Pack and Force Your Memory: Long-form and Consistent Video Generation
Long-form video generation presents a dual challenge: models must capture long-range dependencies while preventing the error accumulation inherent in autoregressive decoding. To address these challenges, we make two contributions. First, for dynamic context modeling, we propose MemoryPack, a learnable context-retrieval mechanism that leverages both textual and image information as global guidance to jointly model short- and long-term dependencies, achieving minute-level temporal consistency. This design scales gracefully with video length, preserves computational efficiency, and maintains linear complexity. Second, to mitigate error accumulation, we introduce Direct Forcing, an efficient single-step approximating strategy that improves training-inference alignment and thereby curtails error propagation during inference. Together, MemoryPack and Direct Forcing substantially enhance the context consistency and reliability of long-form video generation, advancing the practical usability of autoregressive video models.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencyVideo GenerationSimilar Papers 제목 키워드 기반
MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing
Long-term LLM agents must compress streams of past interactions into persistent memory before future queries are known. Existing evaluations usually measure final question-answering accuracy, which entangles memory writi…
Trust Your Memory: Verifiable Control of Smart Homes through Reinforcement Learning with Multi-dimensional Rewards
Large Language Models (LLMs) have become a key foundation for enabling personalized smart home experiences. While existing studies have explored how smart home assistants understand user queries to control devices in rea…
Reinforcement LearningSample Efficiency in Sparse Reinforcement Learning: Or Your Money Back
Sparse rewards present a difficult problem in reinforcement learning and may be inevitable in certain domains with complex dynamics such as real-world robotics. Hindsight Experience Replay (HER) is a recent replay memory…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)PackKV: Reducing KV Cache Memory Footprint through LLM-Aware Lossy Compression
Transformer-based large language models (LLMs) have demonstrated remarkable potential across a wide range of practical applications. However, long-context inference remains a significant challenge due to the substantial …
Computational EfficiencyMultibit Tries Packet Classification with Deep Reinforcement Learning
High performance packet classification is a key component to support scalable network applications like firewalls, intrusion detection, and differentiated services. With ever increasing in the line-rate in core networks,…
ClassificationDeep Reinforcement LearningIntrusion Detectionreinforcement-learning+2