{"total":26,"items":[{"citing_arxiv_id":"2606.30599","ref_index":17,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing","primary_cat":"cs.CV","submitted_at":"2026-06-29T17:38:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Goku provides a 2M-pair dataset for multi-task structural video editing, Goku-Edit model with MLLM and dual-branch design, and Goku-Bench yielding up to 8% gains in instruction following.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29020","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis","primary_cat":"cs.CV","submitted_at":"2026-06-27T17:38:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A new framework factorizes weather video synthesis into semantic appearance anchoring, physics-informed Gaussian particle simulation under gravity/wind/turbulence, and geometry-grounded alignment to produce diverse realistic weather effects.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23254","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SteerVTE: Seamless Video Text Editing with Style and Glyph Control","primary_cat":"cs.CV","submitted_at":"2026-06-22T12:37:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SteerVTE adds lightweight style and dual-granularity glyph adapters to a frozen video diffusion model, introduces a glyph-aware loss and progressive training, and releases a 1M synthetic dataset to enable accurate video text editing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22042","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"IDAG-Edit: Multi-Object Video Editing via Instance-Decoupled Attention and Guidance","primary_cat":"cs.CV","submitted_at":"2026-06-20T13:47:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"IDAG-Edit proposes a training-free method with Layout-guided Attention Modulation and Instance-level Masks for improved temporal consistency and multi-object controllability in diffusion-based video editing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01399","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion","primary_cat":"cs.CV","submitted_at":"2026-05-31T18:45:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PAI-Studio reformulates cinematic background replacement as in-context conditional generation inside a Diffusion Transformer with bidirectional attention, trained on a new 30K film-sourced dataset, and reports better motion consistency and relighting than prior open-source and commercial systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01362","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance","primary_cat":"cs.GR","submitted_at":"2026-05-31T17:33:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AlbedoEdit fine-tunes video foundation models to translate RGB videos into edited versions conditioned on user-edited first-frame albedo maps, trained on a new synthetic paired dataset for insertion, removal, and texture tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.25193","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SpongeBob: Sync-Aware Harmonious Audio-Visual Generative Editing","primary_cat":"cs.CV","submitted_at":"2026-05-24T17:50:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SpongeBob introduces the first end-to-end audio-visual joint editing framework using sync-aware bidirectional attention and context-aware modules, plus a new dataset and benchmark, claiming 30% Sync-C and 12.5% Ctx-F1 gains over baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.24674","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing","primary_cat":"cs.CV","submitted_at":"2026-05-23T17:22:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RVEDiT improves DiT-based video editing by granularity-routed token conditioning and reference-anchored attention alignment to achieve better temporal coherence and localized edits.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23245","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion","primary_cat":"cs.CV","submitted_at":"2026-05-22T05:28:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SimInsert is a training-free video object insertion technique that decouples the task into single-frame editing and semantic motion description, using image-to-video diffusion models with non-invasive guidance to achieve spatio-temporal coherence.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23192","ref_index":118,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing","primary_cat":"cs.CV","submitted_at":"2026-05-22T03:19:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A new keyframe selection framework combines structural, tracking, and semantic criteria to select reliable anchor frames for diffusion-based video editing under occlusion.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21466","ref_index":35,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:52:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"StreamEdit enables high-quality training-free video editing by adapting streaming video generation models with dual-branch fast sampling, self-attention bridge, cross-attention grounding, source-oriented guidance, and visual prompting, outperforming prior methods in few-step regimes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18678","ref_index":52,"ref_count":4,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","primary_cat":"cs.CV","submitted_at":"2026-05-18T17:18:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Lance presents a dual-stream mixture-of-experts model with modality-aware positional encoding and staged multi-task training that outperforms prior open-source unified models on image and video generation while keeping strong understanding performance.","context_count":2,"top_context_role":"background","top_context_polarity":"background","context_text":"More recent video-focused frameworks, including Omni-Video [99], UniVideo [119], and TV2TV [36], move closer to genuinely unified video models by jointly addressing video understanding, generation, editing, or interleaved language-video modeling under a more integrated architecture. Meanwhile, several task-unified video editing frameworks, such as AnyV2V [52], VACE [47], UNIC [141], EditVerse [48], and FullDiT [49], expand the controllability of video generation, but typically do not aim for full understanding-generation unification within a single multimodal model. Overall, multi-task synergy for image-video unified multimodal modeling remains to be further explored. 3 Methodology The core idea of Lance is that broad multi-task learning can further unlock the potential of unified multimodal"},{"citing_arxiv_id":"2605.17312","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformers","primary_cat":"cs.CV","submitted_at":"2026-05-17T08:03:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VISTA introduces a new synthetic triplet dataset and diffusion-transformer framework with style adapter that jointly models style, content, and motion to achieve state-of-the-art video style transfer.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17019","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"StreamingEffect: Real-Time Human-Centric Video Effect Generation","primary_cat":"cs.CV","submitted_at":"2026-05-16T14:45:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14136","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion","primary_cat":"cs.CV","submitted_at":"2026-05-13T21:39:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TeDiO regularizes temporal diagonals in diffusion transformer attention maps to produce smoother video motion while keeping per-frame quality intact.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12271","ref_index":24,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm","primary_cat":"cs.CV","submitted_at":"2026-05-12T15:35:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Proposes V2V-Zero, a training-free framework replacing text conditioning with VLM final-layer hidden states from visual pages, achieving 0.85 on GenEval and 32.7/100 on new Simple-V2V Bench across models including video extension.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"pattern recognition, pages 18392-18402, 2023. [22] Michal Geyer, Omer Bar-Tal, Shai Bagon, and Tali Dekel. Tokenflow: Consistent diffusion features for consistent video editing.arXiv preprint arXiv:2307.10373, 2023. [23] Max Ku, Cong Wei, Weiming Ren, Harry Yang, and Wenhu Chen. Anyv2v: A tuning-free framework for any video-to-video editing tasks.arXiv preprint arXiv:2403.14468, 2024. [24] Lvmin Zhang, Anyi Rao, and Maneesh Agrawala. Adding conditional control to text-to-image diffusion models. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 3836-3847, 2023. [25] Chong Mou, Xintao Wang, Liangbin Xie, Yanze Wu, Jian Zhang, Zhongang Qi, and Ying Shan. T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion"},{"citing_arxiv_id":"2605.04569","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","primary_cat":"cs.CV","submitted_at":"2026-05-06T07:15:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LIVEditor-14B applies a new sparse attention method (ISA) that prunes context and uses query-sharpness routing to cut attention latency ~60% with no loss in editing quality on standard benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21921","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Context Unrolling in Omni Models","primary_cat":"cs.CV","submitted_at":"2026-04-23T17:58:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Omni is a multimodal model whose native training on diverse data types enables context unrolling, allowing explicit reasoning across modalities to better approximate shared knowledge and improve downstream performance.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"edit↑Fid S.×102↑YN↑MC↑ ∪↑ ∩↑Acc↑ Source Videos 0.00∞0.00 100.00 24.59 19.87 93.76 - - - - - TokenFlow [13] 35.62 19.06 263.61 72.51 26.46 21.15 89.00 19.36 35.51 36.68 18.18 27.43 DMT [47] 85.95 14.71 404.60 51.64 26.6621.4482.30 34.78 62.06 62.9833.86 48.42 VidToMe [26] 22.37 21.15 263.91 70.69 26.84 21.0590.0620.03 33.50 36.20 17.34 26.77 AnyV2V [23] 71.36 15.90 348.59 50.77 24.89 19.72 60.36 30.62 45.42 48.96 27.09 38.02 VideoGrain [46]12.40 27.05185.21 79.13 25.69 20.31 88.57 30.50 43.97 44.30 30.17 37.23 Pyramid-Edit [25] 28.65 20.84 276.59 71.72 26.82 20.20 80.59 33.67 54.01 56.36 31.31 43.84 Wan-Edit [25] 12.53 25.57 94.61 82.5526.39 21.23 89.43 41.4152.53 55.72 38.2246.97 O mni 34.94 22."},{"citing_arxiv_id":"2604.19741","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CityRAG: Stepping Into a City via Spatially-Grounded Video Generation","primary_cat":"cs.CV","submitted_at":"2026-04-21T17:59:03+00:00","verdict":"CONDITIONAL","verdict_confidence":"UNKNOWN","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PlayCoder combines a repository-aware coding agent with a vision-based GUI testing agent and an automated program repair loop to detect and fix silent logic errors in LLM-generated interactive application code.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"It shows driving simulations as one of its applications. 2)V2V+posecontrol.WeuseanothervariantofGen3CandTrajectoryCrafter[68]. Both methods take a dynamic input video and re-render it given a different tra- jectory. For our setup, we provide the conditioning frames and re-render with the target camera trajectory. 3) V2V + style transfer. We use AnyV2V [32], a method that transforms a video to the style of an image. We provide the conditioning frames as the input video, and the first image as the style reference. Evaluation data.From the collected 10 cities, we filtered the data for chal- lenging trajectories with turns and complex camera movement, and randomly selected 10 per city for evaluation across diverse conditions."