NLP Wiki

User Tools

Site Tools

Trace: • state-space_models • patent_domain_nlp • writing_assistants • zero-shot_learning • gpu_deep_learning • miscellaneous_neural_networks • morphological_analysis • grammatical_error_correction • distribution_shift • nlp_for_social_good
nlp:seq2seq

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
nlp:seq2seq [2025/05/29 07:14] – [Decoding Strategies] jmflanignlp:seq2seq [2025/05/29 07:15] (current) – [Decoding Strategies] jmflanig
Line 28: Line 28:
     * [[https://arxiv.org/pdf/2404.11912|Sun et al 2024 - TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding]]     * [[https://arxiv.org/pdf/2404.11912|Sun et al 2024 - TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding]]
     * [[https://arxiv.org/pdf/2502.17421|Yang et al 2025 - LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification]]     * [[https://arxiv.org/pdf/2502.17421|Yang et al 2025 - LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification]]
 +    * [[https://arxiv.org/pdf/2505.20776|Cha et al 2025 - SpecExtend: A Drop-in Enhancement for Speculative Decoding of Long Sequences]]
   * **Miscellaneous Decoding Techniques**   * **Miscellaneous Decoding Techniques**
     * Contrastive Decoding     * Contrastive Decoding
nlp/seq2seq.1748502883.txt.gz · Last modified: 2025/05/29 07:14 by jmflanig
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki