{ "schema_version": "1.1", "id": "atlas-generative-media", "slug": "generative-media", "title": "Generative Media", "url": "https://feed7.dev/atlas/generative-media", "current_answer": null, "implementation_consequence": null, "agent_context": null, "confidence": "auto_collected", "last_verified": null, "last_updated": null, "evidence": [], "conflicting_sources": [], "superseded_claims": [], "corpus_evidence": [ { "title": "SOTA Generative Media Panel — Dumitru Erhan, Shane Gu & Nicole Brichtova, Google DeepMind", "url": "https://www.youtube.com/watch?v=KLDdXOw6jIc", "source_name": "AI Engineer", "published_at": "2026-08-30T14:00:06+00:00", "summary": "DeepMind’s panel shows why generative-media evals need task-specific human review: broad preferences can miss repeated artifacts, exact sizing, text errors, and brand consistency." }, { "title": "MiniMax H3 and H3 Max are 50% off on AI Gateway", "url": "https://vercel.com/changelog/minimax-h3-and-h3-max-are-50-off-on-ai-gateway", "source_name": "Vercel", "published_at": "2026-08-30T00:00:00+00:00", "summary": "Vercel is halving AI Gateway charges for MiniMax H3 and H3 Max through September 13; existing model IDs receive the discount without code changes." }, { "title": "Agentic Sites: Building Hyper Personalized Websites — Carlos Sanchez, Adobe", "url": "https://www.youtube.com/watch?v=jebp4V0vh30", "source_name": "AI Engineer", "published_at": "2026-08-29T17:00:17+00:00", "summary": "Adobe’s prototype assembles intent-specific page blocks from existing site content in roughly a second, making model latency and per-site evaluation part of frontend architecture." }, { "title": "Muse Image now available on AI Gateway", "url": "https://vercel.com/changelog/muse-image-now-available-on-ai-gateway", "source_name": "Vercel", "published_at": "2026-08-26T00:00:00+00:00", "summary": "Muse Image is available through Vercel AI Gateway for both generation and instruction-based editing, including reference-image guidance through the AI SDK." }, { "title": "Gemini 3.5 Transcribe now available on AI Gateway", "url": "https://vercel.com/changelog/gemini-3-5-transcribe-now-available-on-ai-gateway", "source_name": "Vercel", "published_at": "2026-08-26T00:00:00+00:00", "summary": "Gemini 3.5 Transcribe adds batch and live WebSocket transcription to AI Gateway, with automatic language detection, 85+ languages, and custom vocabulary." }, { "title": "Wan 3.0 now available on AI Gateway", "url": "https://vercel.com/changelog/wan-3-0-now-available-on-ai-gateway", "source_name": "Vercel", "published_at": "2026-08-25T00:00:00+00:00", "summary": "Wan 3.0 gives AI Gateway one video model ID for text, image, frame, and reference workflows, with async renders up to 30 seconds at 1080p and synchronized audio." }, { "title": "Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning", "url": "https://arxiv.org/abs/2608.21305v1", "source_name": "arXiv", "published_at": "2026-08-21T17:07:41+00:00", "summary": "Re³Cap uses multimodal retrieval to find caption omissions and hallucinations before refinement, offering a concrete retrieval-and-review pattern for vision agents." }, { "title": "DeepSeek V4 Flash Vision Experimental now available on AI Gateway", "url": "https://vercel.com/changelog/deepseek-v4-flash-with-vision-now-available-on-ai-gateway", "source_name": "Vercel", "published_at": "2026-08-21T00:00:00+00:00", "summary": "DeepSeek V4 Flash Vision adds screenshot, image, and chart input to Vercel AI Gateway while retaining tool use, reasoning, and caching, but its experimental ID signals production risk." }, { "title": "Fish Audio models now available on Vercel AI Gateway for free", "url": "https://vercel.com/changelog/fish-audio-models-now-available-on-ai-gateway-for-free", "source_name": "Vercel", "published_at": "2026-08-19T00:00:00+00:00", "summary": "Vercel AI Gateway added four Fish Audio models for speech generation and transcription, with AI SDK 7 support and a free window whose model naming determines later billing." }, { "title": "The Next Medium: Why Real-Time Interactive Video Changes Everything — Ahmed Ahres, Reactor", "url": "https://www.youtube.com/watch?v=5dCAmSDOAjI", "source_name": "AI Engineer", "published_at": "2026-08-18T17:30:18+00:00", "summary": "Reactor frames real-time video as a programmable session rather than a generated file, enabling interactive worlds and live editing but exposing hard state, latency, and evaluation problems." }, { "title": "Generative Video at the Speed of Light — Keegan McCallum, uRun", "url": "https://www.youtube.com/watch?v=Xln-On3syJk", "source_name": "AI