Repairing Speech Access After Text Updates with Frozen Affine Fields

cs.CL, eess.AS

Submitted: 2026-10-14

Updated: 2026-10-14

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs
• CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
• Steer-MoE: Efficient Audio-Language Alignment with a Mixture-of-Experts Steering Module
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation
• Kimi-Audio Technical Report
• Steering Language Models With Activation Engineering
• BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing
• BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation
• MiMo-Audio: Audio Language Models are Few-Shot Learners
• Qwen2.5-Omni Technical Report
• SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering