LAION-Audio-XL: A Web-Scale Corpus and Scaling Studies for Contrastive Language-Audio Pretraining
cs.SD, cs.CL
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- Learning Transferable Visual Models From Natural Language Supervision
- M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation
- Scaling Laws for Neural Language Models
- DataComp: In search of the next generation of multimodal datasets
- Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music
- MiDashengLM: Efficient Audio Understanding with General Audio Captions
- MiMo-Audio: Audio Language Models are Few-Shot Learners
- Qwen3.5-Omni Technical Report
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- MAEB: Massive Audio Embedding Benchmark
- Scaling Audio-Text Retrieval with Multimodal Large Language Models
- CapTalk: Unified Voice Design for Single-Utterance and Dialogue Speech Generation
- LP-MusicCaps: LLM-Based Pseudo Music Captioning
- Qwen2.5-Omni Technical Report
- MOSS-Audio Technical Report
- SALMONN-2: Advancing General-Purpose Hearing Abilities with Self-Supervised Representations
- Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
- LAION-BVD: A 13-Million-Hour Open Video Dataset for Multimodal Pre-training
- Movie Gen: A Cast of Media Foundation Models
- Scaling Laws and Interpretability of Learning from Repeated Data
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems