MahatmA

maha-atman

·

AI & ML interests

None yet

Recent Activity

liked a model about 1 month ago

NousResearch/Hermes-3-Llama-3.1-405B

liked a model 3 months ago

zai-org/GLM-OCR

liked a Space 4 months ago

OmniLottie/OmniLottie

View all activity

Organizations

None yet

upvoted 3 papers 9 months ago

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

Paper • 2510.08673 • Published Oct 9, 2025 • 128

CommonForms: A Large, Diverse Dataset for Form Field Detection

Paper • 2509.16506 • Published Sep 20, 2025 • 22

StreamingVLM: Real-Time Understanding for Infinite Video Streams

Paper • 2510.09608 • Published Oct 10, 2025 • 53

upvoted an article 9 months ago

Article

BigCodeArena: Judging code generations end to end with code executions

bigcode

•

Oct 7, 2025

• 21

upvoted 3 papers 10 months ago

Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play

Paper • 2509.25541 • Published Sep 29, 2025 • 142

DA^2: Depth Anything in Any Direction

Paper • 2509.26618 • Published Sep 30, 2025 • 26

LongLive: Real-time Interactive Long Video Generation

Paper • 2509.22622 • Published Sep 26, 2025 • 190

upvoted a collection 10 months ago

🎯 Liquid Nanos

Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices • 34 items • Updated 24 days ago • 123

upvoted 2 papers 10 months ago

Video models are zero-shot learners and reasoners

Paper • 2509.20328 • Published Sep 24, 2025 • 101

LLM-I: LLMs are Naturally Interleaved Multimodal Creators

Paper • 2509.13642 • Published Sep 17, 2025 • 9

upvoted 2 collections 10 months ago

Granite Docling

Models for parsing complex PDFs and structured documents, designed to complement Docling. • 4 items • Updated Apr 29 • 64

Holo1.5

Holo1.5 - Open Foundation Models for Computer Use Agents • 5 items • Updated Sep 15, 2025 • 35

upvoted an article 10 months ago

Article

PP-OCRv5 on Hugging Face: A Specialized Approach to OCR

baidu

•

Sep 10, 2025

• 112

upvoted a collection 10 months ago

PP-OCRv5

PP-OCRv5 is the latest text recognition solution, supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese • 13 items • Updated May 12 • 58

upvoted an article about 1 year ago

Article

Introducing ColQwen-Omni: Retrieve in every modality

manu

•

Jul 17, 2025

• 77

upvoted 3 papers about 1 year ago

Depth Anything at Any Condition

Paper • 2507.01634 • Published Jul 2, 2025 • 49

Seedance 1.0: Exploring the Boundaries of Video Generation Models

Paper • 2506.09113 • Published Jun 10, 2025 • 109

PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

Paper • 2506.05573 • Published Jun 5, 2025 • 83

upvoted a collection about 1 year ago

Lingshu MLLMs

Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning • 5 items • Updated Apr 8 • 21

upvoted a paper about 1 year ago

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

Paper • 2506.03143 • Published Jun 3, 2025 • 54