Reza Sayar's picture

Reza Sayar

Reza2kn

·

AI & ML interests

None yet

Organizations

Reza2kn's activity

upvoted a paper 2 days ago

LLaVA-o1: Let Vision Language Models Reason Step-by-Step

Paper • 2411.10440 • Published 4 days ago • 78

upvoted a collection 5 days ago

LLM2CLIP

LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. • 7 items • Updated about 8 hours ago • 34

upvoted 2 collections 19 days ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 8 items • Updated 15 days ago • 169

MobileLLM

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 8 items • Updated 13 days ago • 95

upvoted a paper 24 days ago

SMITE: Segment Me In TimE

Paper • 2410.18538 • Published 27 days ago • 15

upvoted a collection 25 days ago

Pangea

A Fully Open Multilingual Multimodal LLM for 39 Languages • 18 items • Updated 18 days ago • 17

upvoted an article 28 days ago

Article

Advanced Flux Dreambooth LoRA Training with 🧨 diffusers

By

•

30 days ago

• 27

upvoted a collection 28 days ago

Granite 3.0 Language Models

A series of language models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 8 items • Updated 15 days ago • 88

upvoted an article about 1 month ago

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Sep 18

• 201

upvoted a paper about 1 month ago

WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines

Paper • 2410.12705 • Published Oct 16 • 29

upvoted a collection about 1 month ago

SAM 2.1

Collection of SAM 2.1 model checkpoints • 8 items • Updated Oct 6 • 8

upvoted an article about 2 months ago

Article

DEMO: French Spoken Language Understanding with the new speech resources from NAVER LABS Europe

By

•

Aug 28

• 9

upvoted a collection about 2 months ago

Emu3

5 items • Updated 25 days ago • 65

upvoted a paper 2 months ago

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Paper • 2409.12191 • Published Sep 18 • 73

upvoted 2 collections 2 months ago

Moshi v0.1 Release

MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi • 13 items • Updated Sep 18 • 218

xLAM models

xLAM: A Family of Large Action Models to Empower AI Agent Systems: https://github.com/SalesforceAIResearch/xLAM • 11 items • Updated 20 days ago • 43

upvoted 2 papers 3 months ago

Generative Verifiers: Reward Modeling as Next-Token Prediction

Paper • 2408.15240 • Published Aug 27 • 13

LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs

Paper • 2408.13467 • Published Aug 24 • 24

upvoted 2 articles 3 months ago

Article

Llama-3.1-Storm-8B: Improved SLM with Self-Curation + Model Merging

By

•

Aug 19

• 73

Article

Tool Use, Unified

Aug 12

• 64