Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals?
Paper โข 2610.37662 โข Published โข 90
AI & ML interests
Computer Vision
Recent Activity
View all activity
Papers
Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping
Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction
yuezhengrongย
submitted a
paper to Daily Papers 1 day ago
prithivMLmodsย
posted an update 5 days ago
Post
606
Flux-3-Image-Klein-LoRAs-Fast is now live on Hugging Face Spaces.๐ค๐ฅ
Plug and play with any custom LoRAs based on flux-3-image-klein. 16-step distilled fast inference, with support for prompt upsampling. More LoRAs will be added in the coming days!
๐ Space: prithivMLmods/flux-3-image-klein-loras-fast
๐ Image Generation Apps Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
๐ GitHub: https://github.com/PRITHIVSAKTHIUR/flux-3-image-klein-loras-fast
To learn more, visit the app page or the respective model pages.
Plug and play with any custom LoRAs based on flux-3-image-klein. 16-step distilled fast inference, with support for prompt upsampling. More LoRAs will be added in the coming days!
๐ Space: prithivMLmods/flux-3-image-klein-loras-fast
๐ Image Generation Apps Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
๐ GitHub: https://github.com/PRITHIVSAKTHIUR/flux-3-image-klein-loras-fast
To learn more, visit the app page or the respective model pages.
Post
3,716
Introducing Live Subtitles, a Windows tray app that captions anything your PC is playing and isn't butt ugly. live and fully local. It runs NVIDIA's Parakeet-unified 0.6B on your GPU, puts words on screen about 0.36 s after they're spoken, and uses less than one CPU core while it does it.
I built a benchmark for it out of real TV, podcasts, earnings calls and a short film. Parakeet-unified scores 12.1% WER there, close to Nemotron streaming's 11.4%, but with much better punctuation and lower worst-case delay. Once a caption is on screen it never gets rewritten or jumps lines, and the overlay disappears when nobody's talking.
No NVIDIA GPU? It falls back to Nemotron on the CPU, which also covers 30 other languages. It can also write SRT/ASS/VTT files for videos on disk.
Windows only. The GPU engine needs an NVIDIA card with ~3.2 GB of free VRAM. MIT.
Edit: the first version of this post said 13.8% vs 17.0%. The replies caught a scoring bug (numbers weren't normalized), so the benchmark now uses Whisper's English normalizer and the numbers above are re-scored.
Get it here:
https://github.com/Nymbo/Live-Subtitles
Models:
nvidia/parakeet-unified-en-0.6b
nvidia/nemotron-speech-streaming-en-0.6b
I built a benchmark for it out of real TV, podcasts, earnings calls and a short film. Parakeet-unified scores 12.1% WER there, close to Nemotron streaming's 11.4%, but with much better punctuation and lower worst-case delay. Once a caption is on screen it never gets rewritten or jumps lines, and the overlay disappears when nobody's talking.
No NVIDIA GPU? It falls back to Nemotron on the CPU, which also covers 30 other languages. It can also write SRT/ASS/VTT files for videos on disk.
Windows only. The GPU engine needs an NVIDIA card with ~3.2 GB of free VRAM. MIT.
Edit: the first version of this post said 13.8% vs 17.0%. The replies caught a scoring bug (numbers weren't normalized), so the benchmark now uses Whisper's English normalizer and the numbers above are re-scored.
Get it here:
https://github.com/Nymbo/Live-Subtitles
Models:
nvidia/parakeet-unified-en-0.6b
nvidia/nemotron-speech-streaming-en-0.6b
- 7 replies
Euraykaย
authored a
paper 15 days ago
SongzeLiย
authored a
paper 15 days ago
Euraykaย
authored a
paper 15 days ago
SongzeLiย
authored 4
papers 15 days ago
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
Paper โข 2607.17423 โข Published โข 160
ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI
Paper โข 2607.04426 โข Published
InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning
Paper โข 2606.12195 โข Published โข 25
Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction
Paper โข 2606.05769 โข Published โข 7
SongzeLiย
submitted a
paper to Daily Papers 15 days ago
prithivMLmodsย
posted an update 22 days ago
Post
4,755
OneDecision-VisionGuard-Demo is now available on Hugging Face Spaces!
๐ค Space: prithivMLmods/OneDecision-VisionGuard-Demo
This demo showcases the OneDecision-VisionGuard family of multimodal image classification models for detecting NSFW and other sensitive visual content, with structured JSON reasoning, improved accuracy, and better handling of edge cases such as sensitive imagery, uncensored analysis, scene descriptions, and classification reasoning.
