Mayank Bhaskar's picture

Mayank Bhaskar

cataluna84

·

AI & ML interests

Research interest includes anything that moves or in processing things that are on the audible spectrum and has recently been seduced by RL Theory, GNNs, Transformers & applications of them in solving self-driving autonomous systems including vehicles, drones, and robots.

Recent Activity

upvoted a collection about 3 hours ago

upvoted an article about 3 hours ago

SigLIP 2: A better multilingual vision language encoder

liked a Space about 16 hours ago

nanotron/ultrascale-playbook

View all activity

Organizations

cataluna84's activity

upvoted a collection about 3 hours ago

SigLIP2

36 items • Updated about 9 hours ago • 29

upvoted an article about 3 hours ago

Article

SigLIP 2: A better multilingual vision language encoder

about 18 hours ago

• 47

upvoted a paper 6 days ago

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

Paper • 2402.13753 • Published Feb 21, 2024 • 116

upvoted an article 14 days ago

Article

What is test-time compute and how to scale it?

By

and 1 other •

15 days ago

• 39

upvoted a collection 15 days ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 16 items • Updated 1 day ago • 238

upvoted a paper 15 days ago

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

Paper • 2502.02737 • Published 17 days ago • 187

upvoted 3 collections 15 days ago

🧪 FineWeb v1 data experiments

Ablation models trained for our data experiments. • 22 items • Updated Jun 12, 2024 • 5

📀 Dataset comparison models

1.8B models trained on 350BT to compare different pretraining datasets • 8 items • Updated Jun 12, 2024 • 37

🥂 FineWeb2

3 items • Updated Dec 8, 2024 • 13

upvoted an article 17 days ago

Article

Open-source DeepResearch – Freeing our search agents

18 days ago

• 1.06k

upvoted an article 22 days ago

Article

Open-R1: a fully open reproduction of DeepSeek-R1

25 days ago

• 768

upvoted 2 papers 23 days ago

Baichuan-Omni-1.5 Technical Report

Paper • 2501.15368 • Published 27 days ago • 61

Qwen2.5-1M Technical Report

Paper • 2501.15383 • Published 27 days ago • 61

upvoted a collection 25 days ago

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 3 items • Updated 26 days ago • 359

upvoted a paper 29 days ago

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

Paper • 2501.12948 • Published about 1 month ago • 327

upvoted a collection about 1 month ago

DeepSeek-R1

8 items • Updated Jan 21 • 523

upvoted an article about 1 month ago

Article

ZebraLogic: Benchmarking the Logical Reasoning Ability of Language Models

By

•

Jul 27, 2024

• 30

upvoted 2 collections about 1 month ago

DeepSeek R1 (All Versions)

DeepSeek R1 - the most powerful reasoning open-source model - available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 29 items • Updated 14 days ago • 192

Deepseek V3 (All Versions)

Deepseek V3 - available in bf16, original, and GGUF formats, with support for 2, 3, 4, 5, 6 and 8-bit quantized versions. • 3 items • Updated 17 days ago • 33

upvoted a paper about 1 month ago

Simplified State Space Layers for Sequence Modeling

Paper • 2208.04933 • Published Aug 9, 2022 • 1