PDF 理解

MeanFlow promises high-quality generative modeling in few steps, by jointly learning instantaneous and average velocity fields. Yet, the underlying training dynamics remain unclear. We analyze the interaction between the two velocities and find: (i) well-established instantaneous velocity is a prerequisite for learning average velocity; (ii) learning of instantaneous velocity benefits from average velocity when the temporal gap is small, but degrades as the gap increases; and (iii) task-affinity analysis indicates that smooth learning of large-gap average velocities, essential for one-step generation, depends on the prior formation of accurate instantaneous and small-gap average velocities. Guided by these observations, we design an effective training scheme that accelerates the formation of instantaneous velocity, then shifts emphasis from short- to long-interval average velocity. Our enhanced MeanFlow training yields faster convergence and significantly better few-step generation: With the same DiT-XL backbone, our method reaches an impressive FID of 2.87 on 1-NFE ImageNet 256x256, compared to 3.43 for the conventional MeanFlow baseline. Alternatively, our method matches the performance of the MeanFlow baseline with 2.5x shorter training time, or with a smaller DiT-L backbone.

Recent Video-Language Models (VLMs) achieve promising results on long-video understanding, but their performance still lags behind that achieved on tasks involving images or short videos. This has led to great interest in improving the long context modeling of VLMs by introducing novel modules and additional complexity. In this paper, we take a different approach: rather than fine-tuning VLMs with the limited data available, we attempt to maximize the performance of existing models.To this end, we propose a novel visual prompting strategy specifically designed for long-video understanding. By combining multiple frames as panels into one image, we effectively trade off spatial details for temporal resolution.Our approach is training-free, parameter-free, and model-agnostic, and can be seamlessly integrated into existing VLMs.Extensive experiments on five established benchmarks across a wide range of model architectures, sizes, and context windows confirm the consistency of our approach. For the TimeScope (Long) dataset, which has the longest videos, the accuracy for video question answering is improved by up to 19.4%. Overall, our method raises the bar for long video understanding models. The code is available at https://fedespu.github.io/Video-Panels.

Recent advances in Multimodal Large Language Models (MLLMs) have led to significant progress in video understanding. Due to limited context windows and computational overhead, most MLLMs adopt uniform frame sampling. This approach is at high risk of missing critical visual information and constrains performance especially for long videos. To address this problem, we propose a lightweight frame selection method to identify keyframes and train it via a two-stage strategy. In the pre-training stage, the frame selector learns to model relevance between individual video frames and queries. In the reinforcement learning (RL) stage, we employ a hierarchical reward that evaluates selection quality at combination and frame levels. Through stochastic exploration of frame combinations, the selector learns to identify and retain frames that improve task performance rather than merely maximizing query relevance, which can be misleading. The selected frames serve as input to downstream MLLMs for video understanding and reasoning. Experimental results demonstrate the proposed selector improves performance of diverse downstream MLLMs across benchmarks spanning medium to long videos.

Long-form video understanding remains challenging due to the extended temporal structure and dense multimodal cues. Despite recent progress, many existing approaches still rely on hand-crafted reasoning pipelines or employ token-consuming video preprocessing to guide MLLMs in autonomous reasoning. To overcome these limitations, we introduce VideoARM, an agentic reasoning-over-hierarchical-memory paradigm for long-form video understanding. Instead of static, exhaustive preprocessing, VideoARM performs adaptive, on-the-fly agentic reasoning and memory construction. Specifically, VideoARM performs an adaptive and continuous loop of observing, thinking, acting, and memorizing, where a controller autonomously invokes tools to interpret the video in a coarse-to-fine manner, thereby substantially reducing token consumption. In parallel, a hierarchical multimodal memory continuously captures and updates multi-level clues throughout the operation of the agent, providing precise contextual information to support the controller in decision-making. Experiments on prevalent benchmarks demonstrate that VideoARM outperforms the state-of-the-art method, DVD, while significantly reducing token consumption for long-form videos.

Recent Vision-Language Models (VLMs) have made remarkable progress in multimodal understanding tasks, yet their evaluation on long video understanding remains unreliable. Due to limited frame inputs, key frames necessary for answering the question may be missing from the model's input. However, models that truthfully refuse to answer under such uncertainty are marked as incorrect, while those that guess may coincidentally produce the correct answer and thus obtain deceptively higher accuracy, leading to misleading evaluation results and encouraging models to guess rather than respond honestly. To address this issue, we introduce VirtueBench, a benchmark explicitly designed to assess model trustworthiness under uncertainty. VirtueBench constructs multiple frame-sampling levels for each video and provides ground truths that distinguish between answerable and unanswerable cases. Evaluations on 25 open-source and commercial VLMs reveal distinct refusal behaviors across different model families, with refusal accuracy ranging from over 70% in the best models to nearly 0% in the worst. Moreover, most models exhibit a substantial drop in refusal when the prompt does not explicitly require them to do so. These findings highlight the need for developing trustworthy VLMs for multimodal understanding, guided by benchmarks and leaderboards that emphasize reliability and trustworthiness.

