arXiv:2607. 14194v1 Announce Type: cross Abstract: Text-to-video (T2V) generators can synthesize realistic and temporally coherent videos, but controllably removing a target concept from a generator remains difficult.
arXiv:2609.36832v1 Announce Type: new Abstract: Text-to-video (T2V) diffusion models can generate realistic depictions of actions such as kicking, stabbing, and shooting, raising safety concerns that...
CleanVideo introduces a selective erasure framework for text-to-video diffusion models, addressing the challenge of removing undesired visual concepts from videos. The method uses a low-dimensional subspace intervention guided by a tri-modal gating mechanism that jointly considers spatiotemporal visual features, timestep signals, and textual semantics to decide where, when, and whether to intervene. Experiments on three video diffusion models demonstrate that CleanVideo effectively erases target concepts while preserving visual fidelity, temporal coherence, and outperforming existing baselines in both frame-level and video-level evaluations, even under concept-recovery attacks.
arXiv:2609.36598v1 Announce Type: new Abstract: A video can exhibit convincing motion and photorealism yet fail immediately when visual text collapses. Unlike generic scene content, visual text is un...
WanPE is a 397‑B parameter prompt‑enhancement model that learns director‑level cinematic planning from 1.05 M real‑world videos. It generates shot‑level cinematic plans through video‑grounded reverse construction and uses Semantic‑Consistency GRPO (SC‑GRPO) to maintain user intent across shots and time. In evaluations, WanPE improves human preference over raw prompts by up to 50.86 points for 30‑second videos and outperforms commercial offerings for shorter durations.
arXiv:2609.40356v1 Announce Type: cross Abstract: Recent video generation is increasingly realistic and controllable, yet video editing remains less developed, particularly for precise local edits th...
The paper introduces Event-Driven Refresh + Recurrence Memory (EDRRM) to improve Referring Video Object Segmentation (RVOS). EDRRM selectively re-invokes the Sa2VA model at stable change points, using an EMA‑smoothed event score from tracking cues and a recurrence memory that retrieves anchor frames via CLIP similarity. Experiments on Ref‑DAVIS17, MeViS, and ReVOS show that EDRRM maintains or surpasses J&F scores while reducing refresh calls and false‑positive failures, with modest overhead compared to Sa2VA inference.
arXiv:2609.37042v1 Announce Type: cross Abstract: Video Large Language Models (VideoLLMs) have achieved strong video understanding capabilities but incur substantial inference overhead due to the lar...
LongVU‑TTT is a causal test‑time training method for long‑video multimodal large language models that inserts a convolutional resampler with fast‑weight updates between the vision encoder and the LLM. The fast weights adapt per video and contextualize frame features before compression, while a hybrid selector keeps explicit visual evidence for downstream reasoning. Experiments show that TTT‑Conv outperforms TTT‑MLP and bidirectional Mamba2 on MLVU, and beats attention‑ and fixed‑state recurrent resamplers on three benchmarks, achieving competitive results on five video‑understanding tasks after reducing 512 frames to 128 LLM frames.
The paper introduces Cue2Narrate, a two‑stage pipeline that jointly predicts what visual events to narrate and when to insert the narration in long, untrimmed movie clips. It uses a dual‑head audio‑visual localizer to identify visual cue and narration windows, followed by a LoRA‑adapted vision‑language model that generates concise audio descriptions, trained with a Description Ranking Loss. The authors also present the LongLSMDC benchmark, comprising up to 8‑minute clips, and show that Cue2Narrate outperforms video‑only and audio‑only baselines by 5–12 points in average mAP and improves AD generation over fine‑tuned base VLMs.
Audio Description (AD) provides spoken narration of visual events during dialogue gaps, making movies accessible to visually impaired audiences. The problem requires determining both what (which visua...
OmniVBench introduces a comprehensive benchmark and a large-scale dataset for omni reference-to-video (R2V) generation, addressing gaps in existing evaluations that focus only on limited reference types and holistic consistency. The benchmark expands evaluation across 7 task families and 18 fine-grained tasks, covering content, motion, style, structure, narrative, and multi-reference settings, and employs a factor‑grounded evaluation with 12,172 checklist items to assess preservation, disentanglement, and routing of reference factors. The accompanying Omni‑R2V Dataset provides 340K training samples derived from professional video footage, along with task‑specific pipelines for scalable data construction, enabling broader research and revealing performance gaps in current R2V models.
arXiv:2510. 09608v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage.