Self-attention selects information freely across the sequence, but across depth Transformers merely add each layer’s output to the residual stream, so later layers cannot selectively reuse earlier-layer representations. Recent cross-layer methods improve this flow but operate on hidden states outside attention, adding state beyond the key-value cache at inference—a cost that becomes increasingly salient as modern LLMs compress the cache with grouped-query and multi-head latent attention. We introduce Depth-Attention, which performs this selection inside the attention module itself: before a layer attends over the sequence, its query attends along depth over the keys of earlier layers at the same position and mixes their values into the value that self-attention then reads. Because Depth-Attention reuses the standard attention queries, keys, and value-cache slots, storing depth-mixed values in place of the original values, it adds no parameters and introduces no persistent inference state beyond the standard key-value cache—the same cache size as a vanilla decoder and less than hidden-state-based cross-layer methods. On Qwen3-style decoders at 1.5B and 3B parameters, Depth-Attention attains the lowest perplexity and the highest average downstream accuracy, improving over the vanilla Transformer by up to 2.3 accuracy points and surpassing strong cross-layer baselines (mHC, Attention Residuals, DenseFormer) in perplexity and average accuracy, while adding under 0.01% extra arithmetic FLOPs and no additional persistent inference state. The gains hold from 360M to 3B parameters and extend to looped Transformers.

Video-to-speech (V2S) synthesis, the task of generating speech directly from silent video input, is inherently more challenging than other speech synthesis tasks due to the need to accurately reconstruct both speech content and speaker characteristics from visual cues alone. Recently, audio-visual pretraining has eliminated the need for additional acoustic hints in V2S, which previous methods often relied on to ensure training convergence. However, even with pretraining, existing methods continue to face challenges in achieving a balance between acoustic intelligibility and the preservation of speaker-specific characteristics. We analyzed this limitation and were motivated to introduce DiVISe (Direct Vsual-Input Speech Synthesis), an end-to-end V2S model that predicts Mel-spectrograms directly from video frames alone. Despite not taking any acoustic hints, DiVISe effectively preserves speaker characteristics in the generated audio, and achieves superior performance on both objective and subjective metrics across the LRS2 and LRS3 datasets. Our results demonstrate that DiVISe not only outperforms existing V2S models in acoustic intelligibility but also scales more effectively with increased data and model parameters. Code and weights will be made publicly available after acceptance of this paper.