Specialized and Edge Language Models (GLM, Hunyuan, Granite, LFM, LLM-jp, etc.)
i love SSD
aoiandroid
AI & ML interests
None yet
Recent Activity
updated a bucket about 20 hours ago
aoiandroid/SenseVoiceSmall-GGUF-bucket published a bucket about 20 hours ago
aoiandroid/SenseVoiceSmall-GGUF-bucket published a model 1 day ago
aoiandroid/speakerkit-proOrganizations
Audio, VAD & Diarization
Voice Activity Detection, Diarization, and Audio Processing models
Nemotron
NVIDIA Nemotron ASR and VoiceChat models
Papers
-
SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching
Paper • 2509.24832 • Published -
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
Paper • 2605.00658 • Published • 87 -
Map2World: Segment Map Conditioned Text to 3D World Generation
Paper • 2605.00781 • Published • 26 -
From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
Paper • 2604.24026 • Published • 23
mms-lid
translategemma
parakeet
madlad
whisper
omnivoice
OCR & Document AI
OCR, Document Parsing, and Multimodal Vision models
Kokoro & Voice TTS
Kokoro, VibeVoice, CosyVoice, and Text-to-Speech / Voice generation models
Game Dev
neucodec
aoiandroid models matching neucodec search
yolo
gemma
llama
aoiandroid models matching llama search
nllb
qwen
neutts-jp
Other LLM / SLM
Specialized and Edge Language Models (GLM, Hunyuan, Granite, LFM, LLM-jp, etc.)
OCR & Document AI
OCR, Document Parsing, and Multimodal Vision models
Audio, VAD & Diarization
Voice Activity Detection, Diarization, and Audio Processing models
Kokoro & Voice TTS
Kokoro, VibeVoice, CosyVoice, and Text-to-Speech / Voice generation models
Nemotron
NVIDIA Nemotron ASR and VoiceChat models
Game Dev
Papers
-
SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching
Paper • 2509.24832 • Published -
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
Paper • 2605.00658 • Published • 87 -
Map2World: Segment Map Conditioned Text to 3D World Generation
Paper • 2605.00781 • Published • 26 -
From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
Paper • 2604.24026 • Published • 23
neucodec
aoiandroid models matching neucodec search
mms-lid
yolo
translategemma
gemma
parakeet
llama
aoiandroid models matching llama search
madlad
nllb
whisper
qwen
omnivoice
neutts-jp