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.
40
Product
RTX 4090
- Mentions · 7d0
- Mentions · 30d2
- All mentions6
- First seenSep 10, 2026
- Last mentioned23d ago
Timeline
6 articles · newest firstIntern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling
Intern-Decision's 4B model hits 90.02% decision accuracy with 44 ms latency on an RTX 4090.
42
Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s
Strata claims to run 125B Qwen 3.8 Flash Next on an RTX 4090 at about 100 tokens per second.
46
canberkkkkkk/ema-lightning — new model trending #30 on Hugging Face
EMA Lightning is an 8.6M-parameter Apache-2.0 Turkish TTS model reporting 0.92% WER on Freya-TR-Eval.
34
rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference
rMuscle, a caching-based inference framework for vision-language-action models, achieves 1.29-1.42x speedups on RTX 4090 and Jetson Thor while preserving success rates.
32
3D Point Splatting for mmWave Radar Novel View Synthesis
Researchers propose 3DPS, a differentiable point renderer for mmWave radar novel view synthesis that outperforms optical-NVS baselines by 1.7x-5.2x.
28
Appears with
- NVIDIAvendor · 4
- EMA Lightningai model · 1
- Atria-Dawn-Previewai model · 1
- ElevenLabsorganization · 1
- Strataproduct · 1
- rMuscleproduct · 1
- Jetson Thorproduct · 1
- Jev v1.13.0ai model · 1
- Trendyol-TTSai model · 1
- Qwen 3.8 Flash Nextai model · 1
- arXivorganization · 1
- Intern-Decisionai model · 1
- StreamingSwapproduct · 1
- ColoRadarproduct · 1
- Trendyolorganization · 1
- 3DPSproduct · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.