arXiv Machine Learning June 4, 2026 By Yacouba Kaloga, Shashi Kumar, Shakeel A. Sheikh, Driss Khalil, Petr Motlicek, Ina Kodrasi

Test-Time Compute Scaling for ASR with Depth-Conditioned Looped Transformers

Read the original on arXiv Machine Learning →

arXiv:2606. 04678v1 Announce Type: new Abstract: End-to-end ASR systems typically use fixed-depth acoustic encoders at inference, making it difficult to trade additional test-time computation for improved recognition without training a larger model.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

1d ago

RecurrentGPT: Expressive Depth through Recurrent Modulation in Transformers

arXiv:2608. 15062v1 Announce Type: cross Abstract: Scaling transformer language models creates an inherent tension between expressivity and memory efficiency.

By Amr Hegazy, Amr Alanwar, Mostafa Elhoushi

llms efficiency

arXiv AI

Jun 4

MesaNet: Sequence Modeling by Locally Optimal Test-Time Training

arXiv:2506. 05233v2 Announce Type: replace-cross Abstract: Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention.

By Johannes von Oswald, Nino Scherrer, Seijin Kobayashi, Luca Versari, Songlin Yang, Sarthak Mittal, Maximilian Schlegel, Kaitlin Maile, Yanick Schimpf, Oliver Sieberling, Alexander Meulemans, Rif A. Saurous, Guillaume Lajoie, Charlotte Frenkel, Razvan Pascanu, Blaise Ag\"uera y Arcas, Jo\~ao Sacramento

llms benchmarks

arXiv Machine Learning

2d ago

Trajectory Dynamics in Self-Supervised Learning Latent Space for Audio Deepfake Detection

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

diffusion benchmarks

Hugging Face Trending Papers

Jul 9

Hidden Decoding at Scale: Latent Computation Scaling for Large Language Models

Scaling Large Language Models (LLMs) has been driven mainly by enlarging the Transformer backbone, but for an already-strong model this requires another round of costly pretraining. We study whether an existing backbone can keep improving by allocating more computation to each token while leaving the Transformer backbone fixed.

llms rag

arXiv AI

Jul 14

Looped State-Space Language Models with Adaptive Exit-State Selection

arXiv:2607. 10110v1 Announce Type: new Abstract: Recent work on looped language models suggests that many reasoning problems benefit from greater computational depth rather than from additional independent parameters.

By Zhenxuan Yu, Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa

llms robotics benchmarks

arXiv AI

Jun 16

Learning in the Recurrent State: Gradient Descent with Linear Recurrent Networks

arXiv:2410. 11687v3 Announce Type: replace-cross Abstract: Linear recurrent networks (LRNNs) offer linear-time sequence modeling, but standard recurrent updates do not directly expose the supervised products needed for in-context gradient descent.

By Yudou Tian, Neeraj Mohan Sushma, Harshvardhan Mestha, Nicolo Colombo, David Kappel, Anand Subramoney

safety

Related stories

RecurrentGPT: Expressive Depth through Recurrent Modulation in Transformers

MesaNet: Sequence Modeling by Locally Optimal Test-Time Training

Trajectory Dynamics in Self-Supervised Learning Latent Space for Audio Deepfake Detection

Hidden Decoding at Scale: Latent Computation Scaling for Large Language Models

Looped State-Space Language Models with Adaptive Exit-State Selection

Learning in the Recurrent State: Gradient Descent with Linear Recurrent Networks