPE query and key features. It requires no architectural changes to the backbone and can be trained end‑to‑end with the rest of the model. Across multiple multimodal benchmarks, RAVE improves standard attention by an average of 3 points, especially on perception‑intensive tasks such as multilingual OCR, chart understanding, document VQA, and scene text VQA.
arXiv:2609.08615v1 Announce Type: new Abstract: Dimensional attention in learning is often implemented as a globally shared attention vector, where each stimulus dimension corresponds to a single sca...
arXiv:2607. 23634v1 Announce Type: cross Abstract: Attention enables context modeling via query-key scoring with softmax normalization.
arXiv:2601. 11667v2 Announce Type: replace-cross Abstract: Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment.
arXiv:2609.36529v1 Announce Type: new Abstract: Recurrent neural networks (RNNs) compress the historical context into a memory state of fixed size, thus allowing for constant-time inference. The memo...
arXiv:2606. 06249v1 Announce Type: cross Abstract: Transformer-based multimodal models rely on attention mechanisms to integrate information across heterogeneous modalities.