Long video understanding is a key challenge that plagues the advancement of Multimodal Large language Models (MLLMs). In this paper, we study this problem from the perspective of visual memory mechanism, and proposed a novel and training-free approach, termed Flexible Memory (FlexMem). In principle, FlexMem aims to mimic human behavior of video watching, i.e., continually watching video content and recalling the most relevant memory fragments to answer the question. In this way, FlexMem can help MLLMs achieve video understanding of infinite lengths, unlike previous methods that process all video information at once and have input upper-limit. Concretely, FlexMem first consider the visual KV caches as the memory sources, and realize the effective memory transfer and writing via a dual-pathway compression design. Afterwards, FlexMem also explores different memory reading strategies for the diverse video understanding tasks, including the popular streaming one. To validate FlexMem, we apply it to two popular video-MLLMs, and conduct extensive experiments on five long video and one streaming video task. The experimental results show that on a single 3090 GPU, our FlexMem can achieve obvious improvements than existing efficient video understanding methods and process more than 1k frames, which also helps the base MLLMs achieve comparable or even better performance than SOTA MLLMs on some benchmarks, e.g. , GPT-4o and Gemini-1.5 Pro. Our code is released at: https://github.com/city1517/FlexMem.

Processing long-form videos with Video Large Language Models (Video-LLMs) is computationally prohibitive. Current efficiency methods often compromise fine-grained perception through irreversible information disposal or inhibit long-range temporal modeling via rigid, predefined sparse patterns. This paper introduces AdaSpark, an adaptive sparsity framework designed to address these limitations. AdaSpark first partitions video inputs into 3D spatio-temporal cubes. It then employs two co-designed, context-aware components: (1) Adaptive Cube-Selective Attention (AdaS-Attn), which dynamically selects a subset of relevant video cubes to attend for each query token, and (2) Adaptive Token-Selective FFN (AdaS-FFN), which selectively processes only the most salient tokens within each cube. An entropy-based (Top-p) selection mechanism adaptively allocates computational resources based on input complexity. Experiments demonstrate that AdaSpark significantly reduces computational load by up to 57% FLOPs while maintaining comparable performance to dense models and preserving fine-grained, long-range dependencies, as validated on challenging hour-scale video benchmarks.

In the context of long-term video understanding with large multimodal models, many frameworks have been proposed. Although transformer-based visual compressors and memory-augmented approaches are often used to process long videos, they usually compress each frame independently and therefore fail to achieve strong performance on tasks that require understanding complete events, such as temporal ordering tasks in MLVU and VNBench. This motivates us to rethink the conventional one-way scheme from perception to memory, and instead establish a feedbackdriven process in which past visual contexts stored in the context memory can benefit ongoing perception. To this end, we propose Question-guided Visual Compression with Memory Feedback (QViC-MF), a framework for long-term video understanding. At its core is a Question-guided Multimodal Selective Attention (QMSA), which learns to preserve visual information related to the given question from both the current clip and the past related frames from the memory. The compressor and memory feedback work iteratively for each clip of the entire video. This simple yet effective design yields large performance gains on longterm video understanding tasks. Extensive experiments show that our method achieves significant improvement over current state-of-the-art methods by 6.1% on MLVU test, 8.3% on LVBench, 18.3% on VNBench Long, and 3.7% on VideoMME Long. The code will be available at https://github.com/FujitsuResearch/QViC-MF/.

Long-video understanding remains challenging due to extreme temporal redundancy, sparse yet decisive events, and the instability of long-horizon reasoning in visual-language models (VLMs). Existing agent-based methods invoke external micro-tools but remain static, repeatedly rebuilding long chains of fine-grained operations for each task without acquiring reusable multi-step perceptual skills.We propose META, the first training-free agent capable of self-evolving its tool-augmented reasoning. META operates through dual Solving and Evolving loops: it analyzes its own tool trajectories, abstracts recurring multi-step patterns into reusable macro-tools, and distills failed executions into structured failure priors that refine tool usage. Through symbolic consolidation and pruning, META progressively shortens reasoning paths and acquires more general perceptual and temporal abilities--without any parameter updates. META achieves state-of-the-art performance on long-video benchmarks, demonstrating a scalable, model-agnostic paradigm for long-video understanding that can continually evolve without additional training.

Temporal Action Detection (TAD) in untrimmed videos poses significant challenges, particularly for Activities of Daily Living (ADL) requiring models to (1) process long-duration videos, (2) capture temporal variations in actions, and (3) simultaneously detect dense overlapping actions. Existing CNN and Transformer-based approaches, struggle to jointly capture fine-grained detail and long-range structure at scale. State-space Model (SSM) based Mamba offers powerful long-range modeling, but naive application to TAD collapses fine-grained temporal structure and fails to account for the challenges inherent to TAD. To this end, we propose Multi-Scale Temporal Mamba (MS-Temba), which extends Mamba to TAD with newly introduced dilated SSMs. Each Temba block, comprising dilated SSMs coupled with our proposed additional losses, enables the learning of discriminative representations across temporal scales. A lightweight Multi-scale Mamba Fuser then unifies these multi-scale features via SSM-based aggregation, yielding precise action-boundary localization. With only 17M parameters, MS-Temba achieves state-of-the-art performance on densely labeled ADL benchmarks TSU & Charades, and further generalizes to long-form video summarization, setting new state-of-the-art results on TVSum & SumMe.