James Neville's picture

James Neville

Khawn2u

·

AI & ML interests

None yet

Recent Activity

liked a model about 20 hours ago

bartowski/deepcogito_cogito-v1-preview-qwen-14B-GGUF

liked a model 3 days ago

nvidia/Llama-3_1-Nemotron-Ultra-253B-v1

reacted to jjokah's post with 👍 5 days ago

# Video Tokenization — for efficient AI video processing Meet 𝐕𝐢𝐝𝐓𝐨𝐤, a new open-source video tokenization technique developed by Microsoft Research to address the computational challenges of processing large volumes of video data. The core problem VidTok tackles is the inefficiency caused by redundant information in raw video pixels. VidTok converts complex video footage into compact, structured units called tokens, making it easier and more efficient for AI systems to analyze, understand, and generate video content. Research Paper: https://arxiv.org/abs/2412.13061 VidTok Code: https://github.com/microsoft/VidTok

View all activity

Organizations

None yet

Khawn2u's activity

upvoted a paper 28 days ago

Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity

Paper • 2412.02252 • Published Dec 3, 2024 • 2

upvoted 2 papers about 1 month ago

TransMLA: Multi-head Latent Attention Is All You Need

Paper • 2502.07864 • Published Feb 11 • 49

Kimi k1.5: Scaling Reinforcement Learning with LLMs

Paper • 2501.12599 • Published Jan 22 • 113

upvoted an article about 2 months ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.21k

upvoted a collection 2 months ago

Hibiki fr-en

Hibiki is a model for streaming speech translation , which can run on device! See https://github.com/kyutai-labs/hibiki. • 5 items • Updated Feb 6 • 52