Clustering algorithms are fundamental tools across many fields, with density-based methods offering particular advantages in identifying arbitrarily shaped clusters and handling noise. However, their effectiveness is often limited by the requirement of critical parameter tuning by users, which typically requires significant domain expertise. This paper introduces a novel density-based clustering algorithm loosely inspired by the concept of selective attention, designed to minimize reliance on parameter tuning for most applications. The proposed method computes an adaptive threshold to exclude sparsely distributed points and outliers, constructs an initial cluster framework, and subsequently reintegrates the filtered points to refine the final results. Extensive experiments on diverse benchmark datasets demonstrate the robustness, accuracy, and ease of use of the proposed approach, establishing it as a powerful alternative to conventional density-based clustering techniques.

We propose an approach which exploits object features in addition to scene features for vision-and-language navigation (VLN). This domain gap is also present during pretraining. We propose a new model with better vision-and-language navigation performance in indoor environments. We report the mean and standard error for each metric. SPL by 1% which is consistent with the reported results in the main draft.

In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression, selective) attention across layers, rather than using fixed patterns, enables more effective propagation of long-range dependencies and substantially boosts performance on long-sequence tasks. Meanwhile, we further refine NSA's branches with Latent Attention that the sliding-window branch is enhanced with Multi-head Latent Attention (MLA) while compression and selective branches adopt Group-head Latent Attention (GLA). These changes reduce KV-cache memory by 50\% versus NSA while improving the model's common-sense reasoning and long-text understanding capabilities. Experiments on models from 340M to 1.3B parameters (trained on 15B and 100B tokens) show our method matches or exceeds full attention and native sparse attention in both common-sense reasoning and long-context understanding tasks.

The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query.

The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query. While self-attention has enjoyed major success, it notably treats all queries q in the same way by applying the mapping V \top\text{softmax}(Kq), where V,K are the value and key embeddings respectively. In this work, we argue that this uniform treatment hinders the ability to control contextual sparsity and relevance. As a solution, we introduce the Selective Self-Attention (SSA) layer that augments the softmax nonlinearity with a principled temperature scaling strategy. Through theory and experiments, we demonstrate that this alleviates attention dilution, aids the optimization process, and enhances the model's ability to control softmax spikiness of individual queries.

Training of deep reinforcement learning agents is slowed considerably by the presence of input dimensions that do not usefully condition the reward function. Existing modules such as layer normalization can be trained with weight decay to act as a form of selective attention, i.e. an input mask, that shrinks the scale of unnecessary inputs, which in turn accelerates training of the policy. However, we find a surprising result that adding numerous parameters to the computation of the input mask results in much faster training. A simple, high dimensional masking module is compared with layer normalization and a model without any input suppression. The high dimensional mask resulted in a four-fold speedup in training over the null hypothesis and a two-fold speedup in training over the layer normalization method.

The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query. While self-attention has enjoyed major success, it notably treats all queries $q$ in the same way by applying the mapping $V^\top\text{softmax}(Kq)$, where $V,K$ are the value and key embeddings respectively. In this work, we argue that this uniform treatment hinders the ability to control contextual sparsity and relevance. As a solution, we introduce the $\textit{Selective Self-Attention}$ (SSA) layer that augments the softmax nonlinearity with a principled temperature scaling strategy. By controlling temperature, SSA adapts the contextual sparsity of the attention map to the query embedding and its position in the context window. Through theory and experiments, we demonstrate that this alleviates attention dilution, aids the optimization process, and enhances the model's ability to control softmax spikiness of individual queries. We also incorporate temperature scaling for value embeddings and show that it boosts the model's ability to suppress irrelevant/noisy tokens. Notably, SSA is a lightweight method which introduces less than 0.5% new parameters through a weight-sharing strategy and can be fine-tuned on existing LLMs. Extensive empirical evaluations demonstrate that SSA-equipped models achieve a noticeable and consistent accuracy improvement on language modeling benchmarks.

The paper presents a novel method for predicting gene regulation by LSTM with an attention mechanism. The model consists of two levels, where the first level is applied on bins for each histone modifications (HM) and the second level is applied to multiple HMs. Attention mechanism is used in each level to focus on the important parts of the bins and HMs. In the experiments, the proposed method improves AUC scores over baseline models including CNN, LSTM, and CNN with an attention mechanism. This is an interesting paper which shows that LSTM with an attention mechanism can predict gene regulation.

We introduce Selective Attention, a simple parameter-free change to the standard attention mechanism which reduces attention to unneeded elements. Selective attention improves language modeling performance in a variety of model sizes and context lengths. For example, a range of transformers trained with the language modeling objective on C4 with selective attention perform equivalently to standard transformers with 2X more heads and parameters in their attention modules. Selective attention also allows decreasing the size of the attention's context buffer, leading to meaningful reductions in the memory and compute requirements during inference. For example, transformers with 100M parameters trained on C4 with context sizes of 512, 1,024, and 2,048 need 16X, 25X, and 47X less memory for their attention module, respectively, when equipped with selective attention, as those without selective attention, with the same validation perplexity. Different tasks have different memory requirements. On one extreme, copying an arbitrary sequence requires retaining all sequence elements in memory. On the other extreme, determining whether a specific element appeared at least once, only requires persisting a constant amount of memory. Transformers (Vaswani et al., 2017) keep the entire history in their context buffers, allowing them to solve tasks such as copying, while famously leading to their squared attention cost. RNNs (Rumelhart et al., 1986) and their modern structured state space variants (Gu et al., 2022; Gu & Dao, 2024) keep only a constant-sized sketch of the history, making inference cost linear, but rendering them incapable of solving tasks such as arbitrary string copying.