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

• URL: http://arxiv.org/abs/2509.15800v1
• Date: Fri, 19 Sep 2025 09:27:24 GMT
• Title: ChronoForge-RL: Chronological Forging through Reinforcement Learning for Enhanced Video Understanding
• Abstract summary: We propose a novel video understanding framework, called ChronoForge-RL.<n>It combines Temporal Apex Distillation (TAD) and Key-Frame-aware Group Relative Policy Optimization (KF-GRPO)<n>Our proposed ChronoForge-RL achieves 69.1% on VideoMME and 52.7% on LVBench compared to baseline methods.
• Score: 2.28438857884398
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding [21.306038832082553]
  Multimodal Large Language Models (MLLMs) have shown strong performance on video question answering.<n>Their application to long-form videos is constrained by limited context length and computational cost.<n>We propose an evidence-driven sampling framework grounded in information theory.
  arXiv  Detail & Related papers  (2026-04-01T15:02:50Z)
• GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding [63.62445065977448]
  GIFT: Global Irreplaceability Frame Targeting is a training-free framework that selects frames by assessing their intrinsic irreplaceability.<n>We show that GIFT achieves a maximum average improvement of 12.5% across long-form video benchmarks on LLaVA-Video-7B compared to uniform sampling.
  arXiv  Detail & Related papers  (2026-03-26T06:21:41Z)
• K-frames: Scene-Driven Any-k Keyframe Selection for long video understanding [38.06179287702453]
  K-frames is a novel paradigm for scene-driven selection that preserves temporal continuity.<n>Instead of selecting individual frames, K-frames predicts semantically coherent, query-relevant clips.<n>K-frames provides an effective, interpretable, and plug-and-play solution for selection at various scales.
  arXiv  Detail & Related papers  (2025-10-14T06:23:22Z)
• FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning [65.42201665046505]
  Current video understanding models rely on fixed frame sampling strategies, processing predetermined visual inputs regardless of the specific reasoning requirements of each question.<n>This static approach limits their ability to adaptively gather visual evidence, leading to suboptimal performance on tasks that require broad temporal coverage or fine-grained spatial detail.<n>We introduce FrameMind, an end-to-end framework trained with reinforcement learning that enables models to dynamically request visual information during reasoning through Frame-Interleaved Chain-of-Thought (FiCOT)<n>Unlike traditional approaches, FrameMind operates in multiple turns where the model alternates between textual reasoning and active visual perception, using tools to extract
  arXiv  Detail & Related papers  (2025-09-28T17:59:43Z)
• DATE: Dynamic Absolute Time Enhancement for Long Video Understanding [8.720269393713451]
  Long video understanding remains a fundamental challenge for multimodal large language models (MLLMs)<n>We propose Dynamic Absolute Time Enhancement (DATE) that enhances temporal awareness in MLLMs.<n>We introduce a two-stage algorithm to ensure both semantic relevance and temporal coverage.
  arXiv  Detail & Related papers  (2025-09-11T08:49:22Z)
• KFFocus: Highlighting Keyframes for Enhanced Video Understanding [33.69757683688046]
  We propose KFFocus, a method designed to efficiently compress video tokens and emphasize the informative context present within video frames.<n>By assigning varying condensation ratios to frames based on their contextual relevance, KFFocus efficiently reduces token redundancy while preserving informative content details.<n>We also introduce a multimodal modeling module that encodes both the temporal relationships between video frames and the spatial structure within each frame.
  arXiv  Detail & Related papers  (2025-08-12T14:57:03Z)
• Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph Integration [24.337139909108117]
  "Less is more" phenomenon where excessive frames can paradoxically degrade performance due to context dilution.<n>"Visual echoes" yield significant temporal redundancy, which we term 'visual echoes'<n>"AFP" employs an adaptive hierarchical clustering algorithm on a fused ResNet-50 and CLIP feature space to identify and merge these echoes into single representatives.<n>Our full approach demonstrates a drastic reduction in required frames by up to 86.9% and total input tokens by up to 83.2%.
  arXiv  Detail & Related papers  (2025-08-05T11:31:55Z)
• ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding [71.654781631463]
  ReAgent-V is a novel agentic video understanding framework.<n>It integrates efficient frame selection with real-time reward generation during inference.<n>Extensive experiments on 12 datasets demonstrate significant gains in generalization and reasoning.
  arXiv  Detail & Related papers  (2025-06-02T04:23:21Z)
• ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding [52.050036778325094]
  We introduce ReFoCUS (Reinforcement-guided Frame Optimization for Contextual UnderStanding), a novel frame-level policy optimization framework.<n>ReFoCUS learns a frame selection policy via reinforcement learning, using reward signals derived from a reference LMM to reflect the model's intrinsic preferences for frames.<n>Our approach consistently improves reasoning performance across multiple video QA benchmarks.
  arXiv  Detail & Related papers  (2025-06-02T03:08:07Z)
• ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning [68.76048244253582]
  We introduce ViaRL, the first framework to leverage rule-based reinforcement learning (RL) for optimizing frame selection in video understanding.<n>ViaRL utilizes the answer accuracy of a downstream model as a reward signal to train a frame selector through trial-and-error.<n>ViaRL consistently delivers superior temporal grounding performance and robust generalization across diverse video understanding tasks.
  arXiv  Detail & Related papers  (2025-05-21T12:29:40Z)
• Temporally Consistent Referring Video Object Segmentation with Hybrid Memory [98.80249255577304]
  We propose an end-to-end R-VOS paradigm that explicitly models temporal consistency alongside the referring segmentation. Features of frames with automatically generated high-quality reference masks are propagated to segment remaining frames. Extensive experiments demonstrate that our approach enhances temporal consistency by a significant margin.
  arXiv  Detail & Related papers  (2024-03-28T13:32:49Z)
• TimeLens: Event-based Video Frame Interpolation [54.28139783383213]
  We introduce Time Lens, a novel indicates equal contribution method that leverages the advantages of both synthesis-based and flow-based approaches. We show an up to 5.21 dB improvement in terms of PSNR over state-of-the-art frame-based and event-based methods.
  arXiv  Detail & Related papers  (2021-06-14T10:33:47Z)
• All at Once: Temporally Adaptive Multi-Frame Interpolation with Advanced Motion Modeling [52.425236515695914]
  State-of-the-art methods are iterative solutions interpolating one frame at the time. This work introduces a true multi-frame interpolator. It utilizes a pyramidal style network in the temporal domain to complete the multi-frame task in one-shot.
  arXiv  Detail & Related papers  (2020-07-23T02:34:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.