AI Paper Atlas

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

SyncVL: Synchronizing Vision ⟷ Language Using Unsupervised Adaptation

Maria Marrium, Muhammad Haris Khan, Sajid Javed, Arif Mahmood

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Self-distillation for vision-language pretraining

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 V2T synchronizer without OF (ablation)CLIP · CIFAR-10accuracy (%): 91.30 -> 86.37Hurt
add V2T synchronizer with OF (ablation)CLIP · CIFAR-10accuracy (%): 91.30 -> 93.06Improved
add T2V synchronizer to V2T without OF (ablation)SyncVL · CIFAR-10accuracy (%): 86.37 -> 95.86Improved
add proposed objective function (OF) to V2T+T2V (ablation)SyncVL · CIFAR-10accuracy (%): 95.86 -> 98.65Improved
add alignment reward to consistency reward (ablation)SyncVL · CIFAR-10accuracy (%): 94.18 -> 96.32Improved
add KD (latent) reward on top of consistency and alignment (ablation)SyncVL · CIFAR-10accuracy (%): 96.32 -> 98.65Improved
replace MLP autoencoder with two-block transformer synchronizer (ablation)SyncVL · CIFAR-10accuracy (%): 84.72 -> 98.65Improved
increase synchronizer depth from two to four transformer blocks (ablation)SyncVL · CIFAR-100accuracy (%): 81.14 -> 79.91Hurt
add pseudo-label re-grouping (ablation)SyncVL · DTDaccuracy (%): 58.86 -> 59.92Improved
add iterative synchronizer training (ablation)SyncVL · DTDaccuracy (%): 59.92 -> 63.28Improved
use GRPO-based SyncVL instead of baseline formulation for reward gradients (ablation)SyncVL · CIFAR-10gradient cosine similarity: -0.17 -> 0.44Improved
apply SyncVL to CLIP RN50 under poor initialization (ablation)CLIP RN50 · DTDaccuracy (%): 41.70 -> 61.94Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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