# Affordance-First Decomposition for Continual Learning in Video-Language Understanding

arXiv: https://arxiv.org/abs/2512.00694 · HTML: https://mlsanity.com/paper/2512.00694/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 43 references that are in the map.
- First posted on arXiv 30 Nov 2025.

## Builds on (most cited first, 30 of 32)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2211.13218/) (2022)
- [LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding](https://mlsanity.com/paper/2410.17434/) (2024)
- [S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning](https://mlsanity.com/paper/2207.12819/) (2022)
- [Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters](https://mlsanity.com/paper/2403.11549/) (2024)
- [Progressive Prompts: Continual Learning for Language Models](https://mlsanity.com/paper/2301.12314/) (2023)
- [Revisiting the "Video" in Video-Language Understanding](https://mlsanity.com/paper/2206.01720/) (2022)
- [A Unified Continual Learning Framework with General Parameter-Efficient Tuning](https://mlsanity.com/paper/2303.10070/) (2023)
- [Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models](https://mlsanity.com/paper/2303.06628/) (2023)
- [Continual Vision-Language Representation Learning with Off-Diagonal Information](https://mlsanity.com/paper/2305.07437/) (2023)
- [TiC-CLIP: Continual Training of CLIP Models](https://mlsanity.com/paper/2310.16226/) (2023)
- [CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering](https://mlsanity.com/paper/2503.00413/) (2025)
- [Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models](https://mlsanity.com/paper/2407.05342/) (2024)
- [Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering](https://mlsanity.com/paper/1906.04229/) (2019)
- [RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning](https://mlsanity.com/paper/2007.06271/) (2020)
- [A Survey on Temporal Sentence Grounding in Videos](https://mlsanity.com/paper/2109.08039/) (2021)
- [CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation](https://mlsanity.com/paper/2308.07146/) (2023)
- [CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models](https://mlsanity.com/paper/2403.19137/) (2024)
- [Synthetic Data is an Elegant GIFT for Continual Vision-Language Models](https://mlsanity.com/paper/2503.04229/) (2025)
- [ConStruct-VL: Data-Free Continual Structured VL Concepts Learning](https://mlsanity.com/paper/2211.09790/) (2022)
- [VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges](https://mlsanity.com/paper/2409.01071/) (2024)
- [DAM: Dynamic Adapter Merging for Continual Video QA Learning](https://mlsanity.com/paper/2403.08755/) (2024)
- [Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models](https://mlsanity.com/paper/2403.09296/) (2024)
- [Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models](https://mlsanity.com/paper/2406.18868/) (2024)
- [Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting](https://mlsanity.com/paper/2410.00771/) (2024)
- [Bisecle: Binding and Separation in Continual Learning for Video Language Understanding](https://mlsanity.com/paper/2507.00469/) (2025)

## Built on by (most cited first, 4 of 4)

- [RoboRouter: Training-Free Policy Routing for Robotic Manipulation](https://mlsanity.com/paper/2603.07892/) (2026)
- [CL-VISTA: Benchmarking Continual Learning in Video Large Language Models](https://mlsanity.com/paper/2604.00677/) (2026)
- [IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval](https://mlsanity.com/paper/2606.08144/) (2026)
- [VOICE: A Vision-Omics Foundation Model Integrating Direct and Retrieval-Based Prediction of In-situ Single-Cell Gene Expression](https://mlsanity.com/paper/2608.08366/) (2026)

## Abstract (arXiv)

Continual learning for video--language understanding is increasingly important as models face non-stationary data, domains, and query styles, yet prevailing solutions blur what should stay stable versus what should adapt, rely on static routing/capacity, or require replaying past videos. We aim to explicitly specify where stability lives and where plasticity should be focused under realistic memory and privacy constraints. We introduce Affordance-First Decomposition (AFD): videos are mapped to slowly varying affordance tokens that form a shared, time-aligned substrate, while a lightweight, query-routed, conflict-aware scheduler concentrates adaptation and grows capacity only when needed. The substrate is stabilized via weak alignment and teacher consistency, and training uses question-only replay. AFD achieves state-of-the-art across protocols: 51.6% average accuracy with -1.8% forgetting on domain-incremental VideoQA, ViLCo R@1@0.5 of 29.6% (MQ) and 20.7% (NLQ) with 18.4% stAP@0.25 (VQ), and 39.5% accuracy with -1.6% forgetting on time-incremental iVQA. Overall, AFD offers an explicit, interpretable split between a stable interaction-centered substrate and targeted adaptation.