},{"citing_arxiv_id":"2604.19193","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"How Far Are Video Models from True Multimodal Reasoning?","primary_cat":"cs.CV","submitted_at":"2026-04-21T08:04:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"1: Overview of CL VG-Bench. Our framework evaluates video models via Con- text Learning in Video Generation across arbitrary modalities (Text, Image, Audio, Video). It systematically probes reasoning capabilities across6categories and47sub- categories, which provides a roadmap for general-purpose video models. transitioned from simple, single-reference conditioning [32,35,37,39,51,65,86] to accommodating multi-subject and multimodal references [26,72]. Concurrently, theprimaryfocusofthesetasksisshiftingfromprioritizingsheervisualfidelityto emphasizing broader reasoning capabilities. Despite this immense potential and the surging interest in video reasoning, the community still lacks a systematic formulation and comprehensive benchmarking for these emerging paradigms."},{"citing_arxiv_id":"2604.13509","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer","primary_cat":"cs.CV","submitted_at":"2026-04-15T05:52:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RTR-DiT distills a bidirectional DiT teacher into an autoregressive few-step model using Self Forcing and Distribution Matching Distillation, plus a reference-preserving KV cache, to enable stable real-time text- and reference-guided video stylization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13425","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VibeFlow: Versatile Video Chroma-Lux Editing through Self-Supervised Learning","primary_cat":"cs.CV","submitted_at":"2026-04-15T02:51:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VibeFlow performs versatile video chroma-lux editing in zero-shot fashion by self-supervised disentanglement of structure and color-illumination cues inside pre-trained video models, plus residual velocity fields and consistency regularization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.11789","ref_index":74,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","primary_cat":"cs.CV","submitted_at":"2026-04-13T17:55:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"This review organizes literature on large multimodal models and object-centric vision into four themes—understanding, referring segmentation, editing, and generation—while summarizing paradigms, strategies, and challenges like instance permanence and consistent interaction.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"TokenFlow[ 48] enforces temporal consistency through diffusion feature manipulation, propagating keyframe features to intermediate frames via linear combination.ContextFlow[30] addresses background conflicts through adaptive context enrichment mechanisms that preserve scene coherence during object editing. This facilitates intelligent blending of edited objects with dynamic backgrounds.Anyv2v[ 74] offers a tuning- free framework for arbitrary video-to-video translations, balancing spatial editing precision with temporal coherence. 5.3.2 Subject-driven Video Generation DreamVideo-2[ 184] realizes zero-shot subject-driven video customization through attention-based identity preservation and spatial motion guidance, facilitating seamless integration of personalized objects."},{"citing_arxiv_id":"2604.08646","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation","primary_cat":"cs.CV","submitted_at":"2026-04-09T17:59:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"InsEdit adapts a video diffusion backbone for text-instruction video editing via Mutual Context Attention, achieving SOTA open-source results with O(100K) data while also supporting image editing.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"2 Instruction-based Image Editing and Unified Visual Editing Instruction-based image editing establishes the basic source and instruction setup for language-guided visual manipulation. A rep- resentative milestone is InstructPix2Pix [3], and more recent works further improve data quality, editing ability, reward modeling, in- struction diversity, and benchmark coverage [ 18, 23, 25, 34, 43]. These studies provide a useful foundation for instruction follow- ing, but they work on static images and therefore do not address consistency over time or edits that happen only in part of a video. An emerging line of work tries to unify visual understanding, generation, and editing across different modalities. Representative examples include UniWorld [21], DreamVE [40], InstructX [26], Uni-"},{"citing_arxiv_id":"2510.01186","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ASTRA: Let Arbitrary Subjects Transform in Video Editing","primary_cat":"cs.CV","submitted_at":"2025-10-01T17:59:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ASTRA is a plug-and-play training-free method for precise multi-subject video editing that uses prompt-guided multimodal alignment and prior-based mask retargeting to avoid attention dilution and boundary issues.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.04434","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer","primary_cat":"cs.CV","submitted_at":"2025-09-04T17:53:03+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Durian introduces a dual-reference diffusion model trained via self-reconstruction on video frames to enable cross-identity attribute transfer in portrait animations, supporting multi-attribute composition and interpolation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}