paper-with-me

홈 › Papers

ChronoForge-RL: Chronological Forging through Reinforcement Learning for Enhanced Video Understanding

2025-09-19 · Kehua Chen arxiv

Current state-of-the-art video understanding methods typically struggle with two critical challenges: (1) the computational infeasibility of processing every frame in dense video content and (2) the difficulty in identifying semantically significant frames through naive uniform sampling strategies. In this paper, we propose a novel video understanding framework, called ChronoForge-RL, which combines Temporal Apex Distillation (TAD) and KeyFrame-aware Group Relative Policy Optimization (KF-GRPO) to tackle these issues. Concretely, we introduce a differentiable keyframe selection mechanism that systematically identifies semantic inflection points through a three-stage process to enhance computational efficiency while preserving temporal information. Then, two particular modules are proposed to enable effective temporal reasoning: Firstly, TAD leverages variation scoring, inflection detection, and prioritized distillation to select the most informative frames. Secondly, we introduce KF-GRPO which implements a contrastive learning paradigm with a saliency-enhanced reward mechanism that explicitly incentivizes models to leverage both frame content and temporal relationships. Finally, our proposed ChronoForge-RL achieves 69.1% on VideoMME and 52.7% on LVBench compared to baseline methods, clearly surpassing previous approaches while enabling our 7B parameter model to achieve performance comparable to 72B parameter alternatives.

📄 PDF Abstract BibTeX arXiv:2509.15800

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyReinforcement LearningContrastive Learning

Similar Papers 제목 키워드 기반

Using Deep Reinforcement Learning for Zero Defect Smart Forging

2022-01-25 · Yunpeng Ma, Andreas Kassler, Bestoun S. Ahmed, Pavel Krakhmalev 외

Defects during production may lead to material waste, which is a significant challenge for many companies as it reduces revenue and negatively impacts sustainability and the environment. An essential reason for material …

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

An Explainable Deep Reinforcement Learning Model for Warfarin Maintenance Dosing Using Policy Distillation and Action Forging

2024-04-26 · Sadjad Anzabi Zadeh, W. Nick Street, Barrett W. Thomas

Deep Reinforcement Learning is an effective tool for drug dosing for chronic condition management. However, the final protocol is generally a black box without any justification for its prescribed doses. This paper addre…

Deep Reinforcement LearningManagement

Hybrid Ground-State Quantum Algorithms based on Neural Schrödinger Forging

2023-07-05 · Paulin de Schoulepnikoff, Oriel Kiss, Sofia Vallecorsa, Giuseppe Carleo 외

Entanglement forging based variational algorithms leverage the bi-partition of quantum systems for addressing ground state problems. The primary limitation of these approaches lies in the exponential summation required o…

Seeing Time: Benchmarking Chronological Reasoning and Shortcut Biases in Vision-Language Models

2026-06-04 · Haoyu Zhou, Qing Qing, Caichong Li, Qixin Zhang 외 arxiv

Recent advancements in Vision-Language Models (VLMs) have significantly enhanced their ability to interpret complex visual semantics, yet their capacity for chronological reasoning remains under-explored. In this paper, …

The Measure of Deception: An Analysis of Data Forging in Machine Unlearning

2025-09-06 · Rishabh Dixit, Yuan Hui, Rayan Saab arxiv

Motivated by privacy regulations and the need to mitigate the effects of harmful data, machine unlearning seeks to modify trained models so that they effectively ``forget'' designated data. A key challenge in verifying u…