Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm without dynamic feedback, limiting the model's capacity to self-correct and adapt in complex scenarios. Recent efforts have attempted to address this limitation by incorporating reward models and reinforcement learning to enhance reasoning, or by employing tool-agent frameworks. However, these approaches face several challenges, including high annotation costs, reward signals that fail to capture real-time reasoning states, and low inference efficiency. To overcome these issues, we propose ReAgent-V, a novel agentic video understanding framework that integrates efficient frame selection with real-time reward generation during inference. These reward signals not only guide iterative answer refinement through a multi-perspective reflection mechanism--adjusting predictions from conservative, neutral, and aggressive viewpoints--but also enable automatic filtering of high-quality data for supervised fine-tuning (SFT), direct preference optimization (DPO), and group relative policy optimization (GRPO). ReAgent-V is lightweight, modular, and extensible, supporting flexible tool integration tailored to diverse tasks. Extensive experiments on 12 datasets across three core applications--video understanding, video reasoning enhancement, and vision-language-action model alignment--demonstrate significant gains in generalization and reasoning, with improvements of up to 6.9%, 2.1%, and 9.8%, respectively, highlighting the effectiveness and versatility of the proposed framework.

Modern multimodal large language models (MLLMs) can reason over hour-long video, yet their key-value (KV) cache grows linearly with time--quickly exceeding the fixed memory of phones, AR glasses, and edge robots. Prior compression schemes either assume the whole video and user query are available offline or must first build the full cache, so memory still scales with stream length. InfiniPot-V is the first training-free, query-agnostic framework that enforces a hard, lengthindependent memory cap for streaming video understanding. During video encoding it monitors the cache and, once a user-set threshold is reached, runs a lightweight compression pass that (i) removes temporally redundant tokens via Temporal-axis Redundancy (TaR) metric and (ii) keeps semantically significant tokens via Value-Norm (VaN) ranking. Across four open-source MLLMs and four long-video and streaming-video benchmarks, InfiniPot-V cuts peak GPU memory by up to 94%, sustains real-time generation, and matches or surpasses full-cache accuracy--even in multi-turn dialogues. By dissolving the KV cache bottleneck without retraining or query knowledge, InfiniPot-V closes the gap for on-device streaming video assistants.

We introduce MusclePose as an end-to-end learnable physics-infused 3D human pose estimator that incorporates muscle-dynamics modeling to infer human dynamics from monocular video. Current physics pose estimators aim to predict physically plausible poses by enforcing the underlying dynamics equations that govern motion. Since this is an underconstrained problem without force-annotated data, methods often estimate kinetics with external physics optimizers that may not be compatible with existing learning frameworks, or are too slow for real-time inference. While more recent methods use a regression-based approach to overcome these issues, the estimated kinetics can be seen as auxiliary predictions, and may not be physically plausible. To this end, we build on existing regressionbased approaches, and aim to improve the biofidelity of kinetic inference with a multihypothesis approach -- by inferring joint torques via Lagrange's equations and via muscle dynamics modeling with muscle torque generators. Furthermore, MusclePose predicts detailed human anthropometrics based on values from biomechanics studies, in contrast to existing physics pose estimators that construct their human models with shape primitives. We show that MusclePose is competitive with existing 3D pose estimators in positional accuracy, while also able to infer plausible human kinetics and muscle signals consistent with values from biomechanics studies, without requiring an external physics engine.

Sparse inertial measurement units (IMUs) provide a portable, low-cost solution for human motion tracking but struggle with error accumulation from drift and sensor noise when estimating joint position through time-based linear acceleration integration (i.e., indirect measurement). To address this, we propose ToF-IP, a novel 3D full-body pose estimation system that integrates Time-of-Flight (ToF) sensors with sparse IMUs. The distinct advantage of our approach is that ToF sensors provide direct distance measurements, effectively mitigating error accumulation without relying on indirect time-based integration. From a hardware perspective, we maintain the portability of existing solutions by attaching ToF sensors to selected IMUs with a negligible volume increase of just 3%. On the software side, we introduce two novel techniques to enhance multi-sensor integration: (i) a NodeCentric Data Integration strategy that leverages a Transformer encoder to explicitly model both intra-node and inter-node data integration by treating each sensing node as a token; and (ii) a Dynamic Spatial Positional Encoding scheme that encodes the continuously changing spatial positions of wearable nodes as motion-conditioned functions, enabling the model to better capture human body dynamics in the embedding space. Additionally, we contribute a 208-minute human motion dataset from 10 participants, including synchronized IMU-ToF measurements and groundtruth from optical tracking. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches such as PNP, achieving superior accuracy in tracking complex and slow motions like Tai Chi, which remains challenging for inertial-only methods.

Pairwise camera pose estimation from sparsely overlapping image pairs remains a critical and unsolved challenge in 3D vision. Most existing methods struggle with image pairs that have small or no overlap. Recent approaches attempt to address this by synthesizing intermediate frames using video interpolation and selecting key frames via a self-consistency score. However, the generated frames are often blurry due to small overlap inputs, and the selection strategies are slow and not explicitly aligned with pose estimation. To solve these cases, we propose Hybrid Video Generation (HVG) to synthesize clearer intermediate frames by coupling a video interpolation model with a pose-conditioned novel view synthesis model, where we also propose a Feature Matching Selector (FMS) based on feature correspondence to select intermediate frames appropriate for pose estimation from the synthesized results. Extensive experiments on Cambridge Landmarks, ScanNet, DL3DV-10K, and NAVI demonstrate that, compared to existing SOTA methods, PoseCrafter can obviously enhance the pose estimation performances, especially on examples with small or no overlap.

We introduce RFMPose, a novel generative framework for category-level 6D object pose estimation that learns deterministic pose trajectories through Riemannian Flow Matching (RFM). Existing discriminative approaches struggle with multihypothesis predictions (e.g., symmetry ambiguities) and often require specialized network architectures. RFMPose advances this paradigm through three key innovations: (1) Ensuring geometric consistency via geodesic interpolation on Riemannian manifolds combined with bi-invariant metric constraints; (2) Alleviating symmetryinduced ambiguities through Riemannian Optimal Transport for probability mass redistribution without ad-hoc design; (3) Enabling end-to-end likelihood estimation through Hutchinson trace approximation, thereby eliminating auxiliary model dependencies. Extensive experiments on the Omni6DPose demonstrate state-ofthe-art performance of the proposed method, with significant improvements of +4.1 in IoU25 and +2.4 in 5 2cm metrics compared to prior generative approaches. Furthermore, the proposed RFM framework exhibits robust sim-to-real transfer capabilities and facilitates pose tracking extensions with minimal architectural adaptation.

In this section, we introduce the construction pipeline for generating MVU-Eval QA pairs based on2 each data source.3 These questions include: (1) Object Recognition, (2)8 Spatial Understanding, (3) Counting, (4) Knowledge-intensive Reasoning, and (5) Temporal9 Reasoning. These generated questions, answers, and candidate choices are manually checked by10 humans. Pipelines for constructing video pairs are slightly different across datasets.11 By default, 2-6 videos are randomly sampled, regardless of their labels.

The advent of Multimodal Large Language Models (MLLMs) has expanded AI capabilities to visual modalities, yet existing evaluation benchmarks remain limited to single-video understanding, overlooking the critical need for multi-video understanding in real-world scenarios (e.g., sports analytics and autonomous driving). To address this significant gap, we introduce MVU-Eval, the first comprehensive benchmark for evaluating Multi-Video Understanding for MLLMs.

Recent studies have shown that agent-based systems leveraging large language models (LLMs) for key information retrieval and integration have emerged as a promising approach for long video understanding. However, these systems face two major challenges. First, they typically perform modeling and reasoning on individual frames, struggling to capture the temporal context of consecutive frames. Second, to reduce the cost of dense frame-level captioning, they adopt sparse frame sampling, which risks discarding crucial information. To overcome these limitations, we propose VideoLucy, a deep memory backtracking framework for long video understanding.

Recent 6D pose estimation methods demonstrate notable performance but still face some practical limitations. For instance, many of them rely heavily on sensor depth, which may fail with challenging surface conditions, such as transparent or highly reflective materials. In the meantime, RGB-based solutions provide less robust matching performance in low-light and texture-less scenes due to the lack of geometry information. Motivated by these, we propose SingRef6D, a lightweight pipeline requiring only a single RGB image as a reference, eliminating the need for costly depth sensors, multi-view image acquisition, or training view synthesis models and neural fields. This enables SingRef6D to remain robust and capable even under resource-limited settings where depth or dense templates are unavailable.