20 results for “sequence modeling”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper compares three subquadratic architectures (xLSTM, Mamba-2, and Gated DeltaNet) for sequence modeling and finds that xLSTM performs the best on complex tasks.
Yangtian Zhang, Zhe Wang, Arthur Gretton, Rex Ying +3 more
The paper introduces the Insertion Process (IP), a novel stochastic generative model that learns variable-length, non-monotonic sequence generation by explicitly modeling the insertion order of tokens…
Zhichen Tang, Zhengzheng Dang, Yulin Chen, Jixin Wu +2 more
EvoMD-LLM introduces a novel framework that models reactive molecular dynamics as a symbolic temporal language problem, enabling LLMs to accurately predict complex, time-evolving chemical processes.
Keyue Qiu, Yixin Wu, Lihao Wang, Yawen Ouyang +18 more
The paper introduces AMix-2, a novel protein-text foundation model that unifies protein understanding and sequence design by embedding both modalities in a shared token space, achieving state-of-the-a…
This paper presents an efficient algorithm for right-to-left sequence prediction based on a new complexity measure called arithmetic repetition complexity, and demonstrates its application to predicti…
The paper introduces BlockGen, a blockwise sequence model, to investigate the performance of uniform-state versus masked diffusion models when generating sequences block-by-block, showing that the per…
The paper argues that large language models (LLMs) are a special case of world models and proposes a continuous spectrum between token prediction and latent-space architectures.
This paper presents an improved parallel version of MaxFEM algorithm for maximal frequent episode mining, achieving up to 8x speedup in C++ implementation and 35x improvement overall.
This paper proposes Chained Recursive Language Models (Chained RLM), an inference-time architecture for managing context in large language models, allowing for intermediate artifacts to be inspected,…
The paper introduces QuITE, a plug-and-play embedding module that uses learnable query tokens to effectively embed irregular multivariate time series data into latent representations compatible with e…
This paper investigates the performance of Generative Spoken Language Modeling (GSLM) on speech synthesis and continuation using discrete speech representations with varying bitrates.
This paper proposes a method for hierarchically parsing long-form audio data into order-consistent Act-Sub-Event parse trees using Hierarchical Activity Grammar.
The paper applies network science to demonstrate the feasibility of unsupervised dependency parsing in non-human primates due to their sequence length distribution.
The paper proposes Large Language Gibbs, a scheme for structured probabilistic inference using conditional distributions of large language models as transition operators.