SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM

Large language models (LLMs) have demonstrated exceptional capabilities in text understanding, which has paved the way for their expansion into video LLMs (Vid-LLMs) to analyze video data. However, current Vid-LLMs struggle to simultaneously retain high-quality frame-level semantic information (i.e., a sufficient number of tokens per frame) and comprehensive video-level temporal information (i.e., an adequate number of sampled frames per video). This limitation hinders the advancement of Vid-LLMs towards fine-grained video understanding. To address this issue, we introduce the SlowFocus mechanism, which significantly enhances the equivalent sampling frequency without compromising the quality of frame-level visual tokens. SlowFocus begins by identifying the query-related temporal segment based on the posed question, then performs dense sampling on this segment to extract local high-frequency features. A multi-frequency mixing attention module is further leveraged to aggregate these local high-frequency details with global low-frequency contexts for enhanced temporal comprehension. Additionally, to tailor Vid-LLMs to this innovative mechanism, we introduce a set of training strategies aimed at bolstering both temporal grounding and detailed temporal reasoning capabilities. Furthermore, we establish FineAction-CGR, a benchmark specifically devised to assess the ability of Vid-LLMs to process fine-grained temporal understanding tasks. Comprehensive experiments demonstrate the superiority of our mechanism across both existing public video understanding benchmarks and our proposed FineAction-CGR.

KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs

Training-free video understanding leverages the strong image comprehension capabilities of pre-trained vision language models (VLMs) by treating a video as a sequence of static frames, thus obviating the need for costly video-specific training. However, this paradigm often suffers from severe visual redundancy and high computational overhead, especially when processing long videos. Crucially, existing keyframe selection strategies, especially those based on CLIP similarity, are prone to biases and may inadvertently overlook critical frames, resulting in suboptimal video comprehension. To address these significant challenges, we propose \textbf{KTV}, a novel two-stage framework for efficient and effective training-free video understanding. In the first stage, KTV performs question-agnostic keyframe selection by clustering frame-level visual features, yielding a compact, diverse, and representative subset of frames that mitigates temporal redundancy. In the second stage, KTV applies key visual token selection, pruning redundant or less informative tokens from each selected keyframe based on token importance and redundancy, which significantly reduces the number of tokens fed into the LLM. Extensive experiments on the Multiple-Choice VideoQA task demonstrate that KTV outperforms state-of-the-art training-free baselines while using significantly fewer visual tokens, \emph{e.g.}, only 504 visual tokens for a 60-min video with 10800 frames, achieving $44.8\%$ accuracy on the MLVU-Test benchmark. In particular, KTV also exceeds several training-based approaches on certain benchmarks.

Morphe: High-Fidelity Generative Video Streaming with Vision Foundation Model

Video streaming is a fundamental Internet service, while the quality still cannot be guaranteed especially in poor network conditions such as bandwidth-constrained and remote areas. Existing works mainly work towards two directions: traditional pixel-codec streaming nearly approaches its limit and is hard to step further in compression; the emerging neural-enhanced or generative streaming usually fall short in latency and visual fidelity, hindering their practical deployment. Inspired by the recent success of vision foundation model (VFM), we strive to harness the powerful video understanding and processing capacities of VFM to achieve generalization, high fidelity and loss resilience for real-time video streaming with even higher compression rate. We present the first revolutionized paradigm that enables VFM-based end-to-end generative video streaming towards this goal. Specifically, Morphe employs joint training of visual tokenizers and variable-resolution spatiotemporal optimization under simulated network constraints. Additionally, a robust streaming system is constructed that leverages intelligent packet dropping to resist real-world network perturbations. Extensive evaluation demonstrates that Morphe achieves comparable visual quality while saving 62.5\% bandwidth compared to H.265, and accomplishes real-time, loss-resilient video delivery in challenging network environments, representing a milestone in VFM-enabled multimedia streaming solutions.

Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning

Video large language models have demonstrated remarkable capabilities in video understanding tasks. However, the redundancy of video tokens introduces significant computational overhead during inference, limiting their practical deployment. Many compression algorithms are proposed to prioritize retaining features with the highest attention scores to minimize perturbations in attention computations. However, the correlation between attention scores and their actual contribution to correct answers remains ambiguous. To address the above limitation, we propose a novel \textbf{C}ontribution-\textbf{a}ware token \textbf{Co}mpression algorithm for \textbf{VID}eo understanding (\textbf{CaCoVID}) that explicitly optimizes the token selection policy based on the contribution of tokens to correct predictions. First, we introduce a reinforcement learning-based framework that optimizes a policy network to select video token combinations with the greatest contribution to correct predictions. This paradigm shifts the focus from passive token preservation to active discovery of optimal compressed token combinations. Secondly, we propose a combinatorial policy optimization algorithm with online combination space sampling, which dramatically reduces the exploration space for video token combinations and accelerates the convergence speed of policy optimization. Extensive experiments on diverse video understanding benchmarks demonstrate the effectiveness of CaCoVID. Codes will be released.

FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding

Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous perception. However, existing methods lack flexible adaptivity, leading to irreversible detail loss and context fragmentation. To resolve this, we propose FreshMem, a Frequency-Space Hybrid Memory network inspired by the brain's logarithmic perception and memory consolidation. FreshMem reconciles short-term fidelity with long-term coherence through two synergistic modules: Multi-scale Frequency Memory (MFM), which projects overflowing frames into representative frequency coefficients, complemented by residual details to reconstruct a global historical "gist"; and Space Thumbnail Memory (STM), which discretizes the continuous stream into episodic clusters by employing an adaptive compression strategy to distill them into high-density space thumbnails. Extensive experiments show that FreshMem significantly boosts the Qwen2-VL baseline, yielding gains of 5.20%, 4.52%, and 2.34% on StreamingBench, OV-Bench, and OVO-Bench, respectively. As a training-free solution, FreshMem outperforms several fully fine-tuned methods, offering a highly efficient paradigm for long-horizon streaming video understanding.

LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization

We present LongVPO, a novel two-stage Direct Preference Optimization framework that enables short-context vision-language models to robustly understand ultra-long videos without any long-video annotations. In Stage 1, we synthesize preference triples by anchoring questions to individual short clips, interleaving them with distractors, and applying visual-similarity and question-specificity filtering to mitigate positional bias and ensure unambiguous supervision. We also approximate the reference model's scoring over long contexts by evaluating only the anchor clip, reducing computational overhead. In Stage 2, we employ a recursive captioning pipeline on long videos to generate scene-level metadata, then use a large language model to craft multi-segment reasoning queries and dispreferred responses, aligning the model's preferences through multi-segment reasoning tasks. With only 16K synthetic examples and no costly human labels, LongVPO outperforms the state-of-the-art open-source models on multiple long-video benchmarks, while maintaining strong short-video performance (e.g., on MVBench), offering a scalable paradigm for efficient long-form video understanding.

Thinking with Comics: Enhancing Multimodal Reasoning through Structured Visual Storytelling

Chain-of-Thought reasoning has driven large language models to extend from thinking with text to thinking with images and videos. However, different modalities still have clear limitations: static images struggle to represent temporal structure, while videos introduce substantial redundancy and computational cost. In this work, we propose Thinking with Comics, a visual reasoning paradigm that uses comics as a high information-density medium positioned between images and videos. Comics preserve temporal structure, embedded text, and narrative coherence while requiring significantly lower reasoning cost. We systematically study two reasoning paths based on comics and evaluate them on a range of reasoning tasks and long-context understanding tasks. Experimental results show that Thinking with Comics outperforms Thinking with Images on multi-step temporal and causal reasoning tasks, while remaining substantially more efficient than Thinking with Video. Further analysis indicates that different comic narrative structures and styles consistently affect performance across tasks, suggesting that comics serve as an effective intermediate visual representation for improving multimodal reasoning.

DuoGen: Towards General Purpose Interleaved Multimodal Generation

Interleaved multimodal generation enables capabilities beyond unimodal generation models, such as step-by-step instructional guides, visual planning, and generating visual drafts for reasoning. However, the quality of existing interleaved generation models under general instructions remains limited by insufficient training data and base model capacity. We present DuoGen, a general-purpose interleaved generation framework that systematically addresses data curation, architecture design, and evaluation. On the data side, we build a large-scale, high-quality instruction-tuning dataset by combining multimodal conversations rewritten from curated raw websites, and diverse synthetic examples covering everyday scenarios. Architecturally, DuoGen leverages the strong visual understanding of a pretrained multimodal LLM and the visual generation capabilities of a diffusion transformer (DiT) pretrained on video generation, avoiding costly unimodal pretraining and enabling flexible base model selection. A two-stage decoupled strategy first instruction-tunes the MLLM, then aligns DiT with it using curated interleaved image-text sequences. Across public and newly proposed benchmarks, DuoGen outperforms prior open-source models in text quality, image fidelity, and image-context alignment, and also achieves state-of-the-art performance on text-to-image and image editing among unified generation models. Data and code will be released at https://research.nvidia.com/labs/dir/duogen/.

Hand3R: Online 4D Hand-Scene Reconstruction in the Wild

For Embodied AI, jointly reconstructing dynamic hands and the dense scene context is crucial for understanding physical interaction. However, most existing methods recover isolated hands in local coordinates, overlooking the surrounding 3D environment. To address this, we present Hand3R, the first online framework for joint 4D hand-scene reconstruction from monocular video. Hand3R synergizes a pre-trained hand expert with a 4D scene foundation model via a scene-aware visual prompting mechanism. By injecting high-fidelity hand priors into a persistent scene memory, our approach enables simultaneous reconstruction of accurate hand meshes and dense metric-scale scene geometry in a single forward pass. Experiments demonstrate that Hand3R bypasses the reliance on offline optimization and delivers competitive performance in both local hand reconstruction and global positioning.

Self-Supervised Learning from Structural Invariance

Joint-embedding self-supervised learning (SSL), the key paradigm for unsupervised representation learning from visual data, learns from invariances between semantically-related data pairs. We study the one-to-many mapping problem in SSL, where each datum may be mapped to multiple valid targets. This arises when data pairs come from naturally occurring generative processes, e.g., successive video frames. We show that existing methods struggle to flexibly capture this conditional uncertainty. As a remedy, we introduce a latent variable to account for this uncertainty and derive a variational lower bound on the mutual information between paired embeddings. Our derivation yields a simple regularization term for standard SSL objectives. The resulting method, which we call AdaSSL, applies to both contrastive and distillation-based SSL objectives, and we empirically show its versatility in causal representation learning, fine-grained image understanding, and world modeling on videos.