Papersby Glyph

Notable data and AI papers

Papers627 Labs45

627 papers · 45 labs

MotionStream: Real-Time Video Generation with Interactive Motion Controls research paper by Adobe, 2025

Adobe · Multimodal and robotics · Nov 3, 2025 · 88 citations · 33 upvotes · unverified

MotionStream enables real-time video generation with sub-second latency and up to 29 FPS by distilling a text-to-video model with motion control into a causal student using Self Forcing with Distribution Matching Distillation and sliding-window causal attention with attention sinks.

By Joonghyuk Shin, Zhengqi Li, Richard Zhang and 4 more · arXiv 2511.01266 · PDF · Code

UnverifiedHugging Face's summary; not yet checked by hand.

More from Adobe

Multimodal and roboticsUnverifiedNov 2, 2026MoviEdit: Long-form Multi-Shot Video Editing Made EasyMoviEdit is a framework and benchmark for editing long videos across multiple camera shots and changing scenes.

Adobe75 upvotesRead →Applied AIUnverifiedSep 18, 2026Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic DesignDesigner-RSI improves agentic graphic design by continually refining a procedural memory of skills based on user traffic and execution feedback.

Adobe1 citations34 upvotesRead →Multimodal and roboticsUnverifiedAug 7, 2026Beyond Starry Night: Shortcut-Aware Control-State Planning for Artist-Grounded Text to Image GenerationAtelier improves artist-grounded image generation by translating vague artistic intent into explicit control states that separate scene content from style, reducing reliance on stereotypical shortcuts.

Adobe1 citations28 upvotesRead →Multimodal and roboticsUnverifiedMar 18, 2026LoST: Level of Semantics Tokenization for 3D ShapesLevel-of-Semantics Tokenization (LoST) improves 3D shape generation by ordering tokens based on semantic salience and using a novel relational alignment loss for better reconstruction and efficiency.

Adobe4 citations32 upvotesRead →Multimodal and roboticsUnverifiedMar 17, 2026WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric RepresentationVideo diffusion transformers enhanced with camera pose representation enable precise action control and long-term 3D consistency in interactive gaming environments through physics-based action spaces and geometric grounding.

Adobe14 citations61 upvotesRead →Multimodal and roboticsUnverifiedJan 22, 2026Memory-V2V: Augmenting Video-to-Video Diffusion Models with MemoryMemory-V2V enhances multi-turn video editing by maintaining cross-consistency through explicit memory mechanisms and efficient token compression in video-to-video diffusion models.

Adobe3 citations28 upvotesRead →Multimodal and roboticsUnverifiedDec 19, 2025Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and EditingLatent diffusion models using representation encoder features face challenges in semantic compactness and pixel-level reconstruction, which are addressed through a semantic-pixel reconstruction objective that enables compact yet semantically rich representations for unified text-to-image and image editing tasks.

Adobe28 citations37 upvotesRead →Multimodal and roboticsUnverifiedDec 12, 2025V-RGBX: Video Editing with Accurate Controls over Intrinsic PropertiesV-RGBX presents an end-to-end framework for intrinsic-aware video editing that combines video inverse rendering, photorealistic video synthesis, and keyframe-based editing with physically grounded intrinsic channel manipulation.

Adobe7 citations30 upvotesRead →

Multimodal and roboticsApr 5, 2023Segment AnythingA promptable model and a dataset of over a billion masks that cut out any object in any image.

Meta16.8k citations6 upvotesRead →Multimodal and roboticsJan 30, 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsBLIP-2 efficiently pre-trains vision-language models using off-the-shelf frozen encoders and decoders, achieving state-of-the-art performance with fewer parameters.

Salesforce9,805 citations3 upvotesRead →Multimodal and roboticsJan 28, 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationBLIP, a Vision-Language Pre-training framework, improves performance across both understanding and generation tasks by bootstrapping captions from noisy web data, achieving state-of-the-art results on image-text retrieval, image captioning, and VQA, and showing strong generalization to video-language tasks.

Salesforce7,655 citations5 upvotesRead →Multimodal and roboticsUnverifiedOct 25, 2024GPT-4o System CardGPT-4o is an omnimodal autoregressive model trained to handle text, audio, image, and video inputs, offering high-performance outputs across these modalities, with particular strengths in vision and audio.

OpenAI5,388 citations88 upvotesRead →Multimodal and roboticsUnverifiedNov 20, 2025SAM 3: Segment Anything with ConceptsSegment Anything Model 3 achieves state-of-the-art performance in promptable concept segmentation and tracking by leveraging a unified model architecture with decoupled recognition and localization.

Meta1,466 citations138 upvotesRead →Multimodal and roboticsUnverifiedMar 8, 2024DeepSeek-VL: Towards Real-World Vision-Language UnderstandingDeepSeek-VL is an open-source vision-language model that achieves state-of-the-art performance in real-world applications by combining a hybrid vision encoder with effective pretraining strategies to preserve language model capabilities.

DeepSeek939 citations49 upvotesRead →

About this paper

Venue: arXiv.org
Citations: 88, 8 influential · Semantic Scholar
Upvotes: 33 · Hugging Face
Lab: Adobe · on Companies · on Acquisitions · on Quarterly · on Paydays · on TechConf

Changes

CitationsNov 2, 2026Citations rose from 80 to 88.

CitationsOct 12, 2026Citations rose from 79 to 80.

CitationsOct 5, 2026Citations rose from 77 to 79.

CitationsSep 28, 2026Citations rose from 76 to 77.

CitationsSep 25, 2026A first count of 8 influential citations.

CitationsSep 25, 2026A first count of 76 citations.

New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.