ODE-Based Transformer Decoders for Iterative Sign Language Translation

• URL: http://arxiv.org/abs/2608.11352v1
• Date: Tue, 11 Aug 2026 18:58:18 GMT
• Title: ODE-Based Transformer Decoders for Iterative Sign Language Translation
• Abstract summary: Sign language translation has achieved strong results with Transformer architectures.<n>Recent improvements largely rely on scaling model capacity at the cost of increased computation.<n>We propose a parameter-efficient alternative that improves without increasing model size.
• Score: 1.054735384167421
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Sign language translation has achieved strong results with Transformer architectures, yet recent improvements largely rely on scaling model capacity at the cost of increased computation. We propose a parameter-efficient alternative that improves expressiveness without increasing model size. Rather than scaling capacity, we focus on enhancing the update dynamics of iterative refinement decoders, where each refinement step corresponds to one internal decoder iteration that progressively improves the latent representation before translation generation. We reinterpret residual refinement updates from an Ordinary Differential Equation (ODE) perspective and replace them with higher-order numerical integration schemes, namely Runge--Kutta methods (RK-2 and RK-4). These methods perform multiple function evaluations within each refinement step to produce more accurate and stable representation updates without adding decoder parameters. To the best of our knowledge, this is the first application of ODE-inspired update dynamics to sign language translation. RK-2 achieves 22.96 BLEU-4 on the PHOENIX-2014-T test set and 19.34 BLEU-4 on the CSL-Daily test set, outperforming the IPSLT baseline on both benchmarks, with fewer decoder layers and refinement iterations on CSL-Daily. These results suggest that stronger refinement dynamics can improve translation performance under parameter-efficient decoder designs, providing a complementary alternative to conventional model scaling.

Related papers

• Sequence Repetition Enhances Token Embeddings and Improves Sequence Labeling with Decoder-only Language Models [2.91425891370655]
  Sequence repetition (SR) is a less invasive alternative for enabling bidirectionality in decoder-only models.<n>We show that SR inherently makes decoders bidirectional, improving the quality of token-level embeddings and surpassing encoders and unmasked decoders.<n>Our findings underscore that SR alleviates the structural limitations of decoders, enabling more efficient and adaptable LMs and broadening their applicability to other token-level tasks.
  arXiv  Detail & Related papers  (2026-01-24T20:49:13Z)
• Continuous Autoregressive Language Models [56.49239051750678]
  We introduce Continuous Autoregressive Language Models (CALM)<n>CALM uses a high-fidelity autoencoder to compress a chunk of K tokens into a single continuous vector.<n>We develop a comprehensive likelihood-free framework that enables robust training, evaluation, and controllable sampling.
  arXiv  Detail & Related papers  (2025-10-31T17:58:11Z)
• Latent Thought Models with Variational Bayes Inference-Time Computation [52.63299874322121]
  Latent Thought Models (LTMs) incorporate explicit latent thought vectors that follow an explicit prior model in latent space.<n>LTMs demonstrate superior sample and parameter efficiency compared to autoregressive models and discrete diffusion models.
  arXiv  Detail & Related papers  (2025-02-03T17:50:34Z)
• Byte Latent Transformer: Patches Scale Better Than Tokens [101.10994909832063]
  Byte Latent Transformer (BLT) encodes bytes into dynamically sized patches, which serve as the primary units of computation.<n>For fixed inference costs, BLT shows significantly better scaling than tokenization-based models, by simultaneously growing both patch and model size.
  arXiv  Detail & Related papers  (2024-12-13T05:33:32Z)
• Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning [73.73967342609603]
  We introduce a predictor-corrector learning framework to minimize truncation errors. We also propose an exponential moving average-based coefficient learning method to strengthen our higher-order predictor. Our model surpasses a robust 3.8B DeepNet by an average of 2.9 SacreBLEU, using only 1/3 parameters.
  arXiv  Detail & Related papers  (2024-11-05T12:26:25Z)
• ReTok: Replacing Tokenizer to Enhance Representation Efficiency in Large Language Model [9.1108256816605]
  We propose a method to improve model representation and processing efficiency by replacing the tokenizers of large language models (LLMs) Our method can maintain the performance of the model after replacing the tokenizer, while significantly improving the decoding speed for long texts.
  arXiv  Detail & Related papers  (2024-10-06T03:01:07Z)
• Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT [120.39362661689333]
  We present an improved version of Lumina-T2X, showcasing stronger generation performance with increased training and inference efficiency. Thanks to these improvements, Lumina-Next not only improves the quality and efficiency of basic text-to-image generation but also demonstrates superior resolution extrapolation capabilities.
  arXiv  Detail & Related papers  (2024-06-05T17:53:26Z)
• Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all Tokens [15.566726645722657]
  We propose a novel framework specifically designed for speculative sampling. Within this framework, we introduce a lightweight draft model that effectively utilizes previously generated tokens to predict subsequent words. We demonstrate impressive results, achieving an average latency speedup ratio of 2.7x compared to the vanilla auto-regressive decoding approach.
  arXiv  Detail & Related papers  (2024-02-24T08:10:39Z)
• Bayesian Prompt Learning for Image-Language Model Generalization [64.50204877434878]
  We use the regularization ability of Bayesian methods to frame prompt learning as a variational inference problem. Our approach regularizes the prompt space, reduces overfitting to the seen prompts and improves the prompt generalization on unseen prompts. We demonstrate empirically on 15 benchmarks that Bayesian prompt learning provides an appropriate coverage of the prompt space.
  arXiv  Detail & Related papers  (2022-10-05T17:05:56Z)
• E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation [95.49128988683191]
  Sequence-to-sequence (seq2seq) learning is a popular fashion for large-scale pretraining language models. We propose an encoding-enhanced seq2seq pretraining strategy, namely E2S2. E2S2 improves the seq2seq models via integrating more efficient self-supervised information into the encoders.
  arXiv  Detail & Related papers  (2022-05-30T08:25:36Z)
• Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer [2.952085248753861]
  A transformer-decoder decoder is employed to replace RNN-based ones. Experiments demonstrate that our model improves the ExpRate of current state-of-the-art methods on CROHME 2014 by 2.23%.
  arXiv  Detail & Related papers  (2021-05-06T03:11:54Z)
• On the Encoder-Decoder Incompatibility in Variational Text Modeling and Beyond [82.18770740564642]
  Variational autoencoders (VAEs) combine latent variables with amortized variational inference. We observe the encoder-decoder incompatibility that leads to poor parameterizations of the data manifold. We propose Coupled-VAE, which couples a VAE model with a deterministic autoencoder with the same structure.
  arXiv  Detail & Related papers  (2020-04-20T10:34:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.