✨TiDAR: Think in Diffusion, Talk in Autoregression

📝 Summary:
TiDAR is a hybrid diffusion-autoregressive model achieving high throughput and AR-level quality. It drafts tokens with diffusion and samples autoregressively in a single pass, outperforming existing methods and delivering 4.71x to 5.91x faster generation.

🔹 Publication Date: Published on Nov 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.08923
• PDF: https://arxiv.org/pdf/2511.08923

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #MachineLearning #DiffusionModels #AutoregressiveModels #GenerativeAI

✨Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning

📝 Summary:
AR models face inefficient exploration and sparse rewards in RL. Internal RL uses a higher-order model to learn temporal abstraction controllers. This enables efficient learning from sparse rewards where standard RL fails.

🔹 Publication Date: Published on Dec 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.20605
• PDF: https://arxiv.org/pdf/2512.20605

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#ReinforcementLearning #HierarchicalRL #AutoregressiveModels #MachineLearning #ArtificialIntelligence

✨Efficient Autoregressive Video Diffusion with Dummy Head

📝 Summary:
Autoregressive video diffusion models underutilize historical frames. Dummy Forcing improves efficiency through heterogeneous memory allocation and dynamic head programming. This method achieves up to 2.0x speedup with less than 0.5% quality drop, enabling faster video generation.

🔹 Publication Date: Published on Jan 28

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.20499
• PDF: https://arxiv.org/pdf/2601.20499
• Project Page: https://csguoh.github.io/project/DummyForcing/
• Github: https://github.com/csguoh/DummyForcing

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VideoDiffusion #AutoregressiveModels #GenerativeAI #DeepLearning #AI

✨Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss

📝 Summary:
This study refines autoregressive image generation with diffusion loss, showing patch denoising effectively mitigates condition errors. A novel Optimal Transport based condition refinement method is introduced to ensure convergence to an ideal condition distribution, outperforming prior methods.

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.07022
• PDF: https://arxiv.org/pdf/2602.07022

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#ImageGeneration #DiffusionModels #AutoregressiveModels #OptimalTransport #MachineLearning

🔥 dots.tts Technical Report

💡 The paper presents dots.tts, a 2 billion parameter continuous autoregressive text-to-speech model that achieves state-of-the-art performance on multiple benchmarks. The model is trained on a large-scale multilingual corpus and enables efficient low-latency speech generation. The key innovations of the model are threefold. First, the authors train an AudioVAE with multiple objectives to build a semantically structured and prediction-friendly continuous speech space. Second, they use full-history conditioning in the flow-matching head to preserve long-range consistency and reduce drift during generation. Third, they apply reward-free self-corrective post-training to the flow-matching head to further improve robustness and acoustic quality.

The model is evaluated on several benchmarks, including Seed-TTS-Eval, where it achieves the best average performance with word error rates of 0.94, 1.30, and 6.60 percent and similarity scores of 81.0, 77.1, and 79.5 on the Chinese, English, and Chinese hard test sets, respectively. The model also demonstrates strong generation stability, voice cloning ability, and emotional expressiveness on other benchmarks.

To enable efficient inference, the authors apply CFG-aware MeanFlow distillation, which allows for low-latency speech generation with first-packet latencies of 85 and 54 milliseconds in output streaming and dual-streaming modes, respectively. The training and inference code, as well as the pre-trained, post-trained, and MeanFlow-distilled checkpoints, are released under the Apache 2.0 license to facilitate reproducible research and practical deployment.

Overall, the paper presents a significant contribution to the field of text-to-speech synthesis, achieving state-of-the-art performance and enabling efficient low-latency speech generation. The model's ability to generate high-quality speech with strong generation stability, voice cloning ability, and emotional expressiveness makes it a valuable tool for a wide range of applications.

📅 Published on Jun 5

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.07080
• PDF: https://arxiv.org/pdf/2606.07080

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#TextToSpeechSynthesis #AutoregressiveModels #MultilingualSpeechGeneration #LowLatencySpeechSystems #ContinuousSpeechModeling