2025 "sequence modeling" Papers

22 papers found

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data

Tianyi Chen, Pengxiao Lin, Zhiwei Wang et al.

NeurIPS 2025spotlightarXiv:2509.17514

BlockScan: Detecting Anomalies in Blockchain Transactions

Jiahao Yu, Xian Wu, Hao Liu et al.

NeurIPS 2025posterarXiv:2410.04039
3
citations

Competition Dynamics Shape Algorithmic Phases of In-Context Learning

Core Francisco Park, Ekdeep Singh Lubana, Hidenori Tanaka

ICLR 2025posterarXiv:2412.01003
34
citations

Controllable Generation via Locally Constrained Resampling

Kareem Ahmed, Kai-Wei Chang, Guy Van den Broeck

ICLR 2025posterarXiv:2410.13111
9
citations

Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient

Wenlong Wang, Ivana Dusparic, Yucheng Shi et al.

ICLR 2025posterarXiv:2410.08893
3
citations

EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling

Jia-Hua Lee, Bor-Jiun Lin, Wei-Fang Sun et al.

NeurIPS 2025spotlightarXiv:2502.00466
2
citations

Enhancing the Maximum Effective Window for Long-Term Time Series Forecasting

Jiahui Zhang, Zhengyang Zhou, Wenjie Du et al.

NeurIPS 2025poster

Evolutionary Reasoning Does Not Arise in Standard Usage of Protein Language Models

Yasha Ektefaie, Andrew Shen, Lavik Jain et al.

NeurIPS 2025poster

Learning Video-Conditioned Policy on Unlabelled Data with Joint Embedding Predictive Transformer

Hao Luo, Zongqing Lu

ICLR 2025poster

Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory

Nikola Zubic, Federico Soldà, Aurelio Sulser et al.

ICLR 2025posterarXiv:2405.16674
17
citations

Neural Attention Search

Difan Deng, Marius Lindauer

NeurIPS 2025posterarXiv:2502.13251

Parallel Sequence Modeling via Generalized Spatial Propagation Network

Hongjun Wang, Wonmin Byeon, Jiarui Xu et al.

CVPR 2025posterarXiv:2501.12381
3
citations

Plug, Play, and Generalize: Length Extrapolation with Pointer-Augmented Neural Memory

Svetha Venkatesh, Kien Do, Hung Le et al.

ICLR 2025poster

Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling

Mónika Farsang, Radu Grosu

NeurIPS 2025posterarXiv:2505.21717
4
citations

SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling

Yizhao Gao, Zhichen Zeng, DaYou Du et al.

NeurIPS 2025poster

Selective induction Heads: How Transformers Select Causal Structures in Context

Francesco D'Angelo, francesco croce, Nicolas Flammarion

ICLR 2025posterarXiv:2509.08184
4
citations

State Space Models are Provably Comparable to Transformers in Dynamic Token Selection

Naoki Nishikawa, Taiji Suzuki

ICLR 2025posterarXiv:2405.19036
6
citations

Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models

Benjamin Walker, Lingyi Yang, Nicola Muca Cirone et al.

NeurIPS 2025spotlightarXiv:2505.17761
6
citations

Tensor Product Attention Is All You Need

Yifan Zhang, Yifeng Liu, Huizhuo Yuan et al.

NeurIPS 2025spotlightarXiv:2501.06425
33
citations

Unsupervised Meta-Learning via In-Context Learning

Anna Vettoruzzo, Lorenzo Braccaioli, Joaquin Vanschoren et al.

ICLR 2025posterarXiv:2405.16124
3
citations

What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains

Chanakya Ekbote, Ashok Vardhan Makkuva, Marco Bondaschi et al.

NeurIPS 2025spotlightarXiv:2508.07208

ZeroS: Zero‑Sum Linear Attention for Efficient Transformers

Jiecheng Lu, Xu Han, Yan Sun et al.

NeurIPS 2025spotlight