OpenMOSS
@Open_MOSS
OpenMOSS is an open research community aimed at building artificial general intelligence.
MOSS-TTSD 🔊 Bilingual text-to-spoken dialogue model by Fudan University @Open_MOSS Model: huggingface.co/fnlp/MOSS-TTSD… Demo: huggingface.co/spaces/fnlp/MO… ✨ Supports Chinese & English ✨ Zero-shot 2-speaker voice cloning ✨ Long-form generation (up to 960s) ✨ Built on Qwen 3
Are attention heads the right units to mechanistically understand Transformers' attention behavior? Probably not!
Are attention heads the right units to mechanistically understand Transformers' attention behavior? Probably not due the attention superposition! We extracted interpretable attention units in LMs and found finer grained versions of many known and novel attention behaviors. 🧵1/N
✨ Excited to share our latest research “World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning” 🤔 Current LVLMs struggle with grounding in embodied environments, how can we make AI agents understand the physical world like humans? 1/8
🥳 Introducing SpeechGPT 2.0-preview: A GPT-4o-level, real-time spoken dialogue system! (Only Chinese for now) 🎆 Highlights: ～⚡️ Real-time speech-to-speech dialogue with latency under 200ms ～😊 Rich in emotion and diverse in style, with strong speech style generalization ～🦁…