D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
Paper โข 2605.05204 โข Published โข 28
AI & ML interests
A Family of Dynamic UltraFast Small Language Models Ready for Embodied Artificial General Intelligence!
Recent Activity
View all activity
QJerryย
authored 2
papers 5 days ago
Post
4186
We trained an open-source Mythos like cybersecurity LLM for the Build Small Hackathon meet OpenMythos
Trained in two stages: SFT on ~1.84K filtered ArXiv cs.CR papers + real CVE data, then RLVR using paired with past vulnerabilities GitHub repos with a verifier model checking outputs against ground truth.
Trained on: H100s from Modal
The RLVR stage made the biggest difference responses got more precise and less prone to confusing similar vulnerability classes.
Everything is open:
๐ค Demo โ build-small-hackathon/OpenMythos
๐ง Model โ build-small-hackathon/OpenMythos
๐ฆ CVE Dataset โ build-small-hackathon/CVE_Vulnerailities_Detailed
๐ ArXiv Dataset โ himanshu17HF/ArvixImport-Filtered-Final
Try it out and let us know where it breaks ๐
Trained in two stages: SFT on ~1.84K filtered ArXiv cs.CR papers + real CVE data, then RLVR using paired with past vulnerabilities GitHub repos with a verifier model checking outputs against ground truth.
Trained on: H100s from Modal
The RLVR stage made the biggest difference responses got more precise and less prone to confusing similar vulnerability classes.
Everything is open:
๐ค Demo โ build-small-hackathon/OpenMythos
๐ง Model โ build-small-hackathon/OpenMythos
๐ฆ CVE Dataset โ build-small-hackathon/CVE_Vulnerailities_Detailed
๐ ArXiv Dataset โ himanshu17HF/ArvixImport-Filtered-Final
Try it out and let us know where it breaks ๐
Post
192
Shipped v0.1.2 of vtx โ a minimalist coding agent for the terminal.
Most agentic CLIs ship 10k+ token system prompts. Vtx is ~2,200. Less prompt overhead means more room for your code in the model's context window.
Vtx is a from-scratch Python implementation of the design philosophy behind pi-mono โ same principles, pure Python, no transpiled runtime.
What ships out of the box:
โ Textual TUI + headless CLI (vtx -p "fix the failing test")
โ 49 LLM provider gateways, all declared in a single provider.yaml
โ 5 core tools (read / edit / write / bash / find) plus web search and fetch
โ Session tree with compaction, handoff, and resume
โ AGENTS.md / CLAUDE.md auto-discovery
โ Skills system โ drop SKILL.md files in .agents/skills/ and they become slash commands
โ Two OAuth flows (GitHub Copilot device flow, OpenAI Codex PKCE)
โ Two-mode permissions: prompt (default) or auto, with a safe-command allowlist
This release adds a proper extension system. Register new LLM-callable tools, intercept tool calls, hook lifecycle events, and add slash commands from a single register(api) function in a Python file under ~/.vtx/agent/extensions/. Extensions can override built-in tools by name and chain handler logic across subscribers.
Apache 2.0. uv tool install vtx-coding-agent and you're running.
GitHub: https://github.com/OEvortex/vtx-coding-agent
PyPI: https://pypi.org/project/vtx-coding-agent
Built in the open. Feedback, extensions, and PRs welcome.
Most agentic CLIs ship 10k+ token system prompts. Vtx is ~2,200. Less prompt overhead means more room for your code in the model's context window.
Vtx is a from-scratch Python implementation of the design philosophy behind pi-mono โ same principles, pure Python, no transpiled runtime.