๐ฆ Models: 27B, 9B, 4B โ prithivMLmods/OneDecision-VisionGuard-27B-SFT, prithivMLmods/OneDecision-VisionGuard-9B-SFT, prithivMLmods/OneDecision-VisionGuard-4B-SFT
โ๏ธ Collection: https://huggingface.co/collections/prithivMLmods/onedecision-visionguard
To learn more, visit the app page or the respective model pages.
๐ค Space: prithivMLmods/OneDecision-VisionGuard-Demo
This demo showcases the OneDecision-VisionGuard family of multimodal image classification models for detecting NSFW and other sensitive visual content, with structured JSON reasoning, improved accuracy, and better handling of edge cases such as sensitive imagery, uncensored analysis, scene descriptions, and classification reasoning.
๐ฆ Models: 27B, 9B, 4B โ prithivMLmods/OneDecision-VisionGuard-27B-SFT, prithivMLmods/OneDecision-VisionGuard-9B-SFT, prithivMLmods/OneDecision-VisionGuard-4B-SFT
โ๏ธ Collection: https://huggingface.co/collections/prithivMLmods/onedecision-visionguard
To learn more, visit the app page or the respective model pages.
nanammaย
authored 2
papers 27 days ago
nanammaย
submitted a
paper to Daily Papers 27 days ago
nanammaย
authored 2
papers about 1 month ago
prithivMLmodsย
posted an update about 1 month ago
Post
3,956
Qwen-Image-2.1 Plug and Play LoRA App is now live on Hugging Face Spaces.
๐ Space: prithivMLmods/Qwen-Image-2.1-LoRAs-PnP
It supports standard inference, 4-step Turbo inference, custom LoRA lazy repacks, and LoRA Plug and Play (PnP), all in one setting!
๐ Qwen-Image-2.1 Image-to-Image LoRAs: https://huggingface.co/collections/prithivMLmods/qwen-image-21-image-to-image-loras
๐ GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-2.1-LoRAs-PnP
To learn more, visit the app page or the respective model pages.
๐ Space: prithivMLmods/Qwen-Image-2.1-LoRAs-PnP
It supports standard inference, 4-step Turbo inference, custom LoRA lazy repacks, and LoRA Plug and Play (PnP), all in one setting!
๐ Qwen-Image-2.1 Image-to-Image LoRAs: https://huggingface.co/collections/prithivMLmods/qwen-image-21-image-to-image-loras
๐ GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-2.1-LoRAs-PnP
To learn more, visit the app page or the respective model pages.
prithivMLmodsย
posted an update about 1 month ago
Post
863
VisionGuardrail EVO-2, a multimodal image-classification content-safety model based on Qwen/Qwen3.8-27B, is now available on the Hub!
Stricter image classification than before, with a dense 27-billion-parameter multimodal model, more precise reasoning, and improved captions for classifying visual media.
โ Models: prithivMLmods/VisionGuardrail-Evo2-27B, prithivMLmods/VisionGuardrail-Evo2-27B-GGUF
โ Collection: https://huggingface.co/collections/prithivMLmods/visionguardrail-evo2
โ Previous Models: https://huggingface.co/collections/prithivMLmods/visionguardrail-collection
โคท To learn more, visit the app page or the respective model pages.
Stricter image classification than before, with a dense 27-billion-parameter multimodal model, more precise reasoning, and improved captions for classifying visual media.
โ Models: prithivMLmods/VisionGuardrail-Evo2-27B, prithivMLmods/VisionGuardrail-Evo2-27B-GGUF
โ Collection: https://huggingface.co/collections/prithivMLmods/visionguardrail-evo2
โ Previous Models: https://huggingface.co/collections/prithivMLmods/visionguardrail-collection
โคท To learn more, visit the app page or the respective model pages.
prithivMLmodsย
posted an update about 2 months ago
Post
504
Scribble-Board-Fast is a sketch-to-image workspace powered by Klein-9B, transforming doodles, brush strokes, stickers, and uploaded images into high-fidelity visuals with 4-step distilled sampling.
> Space: prithivMLmods/Scribble-Board-Fast
> GitHub: https://github.com/PRITHIVSAKTHIUR/Scribble-Board-Fast
> To learn more, visit the app page or the respective model pages.
> Space: prithivMLmods/Scribble-Board-Fast
> GitHub: https://github.com/PRITHIVSAKTHIUR/Scribble-Board-Fast
> To learn more, visit the app page or the respective model pages.