activity
20242026
collaborators

11 papers

cs.CV2026

Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards

Ritesh Thawkar, Shravan Venkatraman, Omkar Thawakar +5

Most unified large multimodal models (LMMs) that support both visual understanding and image generation still rely on curated post-training supervision, such as human annotations,…

cs.CV2026

Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models

Shravan Venkatraman, Ritesh Thawkar, Omkar Thawakar +4

Recently, self-evolving large multimodal models (LMMs) have received attention for improving visual reasoning in a purely unsupervised setting. However, multi-role self-play and se…

cs.CV2026

PCM-NeRF: Probabilistic Camera Modeling for Neural Radiance Fields under Pose Uncertainty

Shravan Venkatraman, Rakesh Raj Madavan, Pavan Kumar Sathya Venkatesh

Neural surface reconstruction methods typically treat camera poses as fixed values, assuming perfect accuracy from Structure-from-Motion (SfM) systems. This assumption breaks down…

cs.CV2025

TIDE: Two-Stage Inverse Degradation Estimation with Guided Prior Disentanglement for Underwater Image Restoration

Shravan Venkatraman, Rakesh Raj Madavan, Pavan Kumar S +1

Underwater image restoration is essential for marine applications ranging from ecological monitoring to archaeological surveys, but effectively addressing the complex and spatially…

eess.IV2025

UGPL: Uncertainty-Guided Progressive Learning for Evidence-Based Classification in Computed Tomography

Shravan Venkatraman, Pavan Kumar S, Rakesh Raj Madavan +1

Accurate classification of computed tomography (CT) images is essential for diagnosis and treatment planning, but existing methods often struggle with the subtle and spatially dive…

cs.CV2025

FUSION: Frequency-guided Underwater Spatial Image recOnstructioN

Jaskaran Singh Walia, Shravan Venkatraman, Pavithra LK

Underwater images suffer from severe degradations, including color distortions, reduced visibility, and loss of structural details due to wavelength-dependent attenuation and scatt…