Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our analyses suggest that classification supervision alone does not sufficiently preserve task-agnostic shared backbone representations over long incremental sequences. We identify two intertwined challenges: cross-task confusion from sequential training on predominantly current-task data, which biases decision boundaries toward recent tasks; and under-optimized shared representations in the backbone that cap long-term discriminability as tasks accumulate.
arXiv:2608.31096v1 Announce Type: cross
Abstract: Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while...
By Yunxiang Fu, Meng Lou, Yizhou Yu
arXiv:2411. 16073v4 Announce Type: replace-cross Abstract: Inspired by the Well-initialized Lottery Ticket Hypothesis (WLTH), we introduce Soft-TransFormers (Soft-TF), a continual learning framework that adapts a frozen pre-trained Transformer through task-specific soft subnetworks: real-valued multiplicative masks over the query, key, value, and output projections of selected self-attention layers.
By Haeyong Kang, Chang D. Yoo
arXiv:2605.12491v2 Announce Type: replace
Abstract: Vision Transformers (ViTs) learn rich visual-semantic representations through all-to-all self-attention among patch tokens. However, this design im...
By Alan Z. Song, Yinjie Chen, Mu Nan, Deva Ramanan, Michael J. Tarr, Andrew F. Luo
arXiv:2603. 11211v3 Announce Type: replace-cross Abstract: Incremental Learning (IL) aims to learn new tasks while preserving previously acquired knowledge.
By Haihua Luo, Xuming Ran, Jiangrong Shen, Timo H\"am\"al\"ainen, Zhonghua Chen, Qi Xu, Fengyu Cong
arXiv:2607. 10391v1 Announce Type: cross Abstract: Despite exposing rich intermediate representations, Vision Transformers (ViTs) are almost exclusively utilized as black-box feature extractors, where only the last layer is considered for downstream tasks.
By Francesco Di Salvo, Shyam Nandan Rai, Hamed Damirchi, Ignacio Meza De la Jara, Sebastian Doerrich, Marco Lents, Christian Ledig
The paper introduces a method to retrofit depth recurrence into pretrained vision‑language models, reducing the language backbone’s parameter count by pruning layers and looping over the remaining ones with linear adapters. A three‑stage recovery training—language‑only pretraining, vision‑language projector alignment, and full fine‑tuning—helps recover performance, with distillation from the non‑recurrent model further improving results. Experiments on TinyLLaVA‑1.4B show the retrofitted recurrent model outperforms the unpruned baseline while saving 23.3% of language parameters and performs better on reasoning‑oriented benchmarks.
By Madhav Iyengar, Andreas Geiger, Hilde K\"uhne
arXiv:2507.00754v3 Announce Type: replace
Abstract: The integration of Large Language Model (LLMs) blocks with Vision Transformers (ViTs) holds immense promise for vision-only tasks by leveraging the...
By Selim Kuzucu, Muhammad Ferjad Naeem, Anna Kukleva, Federico Tombari, Bernt Schiele
arXiv:2605. 04913v4 Announce Type: replace-cross Abstract: LLM post-training typically propagates task gradients through the full depth of the model.
By Hengyu Shi, Tianyang Han, Peizhe Wang, Zhiling Wang, Xu Yang, Junhao Su
Recent advances in Diffusion Transformers (DiTs) have enabled remarkable progress in visual synthesis, benefiting from their superior scalability. To facilitate DiTs' capability of capturing meaningful internal representations, recent works such as REPA incorporate external pretrained encoders for representation alignment.
VisionWeave introduces elastic visual representation weaving, a native capability for multimodal large language models that learns where and at what granularity to encode visual information. The method combines a gated spatial pooler for coarse representations with a granularity router that allocates content‑adaptive token usage, trained end‑to‑end on large‑scale data. Experiments on Qwen3.5‑4B and Qwen3.8‑27B show that VisionWeave can save 43.0% of tokens while preserving 98.9% of performance across eight benchmarks, and delivers significant throughput gains and latency reductions when deployed on the SGLang serving engine.
By Yuan Feng, Qize Yang, Ruizhe Chen, Sibo Song, Haolin He, Muzhi Zhu, Zihan Liu, Yunfei Chu, Xize Cheng, Yuxuan Wang, Jin Xu, Xike Xie
The paper proposes a drift‑adaptive method for Domain‑Incremental Learning that tracks representation drift for each past domain‑class pair. By measuring how much a concept’s current representation deviates from a fixed anchor, the method assigns stronger preservation to high‑drift pairs and down‑weights highly drifted domains during prototype construction. Experiments on DomainNet, Office‑Home, CORe50, and CDDB‑Hard show that this approach maintains a strong accuracy‑forgetting balance while using less training memory and the smallest storage compared to other methods.
By Hyunmin Kong, Gyutae Oh, Jitae Shin