论文 / 方法
8/12 20:00
Interactive autoregressive video generation demands both low-latency rollouts and precise online control. Few-step distillation accelerates generation by reducing denoising steps, while online control…
可信度 74交叉信源 1
话题
视频生成
共 107 条相关资讯 · 来自历史归档
Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation
论文 / 方法
8/12 20:00
Large-scale manipulation data is essential for robot learning, yet collecting robot demonstrations remains expensive and difficult to scale. Meanwhile, abundant egocentric human manipulation videos pr…
可信度 74交叉信源 1
论文 / 方法
8/11 20:02
LTX-2.5 brings frontier video generation to local NVIDIA hardware: 6.8-second clips, native multishot, day-one ComfyUI, open weights. The post The Video Production Stack Now Fits o…
AI 点评 · 本地开源视频生成首次媲美前沿水平，多镜头与ComfyUI支持将大幅降低创作门槛。
论文 / 方法
8/10 20:00
4D generation synthesizes dynamic 3D scenes from conditions such as text or images. Existing methods either reconstruct generated RGB videos with a separate 4D model or adapt a particular video genera…
论文 / 方法
8/9 20:00
We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It contains 1,253 expert-annotated examples spanning 60…
设计 / 产品
8/7 03:23
8月6日，阿里巴巴视频生成大模型Wan 3.0开启公测
模型 / Agent
8/7 00:51
Black Forest Labs 正式推出 FLUX 3 视频生成模型，研究人员发现 iCloud Private Relay 存在 IP 泄露风险等。 查看全文
模型 / Agent
8/5 13:06
Black Forest Labs has launched FLUX 3 Video, which generates Full HD clips up to 20 seconds long with native audio and lip-synced dialogue in more than 14 languages. It can also re…
设计 / 产品
8/5 07:05
10秒1080P，成本只要5毛钱
设计 / 产品
8/3 11:20
Open agentic prompt-expansion harness for image and video generation, bridging polished demos, public APIs, and deployable workflows.
可信度 74交叉信源 1
论文 / 方法
8/2 20:00
Controllable video generation models are increasingly being developed as world models. Accordingly, evaluating them in this role extends beyond the apparent appearance of generated videos to the inher…
设计 / 产品
8/1 10:33
狂刷3小时！
AI 点评 · AI巨头沉迷短视频，揭示人性与算法共谋的荒诞现实。
设计 / 产品
7/31 11:45
🎬 Curated MiniMax H3 video generation prompts — cinematic, ads, anime, UGC, product videos, and more. Includes playable examples and creator attribution.
可信度 74交叉信源 1
行业信号
7/31 10:27
文｜王毓婵 兰杰 编辑｜乔芊 36氪独家获悉，曾爱玲入职哔哩哔哩（下称“B站”），担任AI视频生成业务负责人，向CEO陈睿汇报。 36氪就此事向B站方面求证，对方暂无回应。 曾爱玲 B站此前已公开表示，AI投入主要聚焦视频理解、视频推荐和辅助视频创作等方向。曾爱玲入职后，或将参与相关业务。 曾爱玲的个人主页显示，她曾在腾讯混元&AI Lab团队和国际数字经济…
论文 / 方法
7/28 20:00
Text-to-video models have achieved remarkable visual quality, yet they still struggle to generate physically consistent dynamics because the temporal evolution of a scene must be inferred implicitly f…
行业信号
7/27 22:42
7 月 28 日，OpenAI CEO 萨姆 · 奥尔特曼表示，自己曾因研究 TikTok 的产品机制而逐渐沉迷，甚至在一个周六下午连续刷了约 3 个小时，最终不得不删除这款应用。 奥尔特曼在《Relentless》播客节目中称，OpenAI 此前筹备一款类似 TikTok、以 AI 生成视频为主要内容的社交应用 Sora。为了了解短视频平台的运行方式及用户…
AI 点评 · 科技领袖也难逃算法沉迷，凸显AI时代注意力争夺的普遍性与产品设计的力量。
论文 / 方法
7/27 20:00
Generation in video diffusion or flow models is computationally expensive due to the slow and iterative sampling process. Current state-of-the-art (SOTA) acceleration methods heavily rely on variation…
论文 / 方法
7/26 20:00
Progress in video generation keeps narrowing the visual gap between AI-generated and professionally produced footage, yet most benchmarks still draw prompts from web sources or LLM templates and score…
论文 / 方法
7/26 20:00
Diffusion transformers are essential for high-fidelity video generation, but long token sequences make attention a dominant inference bottleneck. Training-free dynamic sparse attention alleviates this…
行业信号
7/24 15:09
The AI lab Midjourney continues to expand its purview beyond image and video generation.
