AK's picture

AK

akhaliq

·

_akhaliq

AI & ML interests

None yet

Recent Activity

liked a Space about 4 hours ago

nari-labs/Dia-1.6B

upvoted a collection about 4 hours ago

liked a Space about 16 hours ago

nvidia/describe-anything-model-demo

View all activity

Organizations

akhaliq's activity

upvoted a collection about 4 hours ago

LiveCC

Learning Video LLM with Streaming Speech Transcription at Scale (CVPR 2025) • 8 items • Updated about 19 hours ago • 3

upvoted an article 4 days ago

Article

17 Reasons Why Gradio Isn't Just Another UI Library

8 days ago

• 19

upvoted a paper 6 days ago

Towards Learning to Complete Anything in Lidar

Paper • 2504.12264 • Published 7 days ago • 10

upvoted a collection 14 days ago

Kimi-VL-A3B

Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking • 6 items • Updated 11 days ago • 61

upvoted a collection 18 days ago

Llama 4

Llama 4 release • 10 items • Updated 18 days ago • 447

upvoted a collection 27 days ago

LeX-Art

8 items • Updated 23 days ago • 3

upvoted a collection 28 days ago

Qwen2.5-Omni

End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 3 items • Updated 28 days ago • 90

upvoted 5 collections about 1 month ago

PP-VCtrl

10 items • Updated Mar 17 • 2

Open-RS

Model weights & datasets in the paper "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn’t" • 8 items • Updated Mar 21 • 11

JARVIS-VLA-v1

Vision-Language-Action Models in Minecraft. • 4 items • Updated Mar 22 • 10

DeTikZify

Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ • 12 items • Updated Mar 19 • 25

💫StarVector Models

StarVector is a multimodal LLM for Scalable Vector Graphics (SVG) generation, producing structured SVG code directly from images and text. • 2 items • Updated Mar 20 • 93

upvoted a paper about 1 month ago

Cube: A Roblox View of 3D Intelligence

Paper • 2503.15475 • Published Mar 19 • 29

upvoted 5 collections about 1 month ago

Cosmos Transfer1

Multimodal Conditional World Generation for World2World Transfer • 6 items • Updated about 9 hours ago • 14

EXAONE-Deep

EXAONE reasoning model series of 2.4B, 7.8B, and 32B, optimized for reasoning tasks including math and coding • 9 items • Updated Mar 18 • 86

Wan2.1 14B 480p I2V LoRAs

A collection of Remade's Wan2.1 14B 480p I2V LoRAs • 39 items • Updated 23 days ago • 104

BD3-LMs

https://m-arriola.com/bd3lms/ • 4 items • Updated 12 days ago • 20

Gemma 3 Release

24 items • Updated 5 days ago • 342

upvoted a paper about 1 month ago

Forgetting Transformer: Softmax Attention with a Forget Gate

Paper • 2503.02130 • Published Mar 3 • 32

upvoted a paper about 2 months ago

EgoLife: Towards Egocentric Life Assistant

Paper • 2503.03803 • Published Mar 5 • 42