AI Paper Atlas

Research map / Continual learning / Continual fine-tuning of LLMs

SCoT: Similarity-guided Conflict-aware Task Consolidation for Continual VQA

Anand Patel, Moloud Abdar, Biplab Banerjee

ECCV 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Mixture-of-experts for multimodal continual tuning · 0 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 similarity-guided layer-wise consolidation (C2) to uniform task-vector averaging (ablation)SCoT · VQAv2 standard testAP (%): 39.23 -> 42.62Improved
add similarity-guided layer-wise consolidation (C2) (ablation)SCoT · NExT-QA standard testAP (%): 27.35 -> 32.15Improved
add similarity-guided consolidation (C2) (ablation)SCoT · VQAv2 standard testAF (%): -0.35 -> 1.42Hurt
add conflict-aware projection (C3) (ablation)SCoT · VQAv2 standard testAF (%): 1.42 -> 0.92Improved
add conflict-aware projection (C3) (ablation)SCoT · NExT-QA novel composition testAP (%): 34.00 -> 33.75Hurt
add depth-aware stabilization (C4) (ablation)SCoT · VQAv2 novel composition testAP (%): 41.31 -> 42.11Improved
add depth-aware stabilization (C4) (ablation)SCoT · VQAv2 standard testAP (%): 43.02 -> 42.78Hurt
stabilize late encoder and early decoder instead of early encoder layers (ablation)SCoT · VQAv2 novel composition testAP (%): 40.38 -> 42.11Improved
use consolidation range [0.08, 0.45] instead of narrow [0.05, 0.30] (ablation)SCoT · VQAv2 standard testAP (%): 41.22 -> 42.78Improved
use SCoT instead of joint multitask trainingSCoT · VQAv2 standard testAP (%): 41.32 -> 42.78Improved
use SCoT instead of joint multitask trainingSCoT · NExT-QA standard testAP (%): 35.92 -> 32.28Hurt
remove replay buffer (ablation)SCoT · VQAv2 standard testAP (%): 42.78 -> 31.44Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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