What ships out of the box:
โ Textual TUI + headless CLI (vtx -p "fix the failing test")
โ 49 LLM provider gateways, all declared in a single provider.yaml
โ 5 core tools (read / edit / write / bash / find) plus web search and fetch
โ Session tree with compaction, handoff, and resume
โ AGENTS.md / CLAUDE.md auto-discovery
โ Skills system โ drop SKILL.md files in .agents/skills/ and they become slash commands
โ Two OAuth flows (GitHub Copilot device flow, OpenAI Codex PKCE)
โ Two-mode permissions: prompt (default) or auto, with a safe-command allowlist
This release adds a proper extension system. Register new LLM-callable tools, intercept tool calls, hook lifecycle events, and add slash commands from a single register(api) function in a Python file under ~/.vtx/agent/extensions/. Extensions can override built-in tools by name and chain handler logic across subscribers.
Apache 2.0. uv tool install vtx-coding-agent and you're running.
GitHub: https://github.com/OEvortex/vtx-coding-agent
PyPI: https://pypi.org/project/vtx-coding-agent
Built in the open. Feedback, extensions, and PRs welcome.
prithivMLmodsย
posted an update 9 days ago
Post
3757
Wan2.2-I2V-Fast with highly upscaled sequential frame sampling is now available as a Spaces demo, built using Wan2.2-I2V and FLUX.2-Klein. Try the demo using the links below.๐
โ wan2.2-i2v-fast : prithivMLmods/wan2.2-i2v-fast
โ github: https://github.com/prithivsakthiur/wan2.2-i2v-fast
โ collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
โคท To learn more, visit the app page or the respective model pages.
โ wan2.2-i2v-fast : prithivMLmods/wan2.2-i2v-fast
โ github: https://github.com/prithivsakthiur/wan2.2-i2v-fast
โ collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
โคท To learn more, visit the app page or the respective model pages.
Shrijanagainย
posted an update 20 days ago
Post
196
Excited to launch SKT-ST-X-0-3B by SKT AI Labs! ๐๐ฎ๐ณ
โA powerful 3B Parameter Mixture of Experts (MoE) model optimized for high-performance reasoning with a small footprint.
โ--> Quick Specs:
> Total Params: ~3B | Active Params: ~1.1B (2 experts/token)
> Pre-trained on 40B tokens (SKT-OMNI-CORPUS-2T)
1.Context: 8K tokens
2.Bilingual: English & Hindi ๐ฌ๐ง๐ฎ๐ณ
3. Base: Built on ST-X-0 with Mixtral stability
โGet 3B intelligence at 1B inference speeds. Fully open-source under Apache-2.0! ๐
โ๐ Try it on Hugging Face: sKT-Ai-Labs/SKT-ST-X-0-3B
โ#AI #OpenSource #LLM #MixtureOfExperts #SKTAILabs #MachineLearning
โA powerful 3B Parameter Mixture of Experts (MoE) model optimized for high-performance reasoning with a small footprint.
โ--> Quick Specs:
> Total Params: ~3B | Active Params: ~1.1B (2 experts/token)
> Pre-trained on 40B tokens (SKT-OMNI-CORPUS-2T)
1.Context: 8K tokens
2.Bilingual: English & Hindi ๐ฌ๐ง๐ฎ๐ณ
3. Base: Built on ST-X-0 with Mixtral stability
โGet 3B intelligence at 1B inference speeds. Fully open-source under Apache-2.0! ๐
โ๐ Try it on Hugging Face: sKT-Ai-Labs/SKT-ST-X-0-3B
โ#AI #OpenSource #LLM #MixtureOfExperts #SKTAILabs #MachineLearning
prithivMLmodsย
posted an update 24 days ago
Post
2180
Dropping the collection of Qwen 3.5/3.6 MTP GGUF quants. ๐ค
๐ Collection 1: https://huggingface.co/collections/prithivMLmods/mtp-qwen-35-36-moe-stable
๐ Collection 2: https://huggingface.co/collections/prithivMLmods/mtp-qwen-35-36-stable
> To learn more, visit the respective model pages.
