Hugging Face's logo
Activity Feed

AI & ML interests

Our vibrant communities consist of experts, leaders and partners across the globe. They are developing cutting-edge open AI models for Image, Language, Audio, Video, 3D and Biology.

Recent Activity
mboss  authored a paper about 20 hours ago
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
mboss  authored a paper about 20 hours ago
4Director: Controlling Video World Models with Rigid 3D Geometry
mboss  submitted a paper about 22 hours ago
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
View all activity

Papers

4Director: Controlling Video World Models with Rigid 3D Geometry

SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation

View all Papers
mboss 
authored 2 papers about 20 hours ago
mboss 
submitted a paper to Daily Papers about 22 hours ago
vveicao 
submitted a paper to Daily Papers 1 day ago
cortexelus 
in stabilityai/stable-audio-3-small-sfx about 1 month ago

1·111
#1 opened about 1 month ago by
Yun1846205420
cortexelus 
updated a model about 1 month ago
mattricesound 
in stabilityai/stable-audio-3-optimized about 2 months ago

Add T5Gemma SentencePiece tokenizer.model
#8 opened about 2 months ago by
shawnbro12345
cortexelus 
in stabilityai/stable-audio-3-optimized 2 months ago

sm_120 sa3-m: add the fp8 medium-DiT tier (176 fp8 GEMM + 96 bf16 fused MHA, 1.43-1.95x vs fp16mixed)
#7 opened 2 months ago by
cortexelus

sm_120 SAME-L: AOT (graph-capturable) engines + tensorRT/README.md
#6 opened 2 months ago by
cortexelus

Fix the bf16 medium DiT: bake RoPE's tables into the graph (clipping 3.112% -> 0.014%)

1
#5 opened 2 months ago by
cortexelus

Rebuild medium DiT fp16-mixed engines (sm_90 + new sm_120): attention now fuses, 4.3x faster

2
#4 opened 2 months ago by
cortexelus

Fix medium DiT FP16-mixed ONNX: bound the RoPE island so attention fuses (4.3x faster, cos 1.0000)
#3 opened 2 months ago by
cortexelus
kateh 
in stabilityai/sd-turbo-amdnpu 2 months ago

Update AMD NPU model files to Ryzen AI 1.8.0
#1 opened 2 months ago by
bconsolvo
kateh 
in stabilityai/sdxl-base-amdnpu 2 months ago

Update AMD NPU model files to Ryzen AI 1.8.0

1
#1 opened 2 months ago by
bconsolvo
kateh 
in stabilityai/sdxl-turbo-amdnpu 2 months ago

Update AMD NPU model files to Ryzen AI 1.8.0

1
#1 opened 2 months ago by
bconsolvo
kateh 
in stabilityai/stable-diffusion-3.5-medium-amdnpu 2 months ago

Update AMD NPU model files to Ryzen AI 1.8.0

1
#1 opened 2 months ago by
bconsolvo
kateh 
in stabilityai/stable-diffusion-3-medium-amdnpu 2 months ago

Update AMD NPU model files to Ryzen AI 1.8.0

1
#1 opened 2 months ago by
bconsolvo
mattricesound 
in stabilityai/stable-audio-3-optimized 3 months ago

Add MLX base-model DiT weights for LoRA training
#2 opened 3 months ago by
cortexelus

Add bf16 medium DiT TRT engine (sm_90) — FMHA-fused, medium default
#1 opened 3 months ago by
cortexelus
cortexelus 
in stabilityai/stable-audio-3-optimized 3 months ago

Add MLX base-model DiT weights for LoRA training
#2 opened 3 months ago by
cortexelus