24 234 23

Orr Zohar PRO

orrzohar

https://orrzohar.github.io

AI & ML interests

Large Multi-Modal Models, Foundation Models, Video Understanding

Recent Activity

upvoted a collection 1 day ago

SigLIP2

upvoted a paper 1 day ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

new activity 1 day ago

HuggingFaceTB/SmolVLM2-2.2B-Instruct:checkpoint you are trying to load has model type `smolvlm` but Transformers does not recognize this

View all activity

Organizations

orrzohar's activity

upvoted a collection 1 day ago

SigLIP2

Collection

36 items • Updated 2 days ago • 41

upvoted a paper 1 day ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published 3 days ago • 97

upvoted a collection 3 days ago

SmolVLM2 📺 Smallest video LM ever 🤏🏻

Collection

11 items • Updated 3 days ago • 34

upvoted an article 3 days ago

Article

SmolVLM2: Bringing Video Understanding to Every Device

4 days ago

• 135

upvoted a paper 4 days ago

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Paper • 2502.11089 • Published 7 days ago • 133

upvoted a paper 10 days ago

Distillation Scaling Laws

Paper • 2502.08606 • Published 11 days ago • 43

upvoted 2 papers 17 days ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published 19 days ago • 190

Demystifying Long Chain-of-Thought Reasoning in LLMs

Paper • 2502.03373 • Published 18 days ago • 51

upvoted a paper 18 days ago

Inverse Bridge Matching Distillation

Paper • 2502.01362 • Published 20 days ago • 26

upvoted a paper 20 days ago

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Paper • 2501.19324 • Published 23 days ago • 37

upvoted a paper 24 days ago

Optimizing Large Language Model Training Using FP4 Quantization

Paper • 2501.17116 • Published 26 days ago • 35

upvoted a paper 25 days ago

Qwen2.5-1M Technical Report

Paper • 2501.15383 • Published 28 days ago • 61

upvoted 2 papers 27 days ago

Humanity's Last Exam

Paper • 2501.14249 • Published about 1 month ago • 62

Redundancy Principles for MLLMs Benchmarks

Paper • 2501.13953 • Published Jan 20 • 27

upvoted a collection 29 days ago

Temporal Preference Optimization

Collection

Temporal Preference Optimization for Long-form Video Understanding • 3 items • Updated Jan 19 • 4

upvoted a paper 30 days ago

Temporal Preference Optimization for Long-Form Video Understanding

Paper • 2501.13919 • Published about 1 month ago • 22

upvoted 4 papers about 1 month ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published Jan 22 • 329

VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding

Paper • 2501.13106 • Published Jan 22 • 83

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos

Paper • 2501.09781 • Published Jan 16 • 25

Evolving Deeper LLM Thinking

Paper • 2501.09891 • Published Jan 17 • 106