Shravan Nayak

BAJUKA's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 15 days ago

BAJUKA/data_r2

Preview • Updated 15 days ago • 91

published a dataset 15 days ago

BAJUKA/data_r2

Preview • Updated 15 days ago • 91

updated a model 17 days ago

BAJUKA/LLaVA-llama32-3b-Tfull-s42-s2b

Text Generation • 4B • Updated 17 days ago • 285

published a model 17 days ago

BAJUKA/LLaVA-llama32-3b-Tfull-s42-s2b

Text Generation • 4B • Updated 17 days ago • 285

updated a model 17 days ago

BAJUKA/LLaVA-llama32-3b-Tfull-s42-s2a

Text Generation • 4B • Updated 17 days ago • 288

published a model 17 days ago

BAJUKA/LLaVA-llama32-3b-Tfull-s42-s2a

Text Generation • 4B • Updated 17 days ago • 288

updated a model 17 days ago

BAJUKA/LLaVA-llama32-3b-VLfull-s42-s2b

Image-Text-to-Text • 4B • Updated 17 days ago • 24

published a model 17 days ago

BAJUKA/LLaVA-llama32-3b-VLfull-s42-s2b

Image-Text-to-Text • 4B • Updated 17 days ago • 24

updated a model 17 days ago

BAJUKA/LLaVA-llama32-3b-VLfull-s42-s2a

Image-Text-to-Text • 4B • Updated 17 days ago • 24

published a model 17 days ago

BAJUKA/LLaVA-llama32-3b-VLfull-s42-s2a

Image-Text-to-Text • 4B • Updated 17 days ago • 24

upvoted 3 papers about 2 months ago

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents

Paper • 2607.22798 • Published Jul 24 • 63

LLMs Get Lost in Evolving User Intent

Paper • 2607.20734 • Published Jul 22 • 26

An Exam for Active Observers

Paper • 2607.16165 • Published Jul 17 • 26

upvoted a paper 2 months ago

DataComp-VLM: Improved Open Datasets for Vision-Language Models

Paper • 2606.28551 • Published Jun 26 • 56

updated a dataset 2 months ago

BAJUKA/data_v2

Preview • Updated Jul 6 • 75

published a dataset 2 months ago

BAJUKA/data_v2

Preview • Updated Jul 6 • 75

upvoted 2 papers 3 months ago

Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories

Paper • 2606.11176 • Published Jun 9 • 133

TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders

Paper • 2606.09323 • Published Jun 8 • 54

upvoted 2 papers 4 months ago

How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning

Paper • 2605.27310 • Published May 26 • 20

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

Paper • 2605.21573 • Published May 20 • 112