๐ Collection 1: https://huggingface.co/collections/prithivMLmods/mtp-qwen-35-36-moe-stable
๐ Collection 2: https://huggingface.co/collections/prithivMLmods/mtp-qwen-35-36-stable
> To learn more, visit the respective model pages.
prithivMLmodsย
posted an update 27 days ago
Post
6180
PiD โ Pixel Diffusion Decoder Image Edit Upscale and Image Generation Upscale, an all-in-one demo, is now live on Spaces! Great improvements in realism-based image generation and editing are powered by FLUX.2-Klein, while image generation is paired with Z-Image, and upscaling is enabled by default!
๐ค Space: prithivMLmods/PiD-Image-Upscaler
๐ Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
๐ค > To learn more, visit the app page or the respective model pages.
๐ค Space: prithivMLmods/PiD-Image-Upscaler
๐ Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
๐ค > To learn more, visit the app page or the respective model pages.
prithivMLmodsย
posted an update about 1 month ago
Post
5594
I've made 8 Spaces in the Qwen-Image-Edit series, and out of them, 5 Spaces reached โSpace of the Weekโ! A few Spaces are still topping the list even after many months.
Cumulatively, the series has crossed 8.2 million+ ZeroGPU runs and nearly 4 million visitors overall.
Thanks for all the community support! ๐คโค๏ธ
๐ Spaces: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
Cumulatively, the series has crossed 8.2 million+ ZeroGPU runs and nearly 4 million visitors overall.
Thanks for all the community support! ๐คโค๏ธ
๐ Spaces: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
- 4 replies
Shrijanagainย
posted an update about 1 month ago
Post
2606
We are pleased to announce that the W-IMG Vision Dataset infrastructure is officially live.
The complete asset infrastructure is now accessible on Hugging Face for internal validation and architecture scaling targets.
Dataset Endpoint - sKT-Ai-Labs/W-IMG
#SovereignAI #ComputerVision #MachineLearning #OpenSource
The complete asset infrastructure is now accessible on Hugging Face for internal validation and architecture scaling targets.
Dataset Endpoint - sKT-Ai-Labs/W-IMG
#SovereignAI #ComputerVision #MachineLearning #OpenSource
oooranzย
authored a
paper about 1 month ago
Ksgk-fyย
authored a
paper about 1 month ago
Ksgk-fyย
submitted a
paper to Daily Papers about 1 month ago
oooranzย
submitted a
paper to Daily Papers about 1 month ago
prithivMLmodsย
posted an update about 2 months ago
Post
5945
Multimodal-Edge Demo, a node-based inference canvas demo, is now live on Spaces. It features node-based Transformers for fast inference across 10+ edge-device multimodal models on the Hub, all within a single space. The series includes models from Qwen3.5, Qwen3-VL, Gemma 4, and the LFM 2.5 VL model series, with support for reasoning and grounding tasks.
๐ค Demo: prithivMLmods/Multimodal-Edge-Node
๐ GitHub: https://github.com/PRITHIVSAKTHIUR/Multimodal-Edge-Node
โ Multimodal Apps Collections: https://huggingface.co/collections/prithivMLmods/hall-of-multimodal-apps
๐ค > To learn more, visit the app page or the respective model pages.
๐ค Demo: prithivMLmods/Multimodal-Edge-Node
๐ GitHub: https://github.com/PRITHIVSAKTHIUR/Multimodal-Edge-Node
โ Multimodal Apps Collections: https://huggingface.co/collections/prithivMLmods/hall-of-multimodal-apps
๐ค > To learn more, visit the app page or the respective model pages.
prithivMLmodsย
posted an update 2 months ago
Post
1931
Now, a collection of various compression schemes for Qwen3.6 and the abliterated version 1 of dense models is available on the Hub. Check it out via the links below. ๐
๐ Qwen3.6-MoE: https://huggingface.co/collections/prithivMLmods/qwen36-35b-a3b-compressions
๐ Qwen3.6-27B Compressions: https://huggingface.co/collections/prithivMLmods/qwen36-27b-compressions
๐ค > To learn more, visit the app page or the respective model pages.
