150 15 33

Raushan Turganbay

RaushanTurganbay

zucchini-nlp

AI & ML interests

Generation and Multimodality

Recent Activity

liked a model 9 days ago

chenjoya/videollm-online-8b-v1plus

new activity 10 days ago

RaushanTurganbay/llava-onevision:Incomplete generation results on the pancake example?

liked a model 12 days ago

facebook/watermark-anything

View all activity

Articles

Introducing SynthID Text

Oct 23

• 39

Unlocking Longer Generation with Key-Value Cache Quantization

May 16

• 37

Organizations

RaushanTurganbay's activity

upvoted a paper about 2 months ago

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Paper • 2410.17434 • Published Oct 22 • 25

upvoted an article 3 months ago

Article

Saving Memory Using Padding-Free Transformer Layers during Finetuning

•

Jun 11

• 14

upvoted a collection 3 months ago

Molmo

Collection

Artifacts for open multimodal language models. • 5 items • Updated 28 days ago • 289

upvoted an article 4 months ago

Article

Key Insights into the Law of Vision Representations in MLLMs

•

Sep 2

• 18

upvoted a paper 4 months ago

Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance

Paper • 2409.04593 • Published Sep 6 • 23

upvoted a collection 4 months ago

Vision Language Models Papers 🖼️💬📝

Collection

Papers about vision-language models, most important ones are on top of the list. • 27 items • Updated Apr 30 • 34

upvoted an article 4 months ago

Article

Introduction to ggml

Aug 13

• 120

upvoted 2 papers 4 months ago

mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

Paper • 2408.04840 • Published Aug 9 • 32

VITA: Towards Open-Source Interactive Omni Multimodal LLM

Paper • 2408.05211 • Published Aug 9 • 47

upvoted 3 papers 5 months ago

upvoted a paper 6 months ago

Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision

Paper • 2407.06189 • Published Jul 8 • 25

upvoted an article 7 months ago

Article

AI has a problem with objectifying women

•

May 24

• 55

upvoted a paper 10 months ago

BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data

Paper • 2402.08093 • Published Feb 12 • 57