AI Paper Atlas

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

Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection

Ruilin Li, Heming Zou, Xiufeng Yan, Zheming Liang, Jie Yang, Chenliang Li, Xue Yang

ECCV 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation · 6 citations (OpenAlex)

This paper tried a common change: Larger batch size

increase batch size s tenfold · CIL benchmarks · A_last No clear effect

What 785 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
replace random RPL with MGSM data-guided RPL constructionRPL-based CIL · ImageNet-R (B0 Inc-10)A_last: 75.07 -> 77.12 (vs best baseline APT)Improved
replace SCSM greedy criterion with MGSM criterion at 10,000 hidden units (ablation)SCL-MGSM · four CIL benchmarksA_last: approximately 5%-10% gain over SCSMImproved
replace random initialization with MGSM at 10,000 hidden units, ImageNet-A (ablation)SCL-MGSM · ImageNet-AA_lastImproved
SCSM vs random initialization (ablation)RPL construction · frozen PTM featuresA_lastHurt
use adaptive xi instead of fixed xi (0.08 or 0.008) (ablation)SCL-MGSM · four CIL benchmarksA_lastImproved
increase batch size s tenfold (ablation)SCL-MGSM · CIL benchmarksA_lastNo clear effect
enable first-session adaptation (FSA) (ablation)RPL-based methods · CIL benchmarksgain over joint linear probeImproved
swap ViT-B/16-IN21K for DINO-v2SCL-MGSM · ImageNet-R (B0 Inc-10)A_last: 77.12 -> 86.40Improved
MGSM RPL on ResNet-101 backboneSCL-MGSM · ImageNet-A (B0 Inc-10)A_last: 20.08 vs LoRanPAC 21.94Hurt
MGSM RPL with moderate lambda instead of large lambda for RI (ablation)SCL-MGSM · ImageNet-Acondition number / ||P_t||_FImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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