Engineer", "published_at": "2026-08-18T16:30:29+00:00", "summary": "Real-time video models are becoming cheap and responsive enough for agent interfaces, but builders still need global GPU routing, streaming infrastructure, and multi-model orchestration." }, { "title": "Voice agents with Realtime Video — Sidney Primas, LemonSlice", "url": "https://www.youtube.com/watch?v=z1dqv74SpUs", "source_name": "AI Engineer", "published_at": "2026-08-18T16:00:06+00:00", "summary": "LemonSlice’s avatar stack treats long-running visual stability, audio-conditioned emotion, and deterministic action timing as the core engineering problems beyond lip sync." }, { "title": "Training Krea 2: What matters in generative model training — Sangwu Lee, Krea.ai", "url": "https://www.youtube.com/watch?v=-tviRdpmHvs", "source_name": "AI Engineer", "published_at": "2026-08-18T14:00:06+00:00", "summary": "Krea 2’s training notes put data curation and iteration speed ahead of architecture novelty, with explicit safeguards against filtering away unusual visual styles." }, { "title": "Grok Imagine Image 2.0 now available on Vercel AI Gateway", "url": "https://vercel.com/changelog/grok-imagine-image-2-0-preview-now-available-on-vercel-ai-gateway", "source_name": "Vercel", "published_at": "2026-08-08T00:00:00+00:00", "summary": "Vercel AI Gateway now exposes xAI’s image model through the AI SDK, including 1K/2K generation, batches, and targeted edits that aim to preserve untouched details." }, { "title": "SABRE: Scalable and Automated Benchmarking of VLMs under Stress", "url": "https://arxiv.org/abs/2608.07435v1", "source_name": "arXiv", "published_at": "2026-08-07T17:21:04+00:00", "summary": "SABRE turns a Markdown test design into generated VLM stress tests, then filters and repairs candidates. It offers a repeatable pattern for refreshing evals as models improve." }, { "title": "Seedance 2.5 now available on Vercel AI Gateway", "url": "https://vercel.com/changelog/seedance-2-5-now-available-on-vercel-ai-gateway", "source_name": "Vercel", "published_at": "2026-08-06T00:00:00+00:00", "summary": "Seedance 2.5 adds multimodal video generation and local edits to AI Gateway, with clips up to 30 seconds and separate image and video references." }, { "title": "Gadgets: Personal app vibe coding that is actually safe — Kenton Varda, Cloudflare", "url": "https://www.youtube.com/watch?v=RmS5s6Wbin4", "source_name": "AI Engineer", "published_at": "2026-08-05T22:42:10+00:00", "summary": "Kenton Varda argues that personal AI-generated apps need per-user code and strong isolation, not one server-owned version. The demo shows agents modifying app code inside a constrained local runtime." }, { "title": "Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation", "url": "https://arxiv.org/abs/2608.03999v1", "source_name": "arXiv", "published_at": "2026-08-04T17:56:49+00:00", "summary": "Controlled text-to-MIDI tests find token representation matters more than a 34× model-size increase for distributional fidelity; performance timing also beats beat-grid tokenization." }, { "title": "MiniMax H3 now available on AI Gateway", "url": "https://vercel.com/changelog/minimax-h3-now-available-on-vercel-ai-gateway", "source_name": "Vercel", "published_at": "2026-07-30T00:00:00+00:00", "summary": "MiniMax H3 brings short 2K video generation to Vercel AI Gateway, with text, keyframe, and multimodal reference inputs. Reference and keyframe modes cannot be combined." }, { "title": "Grok Voice Think Fast 2.0 now available on AI Gateway", "url": "https://vercel.com/changelog/grok-voice-think-fast-2-0-now-available-on-ai-gateway", "source_name": "Vercel", "published_at": "2026-07-29T00:00:00+00:00", "summary": "Grok Voice Think Fast 2.0 brings speech-to-speech reasoning and earlier tool calls to Vercel’s realtime API, with server-minted tokens keeping gateway keys off clients." }, { "title": "MMOE: Modernizing Diffusion Transformers with Efficient Expert Design", "url": "https://arxiv.org/abs/2607.24665v1", "source_name": "arXiv", "published_at": "2026-07-27T17:05:04+00:00", "summary": "ModernMOE applies efficient expert-routing patterns from LLMs to diffusion transformers, improving convergence and quality-cost balance without relying only on larger parameter counts." }, { "title": "Evaling Video Slop — Maor Bril, Character.ai", "url": "https://www.youtube.com/watch?v=b_PmGocP4rc", "source_name": "AI Engineer", "published_at": "2026-07-25T00:00:02+00:00", "summary": "Video evaluators can reward polish while missing frozen action, broken physics, or failed storytelling. Builders need time-aware criteria and human-calibrated