4 364 546

Habibullah Akbar

ChavyvAkvar

https://chavyv.vercel.app

AI & ML interests

AGI, Ethical-Driven AI, Open-source AI

Recent Activity

liked a model about 9 hours ago

hpcai-tech/Open-Sora-v2

updated a model about 14 hours ago

kreasof-ai/SPL-large-checkpoints

liked a model about 15 hours ago

lodestones/Chroma

View all activity

Organizations

ChavyvAkvar's activity

upvoted a paper 1 day ago

2 OLMo 2 Furious

Paper • 2501.00656 • Published Dec 31, 2024 • 19

upvoted a paper 7 days ago

Token-Efficient Long Video Understanding for Multimodal LLMs

Paper • 2503.04130 • Published 10 days ago • 79

upvoted 2 papers 13 days ago

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation

Paper • 2502.20388 • Published 16 days ago • 15

UniTok: A Unified Tokenizer for Visual Generation and Understanding

Paper • 2502.20321 • Published 16 days ago • 29

upvoted 2 papers 16 days ago

LongRoPE2: Near-Lossless LLM Context Window Scaling

Paper • 2502.20082 • Published 16 days ago • 31

Self-rewarding correction for mathematical reasoning

Paper • 2502.19613 • Published 17 days ago • 77

upvoted a paper 18 days ago

SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference

Paper • 2502.18137 • Published 19 days ago • 53

upvoted a paper 20 days ago

LightThinker: Thinking Step-by-Step Compression

Paper • 2502.15589 • Published 22 days ago • 26

upvoted 3 papers 22 days ago

Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning

Paper • 2502.14768 • Published 23 days ago • 45

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Paper • 2502.14739 • Published 23 days ago • 97

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

Paper • 2502.14786 • Published 23 days ago • 129

upvoted an article 22 days ago

Article

SigLIP 2: A better multilingual vision language encoder

23 days ago

• 135

upvoted 3 papers 24 days ago

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published 24 days ago • 164

Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published 25 days ago • 67

Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs

Paper • 2502.12982 • Published 25 days ago • 14

upvoted a paper 25 days ago

Continuous Diffusion Model for Language Modeling

Paper • 2502.11564 • Published 27 days ago • 52

upvoted a paper 26 days ago

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

Paper • 2502.11089 • Published 28 days ago • 143

upvoted a paper 27 days ago

Large Language Diffusion Models

Paper • 2502.09992 • Published 30 days ago • 103

upvoted 2 papers 30 days ago

InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU

Paper • 2502.08910 • Published about 1 month ago • 143

LLM Pretraining with Continuous Concepts

Paper • 2502.08524 • Published Feb 12 • 28