CE 4 L: Continual Ego, Exo, and Ego-Exo Learning

arXiv:2609.23492 · cs.CV, cs.AI · Submitted 2026-09-20 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-20

Updated: 2026-09-20

Comments: 23 pages. Accepted by ICML 2026

Code: https://github.com/AnAppleCore/CE4L

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 55× in this paper · explained in 2 episodes
• Fine-Tuning — 38× in this paper · explained in 5 episodes
• Accuracy — 37× in this paper · explained in 1 episode
• Continual Learning — 30× in this paper · explained in 2 episodes
• Regularization — 14× in this paper · explained in 3 episodes
• Adaptation — 10× in this paper · explained in 1 episode
• Generalization — 10× in this paper · explained in 13 episodes
• Alignment — 7× in this paper · explained in 1 episode
• Distillation — 7× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Embeddings — 4× in this paper · explained in 2 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• Transferability — 4× in this paper · explained in 4 episodes
• AUC — 3× in this paper · explained in 2 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Catastrophic Forgetting — 3× in this paper · explained in 5 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Domain Adaptation — 3× in this paper · explained in 5 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Representation Learning — 2× in this paper · explained in 2 episodes
• Video Incremental Subspace-routed Task Adapters — 2× in this paper
• Zero-Shot Transfer — 2× in this paper · explained in 4 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Action Flow — 1× in this paper · explained in 1 episode
• Action Groups — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Domain Shift — 1× in this paper · explained in 4 episodes
• Entanglement — 1× in this paper · explained in 4 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
• InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges
• LoRA: Low-Rank Adaptation of Large Language Models
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• Continual Reinforcement Learning by Planning with Online World Models
• VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
• OpenVLA: An Open-Source Vision-Language-Action Model
• The Power of Scale for Parameter-Efficient Prompt Tuning
• Prefix-Tuning: Optimizing Continuous Prompts for Generation
• R3M: A Universal Visual Representation for Robot Manipulation
• CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion
• MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning
• Bisecle: Binding and Separation in Continual Learning for Video Language Understanding
• InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision
• VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding
• Domain Generalizable Continual Learning
• EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos
• InternVideo: General Video Foundation Models via Generative and Discriminative Learning
• InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models