GSLM2: Multi-Stream Speech Representation Learning and Generative Spoken Language Modeling
cs.CL, cs.SD, eess.AS
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/facebookresearch/gslm2
Terminology
Sources
- Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
- FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs
- Seamless: Multilingual Expressive and Streaming Speech Translation
- MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
- Moshi: a speech-text foundation model for real-time dialogue
- Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
- CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
- The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation
- Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science
- Gemma 4 Technical Report
- The Llama 3 Herd of Models
- Moonshine: Speech Recognition for Live Transcription and Voice Commands
- Kimi-Audio Technical Report
- Voxtral
- The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling
- fastabx: A library for efficient computation of ABX discriminability
- Scaling Properties of Continuous Diffusion Spoken Language Models
- Llama-Mimi: Exploring the Limits of Flattened Speech Language Modeling
- LAST: Language Model Aware Speech Tokenization
- Qwen2.5-Omni Technical Report
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data