Karthik Inbasekar

ik6626

AI & ML interests

Diffusion models: AR distillation training, video benchmarking design, diffusion LMs LLM: KV cache optimization, Speculative decoding

Recent Activity

updated a dataset about 1 month ago

ik6626/WorldJen-benchmarking-subsystem

authored a paper 3 months ago

WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video Models

upvoted a paper 4 months ago

WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video Models

View all activity

Organizations

None yet

liked a Space 5 months ago

JEPA Wiki

🧠

Explore the JEPA research knowledge base

liked 2 models 7 months ago

zhuhz22/Causal-Forcing

Text-to-Video • Updated May 11 • 21

nexar-ai/BADAS-Open

Video Classification • Updated Oct 15, 2025 • 61 • 19

liked 2 datasets 8 months ago

facebook/action100m-preview

Viewer • Updated Jan 29 • 120k • 1.09k • 150

HuggingFaceFV/finevideo

Viewer • Updated Apr 30 • 39.5k • 15.5k • 381

liked 2 models 8 months ago

Lightricks/LTX-2

Image-to-Video • 19B • Updated Aug 4 • 365k • • 1.78k

facebook/vjepa2-vitl-fpc64-256

Video Classification • 0.3B • Updated Aug 11, 2025 • 259k • 206

liked a dataset 8 months ago

facebook/IntPhys2

Viewer • Updated Jun 12, 2025 • 1.07k • 1.48k • 14

liked 2 models 8 months ago

Qwen/Qwen2.5-VL-72B-Instruct

Image-Text-to-Text • 73B • Updated Jun 6, 2025 • 168k • • 651

google/gemma-3-27b-it

Image-Text-to-Text • 27B • Updated Mar 21, 2025 • 371k • • 2.02k

liked 2 datasets 8 months ago

WenhaoWang/TIP-I2V

Viewer • Updated Jul 10, 2025 • 1.81M • 3.89k • 24

videophysics/videophy2_train

Updated Feb 6 • 358 • 3

liked a model 9 months ago

FastVideo/CausalWan2.2-I2V-A14B-Preview-Diffusers

Image-to-Video • 14B • Updated Nov 20, 2025 • 56 • 22

liked 2 Spaces 10 months ago

The Ultra-Scale Playbook

🌌

4.03k

The ultimate guide to training LLM on large GPU Clusters

FineWeb: decanting the web for the finest text data at scale

🍷

1.43k

Explore and download the FineWeb web‑scale text dataset

liked a model 10 months ago

gdhe17/Self-Forcing

Text-to-Video • Updated Sep 23, 2025 • 6.92k • 132

liked a Space 10 months ago

The Smol Training Playbook

📚

3.29k

The secrets to building world-class LLMs

liked 3 datasets 10 months ago