Leum-VL Technical Report

• URL: http://arxiv.org/abs/2603.20354v1
• Date: Fri, 20 Mar 2026 12:48:26 GMT
• Title: Leum-VL Technical Report
• Abstract summary: A short video succeeds not simply because of what it shows, but because of how it schedules attention.<n>Existing models can describe scenes, answer event-centric questions, and read on-screen text, but they are far less reliable at identifying timeline-grounded units.<n>We propose SV6D, a representation framework that decomposes internet-native video into six complementary structural dimensions.
• Score: 16.577102201941152
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A short video succeeds not simply because of what it shows, but because of how it schedules attention -- yet current multimodal models lack the structural grammar to parse or produce this organization. Existing models can describe scenes, answer event-centric questions, and read on-screen text, but they are far less reliable at identifying timeline-grounded units such as hooks, cut rationales, shot-induced tension, and platform-facing packaging cues. We propose SV6D (Structured Video in Six Dimensions), inspired by professional storyboard practice in film and television production, a representation framework that decomposes internet-native video into six complementary structural dimensions -- subject, aesthetics, camera language, editing, narrative, and dissemination -- with each label tied to physically observable evidence on the timeline. We formalize a unified optimization objective over SV6D that combines Hungarian-matched temporal alignment, dimension-wise semantic label distance, and quality regularization. Building on this framework, we present Leum-VL-8B, an 8B video-language model that realizes the SV6D objective through an expert-driven post-training pipeline, further refined through verifiable reinforcement learning on perception-oriented tasks. Leum-VL-8B achieves 70.8 on VideoMME (w/o subtitles), 70.0 on MVBench, and 61.6 on MotionBench, while remaining competitive on general multimodal evaluations such as MMBench-EN. We also construct FeedBench, a benchmark for structure-sensitive short-video understanding. Our results indicate that the missing layer in video AI is not pixel generation but structural representation: grounded on the timeline, linked to visible evidence, and directly consumable by downstream workflows such as editing, retrieval, recommendation, and generation control, including text-heavy internet video formats with overlays and image-text layouts.

Related papers

• VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding [61.00809248898572]
  Long video understanding is a problem in which an agent reads the video turn by turn along the temporal axis, deciding at each turn how fast to watch, what evidence to retain, when to revisit uncertain segments, and when to stop and answer.<n>We propose textbfVideoScout, a multi-turn reasoning agent that instantiates the SEA paradigm through adaptive reasoning pacing.<n>Experiments on long video understanding and reasoning benchmarks demonstrate that our 7B model achieves strong performance compared with existing trained 7B agentic models.
  arXiv  Detail & Related papers  (2026-09-14T14:04:03Z)
• Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs [2.1665689529884697]
  Video understanding has rapidly evolved toward video large language models (VideoLLMs)<n>Their strong performance on captioning, question answering, retrieval and temporal grounding comes at a computation and memory cost that grows with frame count and context length.<n>This survey covers inference-efficiency mechanisms for visual and audiovisual VideoLLMs that report concrete reductions in parameter count, FLOPs per input, latency, memory, or visual and audio token count.
  arXiv  Detail & Related papers  (2026-09-09T15:50:39Z)
• Improving Spatial-Temporal Reasoning in Video-Language Models with Structured Video Prompting [0.0]
  Video-language models (VLMs) remain brittle on tasks that require tracking events over time and grounding answers in specific spatial regions.<n>We introduce structured video prompting, a training-free inference-time method that augments the input video with lightweight spatial structure and temporal structure.<n>We evaluate this approach on two complementary video benchmarks and two open video-language models.
  arXiv  Detail & Related papers  (2026-08-23T20:16:09Z)
• DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding [19.492762364136393]
  We present DynFrame, a framework that emits the temporal window and the sampling density as native tokens within a single autoregressive pass.<n>This learnable span-density retrieval enables acquiring multi-granularity evidence with a single retrieval step.
  arXiv  Detail & Related papers  (2026-05-26T08:16:16Z)
• TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions [64.27159505605312]
  This paper proposes Omni Captioning, a novel task designed to generate continuous, fine-grained, and structured audio-visual narratives with explicit timestamps.<n>To ensure dense semantic coverage, we introduce a six-dimensional structural schema to create "script-like" captions.<n>Extensive experiments demonstrate that TimeChat-Captioner-7B achieves state-of-the-art performance, surpassing Gemini-2.5-Pro.
  arXiv  Detail & Related papers  (2026-02-09T14:21:58Z)
• ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts [56.75723197779384]
  ARC-Hunyuan-Video is a multimodal model that processes visual, audio, and textual signals end-to-end for structured comprehension.<n>Our model is capable of multi-granularity timestamped video captioning and summarization, open-ended video question answering, temporal video grounding, and video reasoning.
  arXiv  Detail & Related papers  (2025-07-28T15:52:36Z)
• VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges [39.666361965650836]
  VideoLLaMB is a framework for long video understanding.<n> SceneTiling algorithm segments videos into coherent semantic units.<n>VideoLLaMB processes up to 320 frames using a single Nvidia A100 GPU.
  arXiv  Detail & Related papers  (2024-09-02T08:52:58Z)
• FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance [3.6519202494141125]
  We introduce FancyVideo, an innovative video generator that improves the existing text-control mechanism.<n>CTGM incorporates the Temporal Information (TII) and Temporal Affinity Refiner (TAR) at the beginning and end of cross-attention.<n>Our approach achieves state-of-the-art T2V generation results on the EvalCrafter benchmark.
  arXiv  Detail & Related papers  (2024-08-15T14:47:44Z)
• TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation [97.96178992465511]
  We argue that generated videos should incorporate the emergence of new concepts and their relation transitions like in real-world videos as time progresses. To assess the Temporal Compositionality of video generation models, we propose TC-Bench, a benchmark of meticulously crafted text prompts, corresponding ground truth videos, and robust evaluation metrics.
  arXiv  Detail & Related papers  (2024-06-12T21:41:32Z)
• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• HierVL: Learning Hierarchical Video-Language Embeddings [108.77600799637172]
  HierVL is a novel hierarchical video-language embedding that simultaneously accounts for both long-term and short-term associations. We introduce a hierarchical contrastive training objective that encourages text-visual alignment at both the clip level and video level. Our hierarchical scheme yields a clip representation that outperforms its single-level counterpart as well as a long-term video representation that achieves SotA.
  arXiv  Detail & Related papers  (2023-01-05T21:53:19Z)

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.