行业信号
7/24 00:00
可信度 74交叉信源 1
行业信号
7/23 17:07
The Media Router is a tool that automatically selects the best image, video, or audio generation model for a request based on whether a developer prioritizes quality, speed or cost…
AI 点评 · 解决生成式媒体模型选择难题，自动平衡质量、速度与成本，实用价值高。
论文 / 方法
7/22 20:00
Controllable video generation remains challenging due to the difficulty of specifying precise multi-object interactions using text prompts or motion-control inputs that primarily constrain pixel movem…
AI 点评 · 用图结构控制多对象交互，精准生成动态视频，突破文本与运动控制的局限。
论文 / 方法
7/22 20:00
We introduce SANA-Video 2.0, a hybrid video diffusion transformer instantiated at 5B and 14B scales under a unified architecture. Designed to generate high-quality video up to 720p on a single GPU, SA…
论文 / 方法
7/22 20:00
Recent conditional video generation models have shown promising potentials to transform 3D engine renderings, such as depth maps and untextured geometry, into photorealistic videos for gaming and imme…
设计 / 产品
7/22 13:17
Kandinsky WM 1.0 — a family of models for Physical AI. Image-to-video generation for autonomous driving, robotics & general physics.
可信度 74交叉信源 1
论文 / 方法一手源
7/21 00:00
Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiote…
论文 / 方法
7/20 20:00
Text-to-video generation has advanced significantly over the past five years through scaling of model size, data, and compute. Unlike model architecture, training data is often underexplored. Real-wor…
AI 点评 · 训练数据对文生视频影响被低估，该研究首次系统控制变量，揭示数据质量比规模更关键。
设计 / 产品
7/20 13:19
CLI & async Python library for free AI chat, image & video generation.
论文 / 方法
7/19 20:00
Current video generation models achieve impressive results in single-shot generation, yet remain limited in cinematic video generation, where coherent narratives and effective multi-shot composition r…
论文 / 方法
7/19 20:00
Human-object centric video personalization (HOCVP) is a core task within subject-driven video generation. However, existing methods suffer from two key limitations. First, most approaches focusing on…
论文 / 方法
7/19 20:00
Real-time multimodal applications, including voice agents and interactive video generation, compose heterogeneous models into pipelines whose efficient deployment requires application-specific decisio…
模型 / Agent
7/17 01:05
文 | 周鑫雨 编辑 | 张雨忻 智能涌现从多个独立信源处获悉， 截至 2026 年 7 月， 智谱的 ARR（年度经常性收入）已经达到 10 亿美元 。 截至发稿前，针对上述信息，智谱未回复。 过去一年，AI Coding 和视频生成模型已经成为全球造血能力最强的 AI 赛道。 海外，Anthropic 的 Claude Code 仅发布半年，ARR 就飙…
AI 点评 · 智谱ARR半年飙升15倍达10亿美元，印证AI商业化进入爆发期，行业格局加速重塑。
论文 / 方法
7/16 20:00
Modern video generation models are increasingly hailed as emerging world models with an internalized grasp of physical law. Yet existing benchmarks largely evaluate physical plausibility only at the o…
论文 / 方法
7/16 20:00
Video Diffusion Transformers process long spatio-temporal sequences, making self-attention the main bottleneck in high-resolution video generation. Training-free sparse attention reduces this cost, bu…
论文 / 方法
7/14 20:00
Building interactive worlds that respond coherently to player actions has long been a shared goal of computer graphics, games, and artificial intelligence. Recent video generative models provide a dat…
论文 / 方法
7/14 20:00
Multi-reference-to-audio-video (MR2AV) generation aims to generate coherent audio-video content conditioned on multiple references and textual instructions. Existing benchmarks mainly focus on text-dr…
论文 / 方法
7/14 20:00
Video generation increasingly relies on keyframe-based workflows, where creators specify a sequence of reference images to guide generation. Although recent models support multi-keyframe conditioning,…
论文 / 方法
7/14 20:00
Video generative models commonly rely on latent spaces learned by 3D Variational Autoencoders (3D-VAEs). However, conventional 3D-VAEs are mainly optimized for pixel-level reconstruction, which can li…
论文 / 方法
7/13 10:57
Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements for multi-view consis…
论文 / 方法
7/9 20:00
Driven by next-token prediction, NLP shifted from task-specific models into powerful generalist foundation models. What, then, is the equivalent catalyst needed to achieve a general-purpose model in c…
AI 点评 · 视频生成模型突破任务局限，迈向通用视觉，预示AI基础模型新范式。
设计 / 产品
7/9 05:47
视频生成的下一站，或是机器人大脑
论文 / 方法
7/8 20:00
Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences. Recent video generation models offer a reasoning path distinct f…
论文 / 方法
7/8 20:00
We propose OPSD-V, an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models. Existing few-step AR video generators can produce long videos with low…
行业信号
7/8 03:03
2026年，AI视频生成赛道已迈入全面爆发的成熟竞速期，Seedance 2.0 的出圈更是让AI视频变成一场“全民狂欢”。 短短两年间，AI视频从最初几秒的碎片化模糊画面，到如今分钟级长视频的连贯叙事、真实物理世界的精准还原，AI视频工具的迭代速度远超预期，AI视频工具完成了从“能用”到“好用”再到“专业”的三级跳，让创意落地的门槛降至新低——专业团队能用…
论文 / 方法
7/7 20:00
Despite the recent promise in robot control, video generative models suffer from a domain mismatch due to their primary focus on content creation. For example, their design inherently prioritizes visu…
论文 / 方法
7/6 20:00
Pretrained video generative models are promising backbones for visuomotor control, but their imagined futures often drift from task intent and are not reliably action-conditional. As a result, these m…
论文 / 方法
7/5 20:00
Recent advances in video diffusion models have enabled either long single-view generation through temporal autoregression, or short multi-view synthesis through bidirectional attention. However, gener…
设计 / 产品
7/3 15:27
IT之家 7 月 3 日消息，据 AI 普瑞斯消息，字节豆包视频生成模型 Seedance 2.5 预计 7 月 6 日上线体验中心，将在一周后开放 API 。 据IT之家此前报道， 字节豆包视频生成模型 Seedance 2.5 发布于 6 月 23 日，该模型目前处于全球企业内测阶段。 据介绍，Seedance 2.5 在单段生成长度、多素材参考、视频编…
AI 点评 · 字节视频模型快速从内测走向开放，行业落地节奏加快，值得关注其能力上限。
论文 / 方法
7/2 20:00
Recent progress in large-scale generative models has substantially advanced video generation, yet existing methods remain constrained by a rigid inference paradigm. Bidirectional diffusion models exce…
论文 / 方法
7/2 20:00
We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through voice instructions…
论文 / 方法
7/2 17:27
Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training quantization (PTQ)…
论文 / 方法
7/1 20:00
Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training quantization (PTQ)…
行业信号
6/30 03:24
过去几年，AI的战场在屏幕里。GPT系列用参数堆出了惊人的语言能力，Sora用视频生成震撼了全世界……但2026年，产业界达成了一组共识：2026年，是物理AI的元年。 年初拉斯维加斯CES上，英伟达CEO黄仁勋用一场演讲，17遍提及物理AI，用以宣布“物理AI的ChatGPT时刻已经来了”。这也是他近两年一直推崇备至的关键词。而在过去的2年多时间里，物理A…
论文 / 方法
6/29 20:00
Video World Models are interactive video generation models that predict future world states based on user actions and history video frames. A critical challenge in video world models is the lack of me…
行业信号
6/29 08:04
“每一代模型，我们都在押注一个非共识。” 文｜邓咏仪 编辑｜张雨忻 Sand.ai 创始人曹越，不太关心自己站在共识的哪一边。 Sand.ai 是一家视频生成模型和产品公司，成立于2024年1月。曹越创立Sand.ai 的故事也已经被讲过很多遍：在上一段创业“光年之外”戛然而止后，曹越很快就投入到 Sand.ai 的创业中，做视频生成模型。 彼时，市场的主流…
论文 / 方法
6/28 20:00
Interactive video generation systems for camera-controlled world exploration roll out growing sequences of latent video frames, entangling state transition with high-frequency observation synthesis. W…
论文 / 方法
6/28 20:00
Audio-video generation has recently gained unprecedented research attention, aiming to synthesize high-quality sounding video content with fine-grained synchronization and semantic alignment between t…
论文 / 方法
6/25 20:00
Video generation models have emerged as a promising paradigm for embodied world simulation. However, both general-domain video generators and robot-specific data fine-tuned models can still produce ph…
论文 / 方法
6/24 20:00
Video generation models aspire to simulate dynamic environments, and several benchmarks now evaluate memory consistency across frames. However, most assess consistency only while the target remains in…
论文 / 方法
6/23 20:00
Video generation models are increasingly capable of producing realistic videos, but they still struggle to generate videos that follow basic physical laws. Compounding this is a lack of reliable granu…
论文 / 方法
6/23 20:00
Synthesizing a novel-view video from a monocular reference video along a target camera trajectory requires both geometric consistency and motion fidelity with respect to the reference video. Existing…
论文 / 方法
6/23 20:00
Open domain subject-driven text-to-video (S2V) generation has drawn significant interest in academia and industry. Open domain S2V mainly involves two scenarios: in-domain, which requires retaining th…
论文 / 方法
6/23 20:00
Autoregressive video diffusion with causal diffusion transformers has emerged as a major paradigm for real-time streaming video generation and action-conditioned interactive world models. In this work…
设计 / 产品
6/22 07:30
论文 / 方法
6/21 20:00
Video diffusion models have enabled remarkable progress in video generation and editing. However, content preservation remains a core challenge: existing methods regenerate every pixel and often alter…
设计 / 产品
6/20 10:42
速度快7倍，成本只有Veo 3的1/2000
AI 点评 · 00后挑战行业巨头，用低成本实现7倍速度突破，颠覆音视频模型效率认知。
论文 / 方法
6/18 20:00
Generating a coherent multi-shot video requires structured cross-shot memory. Subject appearance, scene context, and speaker identity must persist across cuts. Existing approaches either train end-to-…
论文 / 方法
6/17 20:00
World Action Models (WAMs) are embodied predictive-action models that make a forecast of the future available to action. Recent WAMs repurpose large video generation models, and a parallel line relies…
论文 / 方法
6/16 20:00
Video generative models ( VGMs) have become a new frontier that can be used not just for video generation but for a multitude of downstream tasks, including world modeling. To advance these tasks, a g…
论文 / 方法
6/16 20:00
World Action Models (WAMs) commonly rely on video generation to bridge visual world modeling and robot control. However, video-based WAMs face three coupled limitations: dense multi-frame future token…
论文 / 方法
6/16 20:00
Precise 3D spatial orchestration in text-to-video generation remains a significant challenge, particularly for multi-object scenes where semantic layout and temporal dynamics are often entangled. Whil…
论文 / 方法
6/16 20:00
Streaming video generation is emerging as a new serving workload in which users interact with long-lived sessions that generate video progressively, chunk by chunk. Unlike offline video generation or…
设计 / 产品
6/16 04:36
Curated, original high-craft prompts for AI video ads (Seedance 2.0 / Veo 3 / Kling / Runway). Companion to HeyDreaming.
论文 / 方法
6/15 20:00
The shift from video generation to interactive world modeling places new demands on data: beyond captioned videos, world models require temporally aligned video-action-language trajectories grounded i…
论文 / 方法
6/15 20:00
As an increasing majority of global video content is consumed on social platforms for interactive social purposes, video generation models built for social worlds are important but largely overlooked…
论文 / 方法
6/14 20:00
Consistent video generation under editing operations requires persistence: when edits modify scene appearance or layout, subsequent generations should remain coherent across time and viewpoints. Howev…
论文 / 方法
6/14 20:00
We introduce Qwen-RobotWorld, a language-conditioned video world model for embodied intelligence. With natural language as a unified action interface, it predicts physically grounded future visual tra…
论文 / 方法
6/13 20:00
Re-rendering an existing video from a novel camera viewpoint requires the output to follow the prescribed camera trajectory while preserving the appearance and dynamics of the original scene across ev…
论文 / 方法
6/11 20:00
Long-form video generation requires recurring subjects to remain consistent across various shots, viewpoints, motions, and scene transitions. Existing temporal decomposition methods improve scalabilit…
论文 / 方法
6/10 20:00
Cloning camera motion from reference videos is an important task in video generation, as videos provide intuitive and precise control. Existing methods either directly use parametric representations t…
论文 / 方法
6/10 20:00
Generating avatar videos that are not merely visually similar to a target individual but behaviorally recognizable, faithfully reproducing their talking rhythm, gestural tendencies, and expression dyn…
论文 / 方法
6/9 20:00
Pretrained video generators are promising visual world models that exhibit emergent task-solving abilities; however, their reliance on detailed textual descriptions limits their direct use for plannin…
论文 / 方法
6/8 20:00
Autoregressive video generation has emerged as a powerful paradigm for World Action Models (WAMs). However, existing approaches suffer from slow training convergence and limited converged accuracy, pa…
论文 / 方法
6/8 20:00
Autoregressive video generators synthesize long videos by generating successive temporal segments, but their historical KV cache grows with video length. Existing bounded-cache methods reduce this cos…
论文 / 方法
6/8 20:00
Recent work has demonstrated that online reinforcement learning (RL) can substantially improve the quality and alignment of flow matching models for image and video generation. Methods such as Flow-GR…
论文 / 方法
6/7 20:00
Video generative models have become increasingly powerful, but long-range consistency remains challenging to achieve because even a few dozen frames require impractically long transformer sequence len…
设计 / 产品
6/6 20:51
Powerful AI magic tools for video editing, text-to-video generation, and VFX.
AI 点评 · 首个为Windows优化的RunwayML套件，让视频AI工具脱离云端限制，本地高效运行。
论文 / 方法
6/4 20:00
We introduce StreamForce, a streaming video generation framework that enables physically grounded control through continuous force inputs. Unlike prior video models that train separate models for diff…
论文 / 方法
6/3 20:00
Video generation models have made impressive strides in synthesizing visually compelling content, yet their outputs remain confined to the virtual domain. A natural question follows: how well do these…
论文 / 方法
6/3 20:00
Developing unified video generation and editing models capable of interpreting interleaved multimodal inputs is a promising yet challenging frontier field. Existing unified frameworks predominantly re…
论文 / 方法
6/3 20:00
Video generation models based on Diffusion Transformers (DiTs) have achieved remarkable performance in video synthesis, yet they suffer from high inference latency and computational costs due to the q…
论文 / 方法
6/2 20:00
We present Echo Infinity, an autoregressive (AR) framework towards real-time infinite video generation that employs a learnable evolving memory to dynamically filter, abstract, and compress any-length…
论文 / 方法
6/1 20:00
We present AAD-1, an Asymmetric Adversarial Distillation framework for One-step autoregressive image-to-video generation. State-of-the-art methods adopt adversarial distillation but suffer from motion…
模型 / Agent
6/1 05:32
36氪获悉，国内大厂首个开源龙虾类产品LobsterAI （网易有道龙虾）近日宣布上线图片生成与视频生成能力，并一次性接入包括Seedream、Seedance、HappyHorse、MiniMax-Hailuo在内的模型。
AI 点评 · 多模型矩阵整合，开源策略降低使用门槛，推动AI创作生态。
论文 / 方法
5/31 20:00
Autoregressive (AR) video diffusion enables variable-length synthesis, but long-horizon generation often suffers from accumulated errors and identity drift. For efficiency, existing methods commonly a…
AI 点评 · 提出通用检索增强框架，解决长视频生成的累积误差与身份漂移，兼顾效率与质量。
论文 / 方法
5/31 20:00
The recent "Reasoning with Video" paradigm utilizes Video Generation Models (VGMs) to generate temporally coherent visual trajectories to complete reasoning tasks. Although state-of-the-art VGMs excel…
AI 点评 · 自适应测试时优化让视觉语言模型成为视频推理的“好老师”，突破传统方法局限。
设计 / 产品
5/31 03:28
Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.
AI 点评 · 开源长视频RAG框架，突破生成时长限制，为AI视频创作提供新路径。
论文 / 方法
5/29 17:56
Text-to-video (T2V) generation faces challenging questions when generating videos with long horizons containing multiple events. Inspired by the intrinsics of the diffusion process, we probe video dif…
AI 点评 · 无需额外训练，即可精准控制多事件视频生成，大幅降低算力门槛，推动视频创作民主化。
论文 / 方法
5/28 20:00
Recent advances in video generative models have promoted rapid progress in controllable world models. However, maintaining fine-grained spatio-temporal consistency under long-horizon reasoning remains…
设计 / 产品
5/27 16:37
Runway Unlimited Pro Gen-3 with unlimited credits, premium models, motion brush, lip sync, upscale, and the complete creative suite—top subscription tier fully…
论文 / 方法
5/26 20:00
Spatial intelligence requires visual representations that capture both semantic objects and geometric structure in the physical world. To support this, two major pre-training schemes are now widely us…
AI 点评 · 对比视觉语言与视频生成模型，揭示哪种预训练范式更利于空间智能发展。
论文 / 方法
5/24 20:00
Real-time streaming joint audio-video generation for character animation requires a generator to speak the requested transcript, maintain visual identity across chunks, and run within a strict playbac…
AI 点评 · 解耦式编排实现长时流式音视频生成，突破实时角色动画的连贯性与延迟瓶颈。
论文 / 方法
5/21 20:00
Recent advances have substantially improved real-time interactive video generation in the autoregressive regime. However, most existing few-step autoregressive video generation methods, often distille…
AI 点评 · 提出单步自回归视频生成新范式，有望突破实时交互瓶颈，显著提升生成稳定性。
Skill / 资源
4/12 00:00
Diffusion models have demonstrated strong results on image synthesis in past years. Now the research community has started working on a harder task—using it for video generation. T…
AI 点评 · 视频生成新突破，扩散模型从图像迈向动态世界。
Skill / 资源
4/12 00:00
Diffusion models have demonstrated strong results on image synthesis in past years. Now the research community has started working on a harder task—using it for video generation. T…
可信度 74交叉信源 1