Shyamgopal Karthik

shyamgopal's activity

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

authored 2 papers 8 days ago

Solving Spatial Supersensing Without Spatial Supersensing

Paper • 2511.16655 • Published Nov 20, 2025

It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models

Paper • 2601.00090 • Published 27 days ago

authored a paper 6 months ago

Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

Paper • 2508.09968 • Published Aug 13, 2025 • 15

authored 2 papers 10 months ago

Post-hoc Probabilistic Vision-Language Models

Paper • 2412.06014 • Published Dec 8, 2024 • 1

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

Paper • 2504.02821 • Published Apr 3, 2025 • 9

authored 5 papers over 1 year ago

ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization

Paper • 2406.04312 • Published Jun 6, 2024 • 2

Scalable Ranked Preference Optimization for Text-to-Image Generation

Paper • 2410.18013 • Published Oct 23, 2024 • 14

Vision-by-Language for Training-Free Compositional Image Retrieval

Paper • 2310.09291 • Published Oct 13, 2023

If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection

Paper • 2305.13308 • Published May 22, 2023

EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval

Paper • 2407.16658 • Published Jul 23, 2024