InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation
Paper • 2507.17520 • Published • 15
James PRO
jtatman
AI & ML interests
improving domain specific models and re-sampling data, refining datasets for use in different modalities, small scale micro-llm clusters using quantized and smoothed models, and all emerging llm stack connecting technologies. Small models rock.
Recent Activity
liked a model about 12 hours ago
moondream/moondream3-preview liked a model about 12 hours ago
Qwen/Qwen3.5-9B liked a dataset about 13 hours ago
unsloth/OpenMathReasoning-miniOrganizations
upvoted a paper 8 months ago
upvoted an article 11 months ago
Article
Page-to-Video: Generate videos from webpages 🪄🎬
•
27
upvoted 2
papers over 1 year ago
upvoted a collection over 1 year ago
upvoted an article over 1 year ago
Article
Llama 3.1 - 405B, 70B & 8B with multilinguality and long context
- +6
•
242
upvoted a paper over 1 year ago
upvoted a paper almost 2 years ago
upvoted an article almost 2 years ago
Article
Welcome Gemma - Google’s new open LLM
- +1
•
26
upvoted a collection almost 2 years ago
upvoted an article almost 2 years ago
Article
SeeMoE: Implementing a MoE Vision Language Model from Scratch
•
39
upvoted 3
papers about 2 years ago
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
Paper • 2403.03853 • Published • 66
Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding
Paper • 2401.12954 • Published • 32
Transformers are Multi-State RNNs
Paper • 2401.06104 • Published • 39
upvoted 2
papers over 2 years ago