ml-4m

lingbot-depth

Masked Depth Modeling for Spatial Perception

github.com오픈소스최근 반응 9개월 전

4D-Humans

4DHumans: Reconstructing and Tracking Humans with Transformers

github.com오픈소스최근 반응 3년 전

Compress vision-language and unimodal AI models by structured pruning

[ICML 2023] UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers

github.com오픈소스반응 2개최근 반응 3년 전

Whisper at 1.58 bits with custom kernels for edge inference

medium.com최근 반응 작년

llm-compressor

State-of-the-art LLM compression, built for production inference with vLLM

github.com오픈소스최근 반응 2년 전