data, not frame quality alone." }, { "title": "Building Closed-Loop Evals for a Multimodal Agent at Scale — Soumya Gupta & Jai Chopra, Uber", "url": "https://www.youtube.com/watch?v=31GUkCBD-Uc", "source_name": "AI Engineer", "published_at": "2026-07-24T22:00:25+00:00", "summary": "Uber’s image-editing agent uses routing, iterative QA, golden-set gates, and production feedback to avoid costly edits, hallucinated food, and quality regressions." }, { "title": "MedGame: Storytelling Gamification Empowered by Large Language Models for Medical Education", "url": "https://arxiv.org/abs/2607.21570v1", "source_name": "arXiv", "published_at": "2026-07-23T17:50:28+00:00", "summary": "MedGame turns static clinical cases into executable decision stories with separate narrative and orchestration stages, a useful architecture pattern for case-grounded learning agents." }, { "title": "Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model", "url": "https://arxiv.org/abs/2607.13013v1", "source_name": "arXiv", "published_at": "2026-07-14T17:53:22+00:00", "summary": "A frozen diffusion language model can transcribe speech by refining the full transcript in parallel. The prototype trains a small audio interface and reaches 6.6% WER in roughly eight steps." }, { "title": "Seedream 5.0 Pro is now available on AI Gateway", "url": "https://vercel.com/changelog/seedream-5-0-pro-is-now-available-on-ai-gateway", "source_name": null, "published_at": null, "summary": "Seedream 5.0 Pro adds image generation and editing to Vercel AI Gateway, targeting reliable text rendering and dense infographic layouts through the AI SDK." }, { "title": "Evidence-Backed Video Question Answering", "url": "https://arxiv.org/abs/2607.11862v1", "source_name": null, "published_at": null, "summary": "E-VQA requires video answers to include tracked pixel-level evidence, revealing when good QA scores hide weak perception and supplying grounded training data." }, { "title": "calesthio/OpenMontage", "url": "https://github.com/calesthio/OpenMontage", "source_name": "GitHub", "published_at": null, "summary": "OpenMontage turns coding agents into pipeline-driven video producers, covering research through rendering with approval gates, provider selection, and auditable costs." }, { "title": "Encoder-Side Neuron Identification and Amplification for Acoustic Perception in Large Audio-Language Models", "url": "https://arxiv.org/abs/2607.11801v1", "source_name": null, "published_at": null, "summary": "IAAN boosts selected audio-encoder neurons at inference, improving fine-grained speech perception across three models without retraining or labels." }, { "title": "Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation", "url": "https://arxiv.org/abs/2607.05382v1", "source_name": null, "published_at": null, "summary": "SearchGen-Bench shows open image generators score 21–28/100 on long-tail entities, and naive search retrieval only adds noise; a teach-then-search co-training recipe learns when to retrieve versus rely on weights." }, { "title": "Meta 3D AssetGen: Generating 3D Worlds With AI", "url": "https://engineering.fb.com/2025/09/29/virtual-reality/assetgen-generating-3d-worlds-with-ai/", "source_name": null, "published_at": null, "summary": "Meta's Tech Podcast covers AssetGen, its foundation model for generating 3D assets from text, and the path toward AI-generated worlds in Horizon Studio. A podcast episode, so light on specifics." }, { "title": "Start building with Nano Banana 2 Lite and Gemini Omni Flash", "url": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-omni-flash-nano-banana-2-lite/", "source_name": null, "published_at": null, "summary": "Two new Gemini API models: Nano Banana 2 Lite generates 1K images in ~4s at $0.034 each, and Omni Flash does video at $0.10/sec in public preview — cheap enough to wire asset generation into agent pipelines." }, { "title": "The latest AI news we announced in June 2026", "url": "https://blog.google/innovation-and-ai/technology/ai/google-ai-updates-june-2026/", "source_name": null, "published_at": null, "summary": "Google's June roundup: Gemma 4 12B runs locally in 16GB of memory, Gemini 3.5 Flash adds computer use for desktop, mobile, and browser agents, and Nano Banana 2 Lite ships as a cheaper image model." }, { "title": "Comfy-Org/ComfyUI", "url": "https://github.com/Comfy-Org/ComfyUI", "source_name": "GitHub", "published_at": null, "summary": "ComfyUI turns multimodal generation into reusable node graphs with API access, incremental execution, and offline operation. Pin stable releases if custom nodes matter to your workflow." } ] }