AI Weekly: New Speech Tech & Smart Browsing Tools

BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding

arXiv:2508.18187v2 Announce Type: replace-cross Abstract: Memory decay makes it harder for the human brain to recognize visual objects and retain details. Consequently, recorded brain signals become weaker, uncertain, and contain poor visual context over time. This paper presents one of the first vision-learning approaches to address this problem. First, we statistically and experimentally demonstrate the existence of inconsistency in brain signals and its impact on the Vision-Brain Understanding (VBU) model. Our findings show that brain signal representations shift over recording sessions, leading to compounding bias, which poses challenges for model learning and degrades performance. Then, we propose a new Bias-Mitigation Continual Learning (BRAIN) approach to address these limitations. In this approach, the model is trained in a continual learning setup and mitigates the growing bias from each learning step. A new loss function named De-bias Contrastive Learning is also introduced to address the bias problem. In addition, to prevent catastrophic forgetting, where the model loses knowledge from previous sessions, the new Angular-based Forgetting Mitigation approach is introduced to preserve learned knowledge in the model. Finally, the empirical experiments demonstrate that our approach achieves State-of-the-Art (SOTA) performance across various benchmarks, surpassing prior and non-continual learning methods.

WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models

arXiv:2604.08558v1 Announce Type: cross Abstract: Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention. In this paper, we propose WAND, Windowed Attention and Knowledge Distillation, a framework that adapts pretrained AR-TTS models to operate with constant computational and memory complexity. WAND separates the attention mechanism into two: persistent global attention over conditioning tokens and local sliding-window attention over generated tokens. To stabilize fine-tuning, we employ a curriculum learning strategy that progressively tightens the attention window. We further utilize knowledge distillation from a full-attention teacher to recover high-fidelity synthesis quality with high data efficiency. Evaluated on three modern AR-TTS models, WAND preserves the original quality while achieving up to 66.2% KV cache memory reduction and length-invariant, near-constant per-step latency.

Turn your best AI prompts into one-click tools in Chrome

<img src="https://storage.googleapis.com/gweb-uniblog-publish-prod/images/GoogleChrome_RR_Skills_KeywordH.max-600x600.format-webp.webp">Skills in Chrome let you discover, save and remix AI workflows — and repeat them instantly.

Meet HoloTab by HCompany. Your AI browser companion.

Gemini 3.1 Flash TTS: the next generation of expressive AI speech

<img src="https://storage.googleapis.com/gweb-uniblog-publish-prod/images/gemini-3.1-flash-tts_blog_keywo.max-600x600.format-webp.webp">Gemini 3.1 Flash TTS is now available across Google products.