从几何视角剖析持续学习中的表征漂移，揭示灾难性遗忘的内在机制，为构建不退化的智能模型提供新思路。
arXiv:2608.15854v1 Announce Type: new Abstract: Catastrophic forgetting remains a fundamental obstacle to continual learning, where neural networks lo…
提出混合子专家架构，让大模型持续学习时有效缓解灾难性遗忘，兼顾精度与效率。
arXiv:2511.06237v2 Announce Type: replace Abstract: Enabling lifelong learning in LLMs demands resolving the stability-plasticity dilemma (i.e., model…
突破LLM持续微调遗忘瓶颈，ReCoLoRA以频谱感知递归合并实现任务序列高效学习。
arXiv:2607.07719v1 Announce Type: new Abstract: Parameter-efficient fine-tuning adapts a large language model to one task cheaply, but across a task s…
用概率提示应对持续学习中的灾难性遗忘，ECCV 2026 新方法值得关注
arXiv:2607.04711v1 Announce Type: new Abstract: Continual learning aims to progressively learn from a sequence of tasks, each containing a disjoint su…
持续学习如何对抗遗忘？贝叶斯方法综述给你严谨答案，从核心原理到前沿进展一网打尽。
arXiv:2507.08922v3 Announce Type: replace-cross Abstract: Continual learning is an online paradigm where a learner continually accumulates knowledge f…
多模态持续学习藏有“隐性遗忘”：模型精度不变，但跨模态对齐已悄悄失效，值得关注。
arXiv:2607.02020v1 Announce Type: new Abstract: Multimodal large language models must continually adapt to evolving tasks and domains, yet standard co…
理论严谨的曲率引导混合方法，有效缓解多模态大模型微调中的灾难性遗忘。
arXiv:2606.24963v1 Announce Type: cross Abstract: Fine-tuning Multimodal Large Language Models (MLLMs) on specialized tasks often leads to catastrophi…
通过表示层干预让大语言模型终身可控记忆知识，不遗忘旧信息，大模型记忆管理新范式。
arXiv:2511.20892v4 Announce Type: replace Abstract: Large language models (LLMs) often produce incorrect or outdated content after being employed. Eff…
新方法「支持边界经验混合」解决持续学习中的灾难性遗忘，理论创新与实践效果兼具。
arXiv:2507.23534v3 Announce Type: replace Abstract: Continual learning (CL) seeks to mitigate catastrophic forgetting when models are trained with seq…
新型FOGO优化器通过遗忘感知正交化机制，有效缓解持续学习中的灾难性遗忘问题
arXiv:2606.10406v1 Announce Type: cross Abstract: We argue that forgetting is not confined to continual learning but is a general optimization phenome…
用频谱有界骨干解决大模型持续微调中灾难性遗忘与跨任务改进的矛盾，模块化方案有新思路
arXiv:2606.00382v1 Announce Type: new Abstract: Sequential fine-tuning of large language models forces a choice: let the shared substrate keep learnin…
用进化策略对抗微调遗忘，提升LLM持续学习能力的新方法
arXiv:2605.30148v1 Announce Type: cross Abstract: Evolution Strategies (ES) has recently emerged as a competitive alternative to reinforcement learnin…
提出On-Policy Replay方法，解决持续监督微调中的灾难性遗忘问题，为LLM高效增量学习提供新思路。
arXiv:2605.29495v1 Announce Type: new Abstract: Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs…
将信任区域优化与元学习思想巧妙融合，提出持续学习新范式，在防止灾难性遗忘的同时实现高效知识迁移，实验数据丰富。
arXiv:2602.02417v2 Announce Type: replace Abstract: Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standar…
最新研究系统评估了大模型后训练中的“灾难性遗忘”，为提升模型持续学习能力提供关键方法论。
arXiv:2603.06610v2 Announce Type: replace Abstract: Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves…
arXiv最新论文提出稀疏正交参数调优方法，仅需微调少量正交参数即可有效缓解持续学习中的灾难性遗忘。
arXiv:2411.02813v3 Announce Type: replace Abstract: Continual learning methods based on pre-trained models (PTM) have recently gained attention which …
持续学习新突破：提出一致性保持混合专家模型，有效解决灾难性遗忘问题。
arXiv:2605.20247v1 Announce Type: new Abstract: Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs)…
Google内部定制LLM实战：万亿token数据集+中训策略，专攻企业软件工程场景。
Article URL: https://arxiv.org/abs/2605.16517 Comments URL: https://news.ycombinator.com/item?id=48202484 Points: 1 # Comments: 0
StrLoRA提出流式持续视觉指令微调新方法，有效缓解多模态大模型在序列任务中的灾难性遗忘。
arXiv:2605.16353v1 Announce Type: new Abstract: Continual Visual Instruction Tuning (CVIT) enables Multimodal Large Language Models to incrementally a…
提出近端在策略蒸馏方法，解决LLM后训练中知识注入与保留的冲突，理论与实验双验证。
arXiv:2603.01683v2 Announce Type: replace Abstract: Injecting new reasoning knowledge into Large Language Models (LLMs) via post-training often induce…