The paper investigates how attention dynamics evolve across recurrent depth in language models, finding that attention support stabilizes early while hidden states and outputs take longer. It proposes WISE, a training‑free method that uses full attention in early steps and then reuses the discovered sparse working set for later steps, preserving performance on multi‑hop QA tasks. Experiments show that WISE maintains quality up to 2K context, offers measurable speedups, and highlights the importance of recurrent discovery of attention support.
By Ke Wan, Chen Chen
arXiv:2606. 17417v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) achieve strong performance on a variety of audio understanding tasks but continue to struggle with temporal reasoning, a fundamental capability central to human auditory perception.
By Apoorva Kulkarni, Kaousheik Jayakumar, Sreyan Ghosh, Sarah Wiegreffe, Dinesh Manocha, Ramani Duraiswami
The study applies causal tracing to large audio language models (LALMs) to uncover how they fuse acoustic and textual information. Layer‑wise analysis reveals distinct fusion strategies—progressive integration in DeSTA versus abrupt late‑stage fusion in Qwen—while token‑wise analysis identifies the final sequence token as an informational bottleneck that decisively retrieves audio content. Additionally, an attention‑like query mechanism at intermediate tokens is observed, prompting the model to pull task‑relevant audio context.
By Wei-Chih Chen, Chien-yu Huang, Hung-yi Lee
arXiv:2608. 08569v1 Announce Type: new Abstract: Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks.
By Wenxu Jia, Dongjie Fu, Xize Cheng, Fangming Feng, Linjun Li, Wenshi Chen, Yingming Li, Zhou Zhao, Tao Jin
Encore is a new framework for generating long, synchronized audio‑video content. It splits the problem into local continuity, handled by iterative chunk‑wise synthesis with cross‑chunk context, and global consistency, enforced through reference audio‑video signals with shifted position embeddings. The Adaptive Signal Routing mechanism learns attention biases and residual scales to modulate the influence of each conditioning signal, enabling end‑to‑end joint audio‑video generation and infinite‑length inference.
By Shaohua Pan, Junbao Chen, Shengyi He, Jingfeng Xue, Wen Tao, Haocheng Feng, Siming Fan, Dongwei Pan, Yi Yang, Wei He, Hang Zhou
arXiv:2608. 13817v1 Announce Type: cross Abstract: Human speech production is constrained by physiology, giving rise to characteristic temporal structure on acoustic signals.
By Tom\'as Andrade Weber
arXiv:2604. 08558v2 Announce Type: replace-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.
By Hanna Lee, Tan Dat Nguyen, Jaehoon Kang, Kyuhong Shim
arXiv:2606. 15186v1 Announce Type: cross Abstract: Text-to-audio (TTA) generation has made significant strides, yet achieving precise and consistent audio editing remains a major challenge.
By Yuxuan Jiang, Mingyang Han, Yusheng Dai, Andong Wang, Tianhong Zhou, Jiaxin Ye, Dongxiao Wang, Haoxiang Shi, Boyu Li, Jun Song, Cheng Yu, Bo Zheng, Weibei Dou, Zehua Chen, Jun Zhu
arXiv:2603. 01006v3 Announce Type: replace-cross Abstract: REPresentation Alignment (REPA) improves the training of generative flow models by aligning intermediate hidden states with pretrained teacher features, but its effectiveness in token-conditioned audio Flow Matching critically depends on the choice of supervised layers, which is typically made heuristically based on the depth.
By Pengfei Zhang, Tianxin Xie, Minghao Yang, Li Liu
Recent Large Audio Language Models (LALMs) have achieved remarkable progress in audio perceptual tasks across individual acoustic layers, including speech, sound, and music. However, existing benchmarks predominantly evaluate these layers in isolation, overlooking the complex contextual relationships that arise when multiple acoustic sources co-occur in real-world auditory scenes.
arXiv:2606. 30700v1 Announce Type: cross Abstract: Self-supervised learning enables audio representations that transfer across domains and tasks.
By Ludovic K. Tuncay (IRIT-SAMoVA), Etienne Labb\'e (IRIT-SAMoVA), Thomas Pellegrini (IRIT-SAMoVA)
TEMPO is a unified model that adds temporally‑grounded capabilities to large audio‑language models, enabling timestamping of events, speakers, and sounds in audio, speech, and music. It introduces a supervised fine‑tuning stage featuring atomic timestamp tokens, a time‑aware projector with sinusoidal encodings, and a distance‑aware Gaussian loss, trained via a synthetic‑to‑real curriculum. Additionally, TEMPO employs reinforcement learning (GRPO) as a refinement step, and achieves state‑of‑the‑art performance on a benchmark of 10K samples across five timestamping tasks, surpassing Audio Flamingo Next and Qwen3‑Omni.
By Apoorva Kulkarni, Kaousheik Jayakumar, Sreyan Ghosh, Utathya Aich, Ramani Duraiswami, Dinesh Manocha