AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs

Behzad Bozorgtabar, Dwarikanath Mahapatra, Sudipta Roy, Muzammal Naseer, Imran Razzak, Zongyuan Ge

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add LATA graph refinement and failure-aware score to SCP (ablation)split conformal prediction (LAC) · 9 medical tasks, alpha=0.10avg set size: 3.99 -> 3.07Improved
add LATA graph refinement (no ViLU) to SCP (ablation)SCP (LAC) · alpha=0.10set size / CCV: Size 3.99 -> 3.14; CCV 9.96 -> 6.65Improved
add ViLU failure-aware score on top of LATA refinement (ablation)LATA (no ViLU) · LAC alpha=0.10set size / CCV: Size 3.14 -> 3.07; CCV 6.65 -> 6.40Improved
add only the ViLU risk term u to SCP (ablation)SCP (LAC) · alpha=0.10set size / CCV: Size 3.99 -> 3.95; CCV 9.96 -> 9.15Mixed
add only image-conditioned alpha term to SCP (ablation)SCP (LAC) · alpha=0.10set size / CCV: Size 3.99 -> 3.60; CCV 9.96 -> 8.85Mixed
use LATA instead of SCA-Ttransductive conformal · APS alpha=0.10set size / CCV / ACA: Size 3.35 -> 2.95; CCV 7.18 -> 6.32; ACA 55.2 -> 57.1Improved
turn on calibration-marginal prior (beta=0.2, LATA-LI) (ablation)LATA-LF · APS alpha=0.10coverage / size: coverage 0.900 -> 0.910; size 2.95 -> 3.03Mixed
fit linear probe on calibration labels then SCP on same split (Adapt+SCP)SCP · APS alpha=0.10coverage: 0.900 -> 0.858Hurt
use LATA instead of TransCLIP/TIMtransductive solvers · LAC alpha=0.10coverage: TransCLIP 0.726 vs LATA-LF 0.900Improved
increase window size W from 64 to 512 (ablation)LATA · LAC alpha=0.10set size: ~3.12 -> ~3.06No clear effect
increase calibration shots K from 4 to 16 (ablation)LATA · LAC alpha=0.10set size: 3.18 -> 3.08Improved
use LATA refinement instead of SCA-T/TIM for computetransductive solvers · LAC alpha=0.10runtime (s): 1.04 -> 0.05 (vs SCA-T)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy