# EgoLCD: Egocentric Video Generation with Long Context Diffusion

arXiv: https://arxiv.org/abs/2512.04515 · HTML: https://mlsanity.com/paper/2512.04515/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 30 of 31)

- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://mlsanity.com/paper/2310.12190/) (2023)
- [Titans: Learning to Memorize at Test Time](https://mlsanity.com/paper/2501.00663/) (2024)
- [MAGI-1: Autoregressive Video Generation at Scale](https://mlsanity.com/paper/2505.13211/) (2025)
- [SkyReels-V2: Infinite-length Film Generative Model](https://mlsanity.com/paper/2504.13074/) (2025)
- [The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines](https://mlsanity.com/paper/2005.00343/) (2020)
- [Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models](https://mlsanity.com/paper/2504.12626/) (2025)
- [Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution](https://mlsanity.com/paper/2312.06640/) (2023)
- [3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding](https://mlsanity.com/paper/2507.23478/) (2025)
- [EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation](https://mlsanity.com/paper/2411.08380/) (2024)
- [Nav-R1: Reasoning and Navigation in Embodied Scenes](https://mlsanity.com/paper/2509.10884/) (2025)
- [VLA-R1: Enhancing Reasoning in Vision-Language-Action Models](https://mlsanity.com/paper/2510.01623/) (2025)
- [PresentAgent: Multimodal Agent for Presentation Video Generation](https://mlsanity.com/paper/2507.04036/) (2025)
- [Visual Perception by Large Language Model's Weights](https://mlsanity.com/paper/2405.20339/) (2024)
- [Hazards in Daily Life? Enabling Robots to Proactively Detect and Resolve Anomalies](https://mlsanity.com/paper/2411.00781/) (2024)
- [FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion](https://mlsanity.com/paper/2506.04648/) (2025)
- [UniVid: The Open-Source Unified Video Model](https://mlsanity.com/paper/2509.24200/) (2025)
- [Shaping embodied agent behavior with activity-context priors from egocentric video](https://mlsanity.com/paper/2110.07692/) (2021)
- [InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption](https://mlsanity.com/paper/2412.09283/) (2024)
- [DC-Scene: Data-Centric Learning for 3D Scene Understanding](https://mlsanity.com/paper/2505.15232/) (2025)
- [DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion](https://mlsanity.com/paper/2510.15264/) (2025)
- [MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots](https://mlsanity.com/paper/2511.17889/) (2025)
- [EvoVLA: Self-Evolving Vision-Language-Action Model](https://mlsanity.com/paper/2511.16166/) (2025)
- [StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes](https://mlsanity.com/paper/2509.16415/) (2025)
- [BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation](https://mlsanity.com/paper/2511.22973/) (2025)

## Built on by (most cited first, 5 of 5)

- [Efficient Video Diffusion Models: Advancements and Challenges](https://mlsanity.com/paper/2604.15911/) (2026)
- [A Mechanistic View on Video Generation as World Models: State and Dynamics](https://mlsanity.com/paper/2601.17067/) (2026)
- [E3C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control](https://mlsanity.com/paper/2605.26316/) (2026)
- [FlashSign: Pose-Free Guidance for Efficient Sign Language Video Generation](https://mlsanity.com/paper/2603.27915/) (2026)
- [FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation](https://mlsanity.com/paper/2609.38839/) (2026)

## Abstract (arXiv)

Generating long, coherent egocentric videos is difficult, as hand-object interactions and procedural tasks require reliable long-term memory. Existing autoregressive models suffer from content drift, where object identity and scene semantics degrade over time. To address this challenge, we introduce EgoLCD, an end-to-end framework for egocentric long-context video generation that treats long video synthesis as a problem of efficient and stable memory management. EgoLCD combines a Long-Term Sparse KV Cache for stable global context with an attention-based short-term memory, extended by LoRA for local adaptation. A Memory Regulation Loss enforces consistent memory usage, and Structured Narrative Prompting provides explicit temporal guidance. Extensive experiments on the EgoVid-5M benchmark demonstrate that EgoLCD achieves state-of-the-art performance in both perceptual quality and temporal consistency, effectively mitigating generative forgetting and representing a significant step toward building scalable world models for embodied AI. Code: https://github.com/AIGeeksGroup/EgoLCD. Website: https://aigeeksgroup.github.io/EgoLCD.