COMET is a temporally grounded framework that systematically strengthens video MLLMs through explicit temporal representation, appearance-motion fusion, and direction-aware optimization and achieves consistent overall improvements with a pronounced motion-temporal bias.
Abstract
Video multimodal large language models have advanced significantly, yet fine-grained motion-temporal understanding remains fragile. The core bottleneck is not only sparse frame sampling, but also the lack of a complete temporal modeling pipeline for explicitly representing frame-to-frame change, enabling appearance-motion interaction, and optimizing temporal direction sensitivity. We propose COMET, a temporally grounded framework that systematically strengthens video MLLMs through explicit temporal representation, appearance-motion fusion, and direction-aware optimization. Architecturally, COMET introduces a temporal motion branch built on Taylor frame differences and injects its motion evidence into the appearance stream via temporal attention bias-enhanced cross-attention. For optimization, COMET combines temporal prior distillation with a forward-reverse TC-GRPO stage that turns temporal order into a direct learning signal and strengthens the model's use of directional motion patterns encoded by the temporal motion branch. The method achieves consistent overall improvements with a pronounced motion-temporal bias: on Qwen3-VL-8B, action-centric tasks (STAR, SSv2) improve by 4.9% on average, temporal reasoning tasks (NExT-QA, CLEVRER, LLaVA-178K) by 2.1% over BL-GRPO, while static perception tasks (PerceptionTest) remain on par. The same gain pattern also transfers to InternVL2.5-8B, indicating that COMET generalizes across model families.
This work introduces ActionLMM, a memory-augmented vision-language model for long-video action summarization that aligns visual and motion modalities through joint representation learning and leverages a novel dual-memory mechanism to retain both local motion details and global temporal structure.
Ruirui Li, Dari Abdullah Alrwoaily, Turgut Sofuyev et al.· International Conference on...· 0 citations
Motion-centric video reasoning is fundamental to interactive applications such as robotic manipulation and autonomous navigation. However, multimodal large language models (MLLMs) typically process videos through sparse uniform sampling to control visual-token and attention costs. This strategy may discard critical transitions between sampled frames, limiting reasoning about object movement, collisions, and causal interactions. To mitigate this issue, we propose Motion-as-Prompt (MaP), a track-guided cross-frame visual prompting framework. MaP recovers dense point trajectories, selects motion-informative frames, and marks the trajectories accumulated between consecutive sampled frames directly onto the visual inputs, making otherwise hidden displacement, direction changes, and interactions observable to frozen MLLMs. Experiments on CLEVRER and Something-Something-v2 show that MaP consistently improves average motion-reasoning accuracy, yielding gains of 4.2% and 8.9% for GPT-5.5, respectively. Notably, these improvements are obtained without degrading non-motion understanding, highlighting the robustness of MaP. These results demonstrate that MaP provides a simple and effective solution for enhancing motion-centric video reasoning without model training or architectural modification. Project page:https://github.com/SunVictor23/MaP.
Xikai Sun, Kebin Liu, Haotian Wang et al.· 0 citations
Multimodal Large Language Models (MLLMs) have achieved strong progress in video understanding, yet it remains challenging because the token limitation makes MLLMs difficult to capture temporally sparse evidence. Existing methods typically rely on uniform sampling, or frame selection, but these strategies usually optimize either broad temporal coverage or local relevance, making it difficult to preserve both global storyline context and fine-grained evidence. We propose VideoRouter(VR) that rethinks long-video understanding as coordinating complementary evidence views rather than selecting a single subset of frames. It first organizes each video into a question-agnostic temporal hierarchy, which partition the video into coarse-to-fine temporally coherent segments. In this hierarchy, upper-level nodes capture broad storyline context and event progression, while lower-level nodes preserve fine-grained local details and evidence-bearing moments. This naturally gives rise to two complementary views: a global view for coverage-oriented reasoning and a local view for detail-oriented evidence recovery. We further introduce a verification-guided router to determine which view is better supported by the selected evidence and select the final answer. We validate the effectiveness of the proposed design through extensive experiments, showing that the verification-guided router effectively coordinates global and local reasoning, and that, on VideoMME, our method outperforms state-of-the-art frame selection methods by 2.9 points, respectively, under the LLaVA-Video-7B backbone. We will release the code.
A cross-modal temporal alignment framework that combines a multi-scale temporal convolutional encoder with capsule-based dynamic routing, jointly optimizing temporal boundary prediction, cross-modal semantic alignment, and capsule diversity is proposed.
Gengtian Shi, Chenhao Wu, Shaofei Wang et al.· IEEE Access· 0 citations
Long-video understanding remains challenging for Multimodal Large Language Models (MLLMs) due to limited context length. Uniform sampling may miss crucial moments, while agent-based frame video understanding methods often evaluate frames independently, overlooking the temporal organization of videos. Ideally, evidence selection should mimic how humans answer questions about long videos: first locating the relevant segment from the global context, then zooming into local objects and details. We propose Temporal Tree of Thought T^3, a training-free framework for adaptive coarse-to-fine long-video understanding. T^3 constructs a question-agnostic hierarchical temporal tree via recursive temporally constrained clustering, where each node represents a contiguous segment with an informative key frame. During inference, T^3 performs an answer-retrieve-explore loop: it reasons over coarse representative frames, generates a search statement when evidence is insufficient, and expands relevant branches for finer-grained evidence. This process adaptively shifts the search target from temporal regions to specific objects and visual details to help video understanding. Experiments on VideoMME, LongVideoBench, and LVBench show that T^3 improves Qwen2.5-VL-7B by 0.5%, 4.6%, and 4.4%, respectively, under the same frame budget, demonstrating the effectiveness of structured temporal reasoning.
Vision-Language-Action (VLA) models have demonstrated effectiveness in robot manipulation, yet state-of-the-art models such as pi0.5 operate under a single-frame paradigm, limiting their ability to retain past observations and develop precise spatial perception. In this paper, we propose StreamPI, a streaming multimodal temporal modeling framework that equips single-frame VLA with temporal reasoning capability without introducing any additional parameters. One core design is instruction-anchored temporal modeling. It treats each (visual observation, language instruction) pair as an atomic temporal unit: bidirectional attention within each pair enables cross-modal fusion, while causal attention across pairs preserves autoregressive streaming inference. This ensures the language instruction serves as a persistent semantic anchor throughout task execution. To bridge the gap between synchronous training and asynchronous real-robot deployment, we introduce a andom-interval streaming training strategy: a proper inter-frame interval (e.g., every 3 frames) enables faster and smoother action execution. Beyond this, randomizing the interval further improves robustness to frame-timing perturbations, supporting asynchronous deployment in practice. Furthermore, by leveraging the length extrapolation capability of the LLM backbone, StreamPI seamlessly inherits pretrained single-frame weights and supports flexible single-frame and multi-frame inference. Experiments on real-robot tasks spanning memory-dependent and precise perception scenarios, as well as the simulation benchmark LIBERO, demonstrate that StreamPI outperforms pi0.5 across diverse tasks.
Zhe Liu, Jinghua Hou, Yuxiang Lu et al.· 0 citations
