3 332 498

Habibullah Akbar

ChavyvAkvar

https://chavyv.vercel.app

AI & ML interests

AGI, Ethical-Driven AI, Open-source AI

Recent Activity

upvoted a paper about 8 hours ago

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

upvoted an article about 14 hours ago

Open R1: Update #2

liked a dataset about 14 hours ago

agentica-org/DeepScaleR-Preview-Dataset

View all activity

Organizations

ChavyvAkvar's activity

upvoted a paper about 8 hours ago

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Paper • 2502.06703 • Published 1 day ago • 53

upvoted an article about 14 hours ago

Article

Open R1: Update #2

and 6 others •

1 day ago

• 115

upvoted a paper about 15 hours ago

LM2: Large Memory Models

Paper • 2502.06049 • Published 2 days ago • 13

upvoted a paper 1 day ago

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published 4 days ago • 40

upvoted 2 papers 4 days ago

Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2

Paper • 2502.03544 • Published 6 days ago • 37

Great Models Think Alike and this Undermines AI Oversight

Paper • 2502.04313 • Published 5 days ago • 24

upvoted 3 papers 5 days ago

upvoted 2 papers 6 days ago

Demystifying Long Chain-of-Thought Reasoning in LLMs

Paper • 2502.03373 • Published 6 days ago • 48

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Paper • 2412.10302 • Published Dec 13, 2024 • 16

upvoted 2 papers 8 days ago

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Paper • 2501.19324 • Published 11 days ago • 34

s1: Simple test-time scaling

Paper • 2501.19393 • Published 11 days ago • 98

upvoted 5 papers 11 days ago

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Paper • 2501.18585 • Published 12 days ago • 51

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

Paper • 2501.18427 • Published 12 days ago • 16

Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch

Paper • 2501.18512 • Published 12 days ago • 25

Large Language Models Think Too Fast To Explore Effectively

Paper • 2501.18009 • Published 13 days ago • 22

WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training

Paper • 2501.18511 • Published 12 days ago • 17

upvoted 2 papers 13 days ago

Optimizing Large Language Model Training Using FP4 Quantization

Paper • 2501.17116 • Published 14 days ago • 33

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published 14 days ago • 101