paper-with-me

Papers

InfLVG: Reinforce Inference-Time Consistent Long Video Generation with GRPO

2025-05-23 · Xueji Fang, Liyuan Ma, Zhiyang Chen, Mingyuan Zhou, Guo-Jun Qi

Recent advances in text-to-video generation, particularly with autoregressive models, have enabled the synthesis of high-quality videos depicting individual scenes. However, extending these models to generate long, cross-scene videos remains a significant challenge. As the context length grows during autoregressive decoding, computational costs rise sharply, and the model's ability to maintain consistency and adhere to evolving textual prompts deteriorates. We introduce InfLVG, an inference-time framework that enables coherent long video generation without requiring additional long-form video data. InfLVG leverages a learnable context selection policy, optimized via Group Relative Policy Optimization (GRPO), to dynamically identify and retain the most semantically relevant context throughout the generation process. Instead of accumulating the entire generation history, the policy ranks and selects the top-$K$ most contextually relevant tokens, allowing the model to maintain a fixed computational budget while preserving content consistency and prompt alignment. To optimize the policy, we design a hybrid reward function that jointly captures semantic alignment, cross-scene consistency, and artifact reduction. To benchmark performance, we introduce the Cross-scene Video Benchmark (CsVBench) along with an Event Prompt Set (EPS) that simulates complex multi-scene transitions involving shared subjects and varied actions/backgrounds. Experimental results show that InfLVG can extend video length by up to 9$\times$, achieving strong consistency and semantic fidelity across scenes. Our code is available at https://github.com/MAPLE-AIGC/InfLVG.

📄 PDF Abstract BibTeX arXiv:2505.17574

Code (1)

maple-aigc/inflvg 공식 구현

Tasks

Text-to-Video GenerationVideo Generation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference

2024-12-18 · Matthew Riemer, Gopeshh Subbaraj, Glen Berseth, Irina Rish

Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectively minimize regret. However, recent advances in machine learning involve larger n…

Reinforcement Learning (RL)

Inference Time Policy Optimization for Offline RL with Differentiable World Models

2026-03-23 · Rohan Deb, Stephen J. Wright, Arindam Banerjee arxiv

Offline Reinforcement Learning (RL) learns optimal policies from fixed datasets, training a policy once and deploying it at inference time without further refinement. Inspired by model predictive control (MPC), we introd…

Reinforcement LearningOffline RL

Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory

2025-12-08 · Sijia Li, Yuchen Huang, Zifan Liu, Zijian Li 외 arxiv

As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing approaches remain limited: full trajectories …

Reinforcement Learning

ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference

2023-12-19 · Ziqian Zeng, Yihuai Hong, Hongliang Dai, Huiping Zhuang 외

Early Exiting is one of the most popular methods to achieve efficient inference. Current early exiting methods adopt the (weighted) sum of the cross entropy loss of all internal classifiers during training, imposing all …

Natural Language Understanding

Statistical Inference After Adaptive Sampling for Longitudinal Data

2022-02-14 · Kelly W. Zhang, Lucas Janson, Susan A. Murphy

Online reinforcement learning and other adaptive sampling algorithms are increasingly used in digital intervention experiments to optimize treatment delivery for users over time. In this work, we focus on longitudinal us…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)