SSM
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
HoT-SSM:Higher-order Temporal Knowledge Graph Reasoning with State Space Models for Health Care
Announce Type: new Abstract: Medical knowledge graphs (MKGs) infused with clinical knowledge have been increasingly used to model electronic health records (EHRs) to support interpretable predictions in healthcare domain. However, existing MKG-based approaches are limited in capturing pairwise relations between clinical concepts (e.g., conditions, procedures, and medications), and restricts their ability to model higher-order interactions among co-occurring or semantically related concepts....
Reinterpreting Safety Thresholds as Neuron Spiking Thresholds
arXiv:2605.30368v1 Announce Type: new Abstract: Surrogate Safety Measures (SSMs) are extensively utilised in the evaluation of traffic risk in automated driving contexts. However, the majority of SSM-based evaluations employ fixed thresholds that fail to capture the human response to sustained borderline conditions or the reaction to brief, high-risk peaks. The present work proposes a biologically inspired reinterpretation of SSM thresholds.
Forget Attention: Importance-Aware Attention Is All You Need
Announce Type: new Abstract: Combining attention's global retrieval with the sequential importance signal of state space models (SSMs) is the open challenge of hybrid language modeling. Transformers see everywhere but cannot prioritize; SSMs know what matters but cannot revisit. Existing hybrids -- Jamba (block level) and Hymba (head level) -- place the two in separate compartments, so neither informs the other during the attention computation itself.
Forget Attention: Importance-Aware Attention Is All You Need
arXiv:2606.02332v2 Announce Type: replace Abstract: Combining attention's global retrieval with the sequential importance signal of state space models (SSMs) is the open challenge of hybrid language modeling. Transformers see everywhere but cannot prioritize; SSMs know what matters but cannot revisit.
Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models
arXiv:2606.04672v1 Announce Type: new Abstract: Continuous-time dynamic graphs (CTDGs) provide a richer framework to capture fine-grained temporal patterns in evolving relational data. Long-range information propagation is a key challenge while learning representations, wherein it is important to retain and update information over long temporal horizons. Existing approaches restrict models to capture one-hop or local temporal neighborhoods and fail to capture multi-hop or global structural...
Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models
arXiv:2606.04672v2 Announce Type: replace Abstract: Continuous-time dynamic graphs (CTDGs) provide a richer framework to capture fine-grained temporal patterns in evolving relational data. Long-range information propagation is a key challenge while learning representations, wherein it is important to retain and update information over long temporal horizons. Existing approaches restrict models to capture one-hop or local temporal neighborhoods and fail to capture multi-hop or global...
COVID-era assistance policies may have reduced food insecurity, housing instability
COVID-era assistance policies may have reduced food insecurity, housing instability Lisa Lock Scientific Editor Andrew Zinin Lead Editor In 2018, Caitlin Caspi started a five-year research project looking at how raising the minimum wage could impact nutrition-related health outcomes. Caspi is an associate professor of allied health sciences in the College of Agriculture, Health and Natural Resources (CAHNR), associate director of InCHIP, and the director of food security initiatives for the...
Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference
arXiv:2605.26099v3 Announce Type: replace Abstract: Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context length. To handle this, we study a sleep-like consolidation mechanism in which a model periodically converts recent context into persistent fast weights before clearing its key-value cache. During sleep, the model performs $N$ offline recurrent passes over the accumulated context and updates the...
Generalizing Geometry-Guided Mamba as a Plug-and-Play Context Module for CNN-based Semantic Segmentation
arXiv:2606.08866v1 Announce Type: new Abstract: CNN-based semantic segmentation networks usually rely on context heads such as ASPP, PPM, or attention modules to enlarge the receptive field. These heads are effective but may introduce heavy computation, memory cost, or boundary leakage. This paper revisits Directional Geometric Mamba (G-Mamba) from DGM-Net and studies it as a plug-and-play context aggregation module rather than a complete new segmentation architecture.
A Held-Out Transition-Pair Falsifier for Long-Horizon Non-Abelian State Tracking
Announce Type: new Abstract: State tracking exposes a sharp limitation of sequence models: the relevant signal is often not a summary of observed tokens, but an ordered latent state that evolves through non-commutative transformations. We introduce a held-out transition-pair falsifier for finite non-Abelian group tracking. The protocol forbids selected ordered generator pairs during training and requires the same local patterns during evaluation, blocking one direct local-transition...