view article Article Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community ResterChed • 13 days ago • 186
MOSS Transcribe Collection A unified multimodal large language model for end-to-end speaker-attributed, time-stamped transcription. • 4 items • Updated 20 days ago • 13
view article Article Ulysses Sequence Parallelism: Training with Million-Token Contexts kashif, stas • Mar 9 • 32
Robust Speech Recognition via Large-Scale Weak Supervision Paper • 2212.04356 • Published Dec 6, 2022 • 55
MOSS-Audio Collection An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex • 13 items • Updated 20 days ago • 67
MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models Paper • 2602.10934 • Published Feb 11 • 50
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning Paper • 2602.10090 • Published Feb 10 • 53
MOVA: Towards Scalable and Synchronized Video-Audio Generation Paper • 2602.08794 • Published Feb 9 • 159
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Paper • 2601.14724 • Published Jan 21 • 75
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development Paper • 2601.11077 • Published Jan 16 • 67
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs Paper • 2601.13836 • Published Jan 20 • 37