arXiv Machine Learning June 18, 2026 By Ali Asaria, Tony Salomone, Deep Gandhi

Reliable Neural-Codec Text-to-Speech by ASR Self-Verification and Distillation: Near-Zero Catastrophic Failures Across Models and Codecs

Read the original on arXiv Machine Learning →

arXiv:2606. 18323v1 Announce Type: cross Abstract: Open autoregressive neural-codec text-to-speech (TTS) models sound excellent on typical inputs yet suffer stochastic catastrophic failures: on a meaningful fraction of utterances they emit silence, terminate early, or collapse into repetitive or hallucinated content.

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

arXiv Machine Learning

Jul 23

Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance

arXiv:2607. 19386v1 Announce Type: new Abstract: Cross-paper comparison of sparse autoencoder (SAE) interpretability often relies on autointerpretability scores.

By Sinie van der Ben, Neele Roch, Anna Hedstr\"om, Mennatallah El-Assady

llms safety

arXiv Machine Learning

Aug 4

Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models

arXiv:2507. 02778v3 Announce Type: replace-cross Abstract: Although large language models (LLMs) have transformed AI, they still make errors and follow unproductive reasoning paths.

By Ken Tsui

llms fine-tuning safety

arXiv Machine Learning

Jun 3

Fast Unlearning at Scale via Margin Self-Correction

arXiv:2606. 02920v1 Announce Type: new Abstract: Language-model unlearning updates a trained model to behave as if it had not seen selected training examples, while preserving utility and avoiding costly retraining.

By Federico Di Gennaro, Alexander Shevchenko, Fanny Yang

fine-tuning

arXiv AI

Jun 9

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones

arXiv:2507. 00322v2 Announce Type: replace-cross Abstract: Despite remarkable advances in coding capabilities, language models (LMs) still struggle with simple syntactic tasks such as generating balanced parentheses.

By Daking Rai, Samuel Miller, Kevin Moran, Ziyu Yao

llms

arXiv AI

Jun 10

Whisfusion: Parallel ASR Decoding with Masked Diffusion

arXiv:2508. 07048v2 Announce Type: replace-cross Abstract: Autoregressive (AR) encoder-decoder models dominate high-quality multilingual ASR, but their left-to-right decoders make inference latency scale with transcript length.

By Taeyoun Kwon, Junhyuk Ahn, Taegeun Yun, Heeju Jwa, Yoonchae Choi, Siwon Park, Jongchan Kim, Hyungon Ryu, Hyuk-Jae Lee, Nam-Joon Kim

llms rag diffusion efficiency multimodal benchmarks

arXiv AI

Jul 17

Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect

arXiv:2607. 14111v1 Announce Type: cross Abstract: Can small language models detect and report on perturbations their own internal activations?

By Ely Hahami, Ishaan Sinha, Lavik Jain

llms fine-tuning benchmarks safety

Related stories

Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance

Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models

Fast Unlearning at Scale via Margin Self-Correction

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones

Whisfusion: Parallel ASR Decoding with Masked Diffusion

Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect