Generative media for expert learners
238 resources · page 8 of 8
Warner Music Ends Legal Battle With AI Firm Suno (eWeek)
by eWeek
eWeek report on Warner Music settling with Suno and forming a licensing partnership.
Whisper
by OpenAI
OpenAI Whisper GitHub repo: speech recognition model trained with large-scale weak supervision.
World Labs
by World Labs
World Labs: spatial intelligence company building models that generate 3D worlds, such as Marble.
YandexART / Shedevrum (Yandex)
Shedevrum: Yandex consumer app for image generation with YandexART.
YVO3D 2.5
by Top 3D AI
Top 3D AI listing for YVO3D 2.5, a 3D generator focused on high-resolution texturing, with ratings.
Zoom Scribe V2 Pro
Artificial Analysis speech-to-text page for Zoom, covering Zoom Scribe V2 Pro: word error rate, speed and price compared with other models.
Copyright and Artificial Intelligence, Part 2: Copyrightability (US Copyright Office)
US Copyright Office report (PDF, January 2025) Copyright and AI Part 2 on copyrightability of AI-generated output.
3D Gaussian Splatting
by Bernhard Kerbl et al. (Inria)
arXiv paper (2023) introducing 3D Gaussian Splatting for real-time radiance field rendering.
DiT (Scalable Diffusion Transformers)
by William Peebles and Saining Xie (UC Berkeley)
arXiv paper (2022) introducing Diffusion Transformers (DiT), scalable diffusion models with transformer backbones.
Flow Matching
by Yaron Lipman et al. (Meta AI)
arXiv paper (2022) "Flow Matching for Generative Modeling", introducing flow matching for training continuous normalising flows.
NeRF
by Ben Mildenhall et al. (UC Berkeley)
arXiv paper (2020) "NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis", introducing neural radiance fields (NeRF) for novel view synthesis.
Whisper paper
by Alec Radford et al. (OpenAI)
arXiv paper (2022) introducing Whisper, speech recognition trained on large-scale weakly supervised audio.
GEMA v OpenAI decision (MediaLaws)
by MediaLaws
MediaLaws analysis of the Munich Regional Court decision in GEMA v. OpenAI on song lyrics and model training.
Hitem3D 2.0: Multi-View Guided Native 3D Texture Generation
arXiv paper (2026) describing Hitem3D 2.0, multi-view guided native 3D texture generation.