APEX few-step streaming video drops the extra fake-score network
Condition shifting estimates the generated velocity inside the generator and cuts peak GPU memory 4.4% and iteration time 9.2% versus DMD.
Stories per day · 30 days
3 RSS
Relatedvideo-generation5benchmark3multimodal3ai-music2deezer2diffusion2flow-matching2generative-ai2spotify23d1agents1anomaly-detection1apex1audio-video1autoregressive1capacity-planning1content-filtering1content-labels1
36 stories, newest first · one card per story
Stories tagged #streaming
LiveFoley streams video-to-audio with look-ahead below perception
A trailing window and wider local diffusion keep alignment with offline models while cutting frontend latency.
Netflix rolls out AI Discover tab for mood-based recommendations
AI Discover tab lets users select themes like “scare me” or “family movie night” for personalized suggestions powered by a new real-time intelligence layer.
TaoMate-HD streams high-resolution audio-video with progressive denoising
Authors report a 1.6x speedup versus direct high-resolution generation and an 11.18-point drop in character error rate.
arXiv paper presents Wave Forcing for speed-of-light video generation
Wave Forcing co-designs generation training and execution for continuous video output achieving 1F1C with 147.6 DiT FPS on eight H200 GPUs.
StreamDuo for cross-game streaming commentary
StreamDuo pairs a commentator with a research agent using game wikis to enable commentary on unseen games.
AskStream benchmark tests when video models should ask
The strongest model scores only 52.18% Ask-F1 across 438 videos labeled for wait, ask, and answer.
Omni-InteractScope tests proactive help on continuous audiovisual streams
Across 12 models, on-time first tool responses stay at or below 40% and reminder recall never exceeds 23%.
DirCast directs and commentates live Dota 2 from raw player cameras
Trained on 27 professional matches, its commentary wins 29.2% of Proact-VL comparisons against GPT-4o.
Spotify pulled 50 million AI slop and spam tracks from recommendations
Spotify also launched an AI Persona badge and says it will not recommend music from those personas.
WorldStream streams open-ended 3D worlds with persistent editable state
Hierarchical planners compile terrain ahead of the player while one world record restores prior visits and edits.
StreamEval benchmarks interactive streaming video generation
Across 37 models and 300 cases, the best Following and Edit Success scores are 36.90, 25.93, and 15.00.
StyleStream 2.0 cuts streaming voice conversion latency to 520 ms
A text-conditioned style embedding supports prompt-based voice design and instruction-based editing of one attribute.
96-day study measures SRT streaming behavior and UDP flood effects
Controlled 500-pps UDP floods raised CPU 176–806% while SRT metrics moved only about 13%.
StreamingSwap aims at real-time identity-preserving video face swapping
Authors report competitive identity transfer at 20 FPS on one RTX 4090, stable on videos up to 10 minutes.
YouTube Music launches new labels as AI-generated music floods streaming platforms
YouTube Music adds disclosure labels identifying fully or partly AI-generated songs across its player.
2
Deezer will soon let you filter out AI-generated music
Deezer will let listeners hide AI-generated music after such tracks exceeded half of daily uploads.
StreamErase: Towards Ultra-Fast Streaming Video Erasing
StreamErase enables real-time streaming video object removal at up to 26 FPS on one GPU.
Drive3R: Block-wise Streaming Geometric Foundation Models for Autonomous Driving
Drive3R streams block-wise 3D reconstruction for driving and sets new nuScenes, KITTI, and Waymo results.
Online AutoML: Evaluating Poisoning Attacks on Adversarial Training Defense Strategy in IoT Networks
Study tests adversarial training against label-flip and noise poisoning of streaming AutoML models for IoT.
Microsoft AI Releases MAI-Transcribe-2-Streaming: #1 Real-Time Speech-to-Text Model on Artificial Analysis
Microsoft released MAI-Transcribe-2-Streaming, ranking first of 38 models on Artificial Analysis streaming speech-to-text accuracy.
8
In a Streaming World, Should You Stand Still? A Comprehensive Benchmark of Anomaly Detection in Streams
A large benchmark finds static time-series anomaly detectors beat streaming methods in most realistic settings.
Pruned CTC for Memory-Efficient Large-Vocabulary ASR Training
Pruned CTC restricts alignment computation to target tokens and blank, cutting ASR training memory 5.1x for 180K-vocabulary LLMs with minimal accuracy loss.
KeyRec: Bounded Visual Memory for Streaming and Long-Video Understanding
KeyRec lets VLMs answer long-video questions using 10% of dense visual tokens via bounded memory.