Full corpus search
33 matches for “video”
Intelligence arXiv
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, SANA-Video 2.0 matches full-softmax video DiTs in quality…
Engineering GitHub Rising
AI video skill for Claude Code & Codex — cinematic product videos with Remotion: 106 shot recipe cards, 161 motion previews, a production-ready template
Research arXiv
Video captioning requires fine-grained spatio-temporal understanding of videos, including spatial perception of where objects are located and temporal perception of when events occur. Existing MLLMs usually generate captions directly from video inputs without…
Research arXiv
Recent autoregressive video diffusion methods are increasingly built upon Self Forcing, where the student is trained on histories produced by its own rollout rather than ground-truth video contexts. This reduces exposure bias, but the historical key-value…
Research arXiv
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 inter-subject personalization still struggle to strike a…
Research arXiv
In line with the prevailing direction of vision research, we explore the integration of both generation and editing capabilities for video and image modalities within a single model. Current approaches to collecting video editing data typically depend on…
Research arXiv
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 movement. In practice, trajectory-based control often requires…
Research arXiv
Understanding motion in video is a fundamental challenge for visual learning, as frame-to-frame change entangles two sources of dynamics: camera motion and object motion. This decomposition has remained underexplored in representation learning, partly because…
Engineering Lobsters
Filed from Lobsters. Open the source for the full story.
Research arXiv
Long audio-video reasoning is difficult for omnimodal LLMs because the decisive evidence is often sparse, cross-modal, and too expensive to preserve with uniformly high-fidelity inputs. We introduce OmniReasoner, a tool-use post-training framework for…
Engineering Lobsters
Filed from Lobsters. Open the source for the full story.
Engineering Lobsters
Filed from Lobsters. Open the source for the full story.
Signal Hacker News
Filed from Hacker News. Open the source for the full story.
Signal Hacker News
Filed from Hacker News. Open the source for the full story.
Technology The Verge
Google announced yet another way to gain access to your account if you get locked out, forget your password, or don't have access to the phone, computer, or two-factor authentication apps you typically use. As the name implies, selfie video lets you capture a…
Technology Ars Technica
Google's selfie videos can be used for account access, AI Avatars, and age verification.
Engineering DEV
This is a submission for DEV's Summer Bug Smash: Clear the Lineup powered by Sentry. ...
Design Smashing Magazine
Design principles with references, examples, and methods for quick look-up. Brought to you by Design Patterns For AI Interfaces, **friendly video courses on UX** and design patterns by Vitaly.
