Papers with generation speed

9 papers
A Study of Non-autoregressive Model for Sequence Generation (2020.acl-main)

Copied to clipboard

Challenge: Non-autoregressive (NAR) models generate all tokens in parallel, resulting in faster generation speed compared to autoregressive models.
Approach: They propose to use knowledge distillation and source-target alignment to bridge the gap between NAR and autoregressive models in various tasks.
Outcome: The proposed techniques can speed up NAR models in some tasks but not all . the proposed techniques reduce target token dependency while allowing for faster inference .
WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching (2025.naacl-long)

Copied to clipboard

Challenge: Flow matching is a robust and stable approach to training diffusion models, but it can result in subpar audio quality.
Approach: They propose a reparameterized flow matching model for mel-spectrogram conditioned speech synthesis that uses a mel prior instead of a standard Gaussian prior to minimize unnecessary transportation costs.
Outcome: The proposed model improves sample quality and generation speed for speech vocoders while reducing transportation costs.
Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion (2024.emnlp-main)

Copied to clipboard

Challenge: Existing mechanisms compromise ownership rights or raise data privacy concerns . existing mechanisms compromise security of released large language models .
Approach: They propose a TaylorMLP to preserve the ownership of large language models by transforming the weights of LLMs into Taylor-series parameters instead of releasing original weights .
Outcome: The proposed model preserves ownership of large language models and prevents their abuse by adjusting the generation speed and causing low-speed token generation.
Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs (2024.lrec-main)

Copied to clipboard

Challenge: Large language models have demonstrated exceptional capability in natural language understanding and generation, but their generation speed is limited by the inherently sequential nature of their decoding process.
Approach: They propose a method that accelerates decoding process without sacrificing quality . they propose lexical unit decoding, which can be integrated with other methods .
Outcome: The proposed method significantly reduces decoding time while maintaining quality while maintaining output quality.
DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off (2025.emnlp-main)

Copied to clipboard

Challenge: et al., 2019; Brown e.t al, 2023; Touvron e t al; 2024; OpenAI, 2024) Large Language Models (LLMs) have demonstrated remarkable capabilities in knowledge encoding and contextual understanding during their pretraining phase.
Approach: They propose a dynamic expert scheduling mechanism that allocates computational resources based on text complexity and a hierarchical sparse attention mechanism that adjusts attention patterns according to a variety of input lengths.
Outcome: The proposed framework overpowers existing methods on long-text generation benchmarks.
Revisiting Over-Smoothness in Text to Speech (2022.acl-long)

Copied to clipboard

Challenge: Non-autoregressive text to speech models ignore correlation in time and frequency domains, causing blurry results.
Approach: They revisit the problem of over-smoothness in non-autoregressive text to speech models . they use methods that reduce complexity of data distributions and improve modeling methods .
Outcome: The proposed models achieve better voice quality and faster inference speed than autoregressive models.
Few-shot Temporal Pruning Accelerates Diffusion Models for Text Generation (2024.lrec-main)

Copied to clipboard

Challenge: Existing acceleration methods for text generation ignore the importance of the distribution of sampling steps, resulting in slow sampling rates.
Approach: They propose a technique to accelerate diffusion models for text generation without additional training by using a Bayesian optimization approach.
Outcome: The proposed technique achieves 400x acceleration even with minimal sampling steps after down to less than 1 minute of optimization yielding a competitive performance even with minimum sampling steps.
Accelerating Multilingual Language Model for Excessively Tokenized Languages (2024.findings-acl)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have shown a significant degree of multilingual proficiency on a variety of tasks in multiple languages.
Approach: They propose a framework to fine-tune a language model head and fine-track it while preserving its performance.
Outcome: The proposed framework increases the generation speed by 1.7 while maintaining the performance of pre-trained multilingual models on target monolingual tasks.
Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance (2025.emnlp-main)

Copied to clipboard

Challenge: Visual Language Models (VLMs) have significant parameter size and autoregressive (AR) decoding nature impose considerable computational demands on VLA models.
Approach: They propose a framework to relax acceptance utilizing the relative distances represented by the action tokens of the VLA model.
Outcome: Empirical results show that the proposed framework improves the speed of the prediction task by 44%.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations