Imagen de Portada

C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Wei, Yuan, Hangjie, Zhao, Zixiang, Zhu, Yifan, Lu, Aojun, Feng, Tao, Sun, Yanan
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
por: Lu, Aojun, et al.
Publicado: (2025)

Make Continual Learning Stronger via C-Flat
por: Bian, Ang, et al.
Publicado: (2024)

Adapt before Continual Learning
por: Lu, Aojun, et al.
Publicado: (2025)

Revisiting Neural Networks for Continual Learning: An Architectural Perspective
por: Lu, Aojun, et al.
Publicado: (2024)

Why Does RL Generalize Better Than SFT? A Data-Centric Perspective on VLM Post-Training
por: Lu, Aojun, et al.
Publicado: (2026)

Continual GUI Agents
por: Liu, Ziwei, et al.
Publicado: (2026)

A Faster Path to Continual Learning
por: Li, Wei, et al.
Publicado: (2026)

Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models
por: Liu, Ziwei, et al.
Publicado: (2025)

CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
por: Chen, Shuhang, et al.
Publicado: (2026)

Frequency Autoregressive Image Generation with Continuous Tokens
por: Yu, Hu, et al.
Publicado: (2025)

ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
por: Feng, Tao, et al.
Publicado: (2025)

MambaVF: State Space Model for Efficient Video Fusion
por: Zhao, Zixiang, et al.
Publicado: (2026)

VideoMAR: Autoregressive Video Generatio with Continuous Tokens
por: Yu, Hu, et al.
Publicado: (2025)

Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning
por: Liu, Xinyu, et al.
Publicado: (2025)

RefComp: A Reference-guided Unified Framework for Unpaired Point Cloud Completion
por: Yang, Yixuan, et al.
Publicado: (2025)

Knowledge is Power: Advancing Few-shot Action Recognition with Multimodal Semantics from MLLMs
por: Xing, Jiazheng, et al.
Publicado: (2026)

DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation
por: Hu, Jie, et al.
Publicado: (2026)

NOAH: Learning Pairwise Object Category Attentions for Image Classification
por: Li, Chao, et al.
Publicado: (2024)

MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems
por: Chen, Shuhang, et al.
Publicado: (2025)

Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction
por: Wei, Yujie, et al.
Publicado: (2026)

Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling
por: Yuan, Bo, et al.
Publicado: (2024)

SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream
por: Zhu, Lin, et al.
Publicado: (2024)

Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models
por: Xing, Jiazheng, et al.
Publicado: (2026)

FitControler: Toward Fit-Aware Virtual Try-On
por: Yang, Lu, et al.
Publicado: (2025)

Towards Accurate and Robust Architectures via Neural Architecture Search
por: Ou, Yuwei, et al.
Publicado: (2024)

Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification
por: Zhu, Lanyun, et al.
Publicado: (2025)

Towards More Unified In-context Visual Understanding
por: Sheng, Dianmo, et al.
Publicado: (2023)

Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
por: Shen, Yang, et al.
Publicado: (2024)

FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing
por: Cai, Lingling, et al.
Publicado: (2024)

HDBFormer: Efficient RGB-D Semantic Segmentation with A Heterogeneous Dual-Branch Framework
por: Wei, Shuobin, et al.
Publicado: (2025)

Learning from Mistakes: Loss-Aware Memory Enhanced Continual Learning for LiDAR Place Recognition
por: Wang, Xufei, et al.
Publicado: (2025)

Revisiting Long-Tailed Learning: Insights from an Architectural Perspective
por: Pan, Yuhan, et al.
Publicado: (2024)

One-for-More: Continual Diffusion Model for Anomaly Detection
por: Li, Xiaofan, et al.
Publicado: (2025)

SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition
por: Lu, Feng, et al.
Publicado: (2025)

DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control
por: Wei, Yujie, et al.
Publicado: (2024)

SAMora: Enhancing SAM through Hierarchical Self-Supervised Pre-Training for Medical Images
por: Chen, Shuhang, et al.
Publicado: (2025)

Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability
por: Hao, Tianxiang, et al.
Publicado: (2023)

NODI: Out-Of-Distribution Detection with Noise from Diffusion
por: Zhou, Jingqiu, et al.
Publicado: (2024)

Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework
por: Shi, Linxiao, et al.
Publicado: (2026)

Ranking-aware Continual Learning for LiDAR Place Recognition
por: Wang, Xufei, et al.
Publicado: (2025)