๐ Qwen3.6-MoE: https://huggingface.co/collections/prithivMLmods/qwen36-35b-a3b-compressions
๐ Qwen3.6-27B Compressions: https://huggingface.co/collections/prithivMLmods/qwen36-27b-compressions
๐ค > To learn more, visit the app page or the respective model pages.
prithivMLmodsย
posted an update 2 months ago
Post
4229
HY-World-2.0 โ A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds is now available on Spaces, and it works both as native Gradio components and in Gradio server mode.
> HY-World-2.0-Demo: prithivMLmods/HY-World-2.0-Demo
> HY-World-2.0 [Server Mode]: prithivMLmods/HY-World-2.0-Demo
> Featuring 3D reconstruction and Gaussian splats with the Rerun viewer, along with camera poses, depth maps, and surface normals.
> In Server Mode, Gradio is served via FastAPI, with FastAPI remaining the top-level server.
> Model: tencent/HY-World-2.0
> GitHub: https://github.com/PRITHIVSAKTHIUR/HY-World-2.0-Demo
๐คTo learn more, visit the app page or the respective model pages.
> HY-World-2.0-Demo: prithivMLmods/HY-World-2.0-Demo
> HY-World-2.0 [Server Mode]: prithivMLmods/HY-World-2.0-Demo
> Featuring 3D reconstruction and Gaussian splats with the Rerun viewer, along with camera poses, depth maps, and surface normals.
> In Server Mode, Gradio is served via FastAPI, with FastAPI remaining the top-level server.
> Model: tencent/HY-World-2.0
> GitHub: https://github.com/PRITHIVSAKTHIUR/HY-World-2.0-Demo
๐คTo learn more, visit the app page or the respective model pages.
prithivMLmodsย
posted an update 2 months ago
Post
6249
A new comparator on Spaces showcases Standard FLUX.2 Decoder vs. FLUX.2 Small Decoder. The Small Decoder is ~1.4ร faster, uses ~1.4ร less VRAM, and maintains near-identical image quality. It has ~28M parameters with narrower channels [96, 192, 384, 384] vs. [128, 256, 512, 512], and the demo supports sequence generation by running both decoders simultaneously and comparing the results side by side.
๐ค Comparator: https://huggingface.co/spaces/prithivMLmods/Flux.2-4B-Decoder-Comparator
๐ FLUX.2-small-decoder: black-forest-labs/FLUX.2-small-decoder
๐ GitHub: https://github.com/PRITHIVSAKTHIUR/Flux.2-4B-Encoder-Comparator
๐ Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
๐ค > App built on the Gradio SDK. To learn more, visit the app page or the respective model pages.
๐ค Comparator: https://huggingface.co/spaces/prithivMLmods/Flux.2-4B-Decoder-Comparator
๐ FLUX.2-small-decoder: black-forest-labs/FLUX.2-small-decoder
๐ GitHub: https://github.com/PRITHIVSAKTHIUR/Flux.2-4B-Encoder-Comparator
๐ Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
๐ค > App built on the Gradio SDK. To learn more, visit the app page or the respective model pages.
prithivMLmodsย
posted an update 2 months ago
Post
4264
Now, a collection of various compression schemes for Gemma 4 and the abliterated version 1 of dense models is available on the Hub. Check it out via the links below. ๐
๐Gemma 4 Compression(s)- https://huggingface.co/collections/prithivMLmods/gemma-4-compressions
๐Gemma 4 Uncensored [MAX] + Compression(s) - [`ฮฒ ]- https://huggingface.co/collections/prithivMLmods/gemma-4-uncensored-max-compressions
๐Gemma 4 Compression(s) - MoE- https://huggingface.co/collections/prithivMLmods/gemma-4-compressions-moe
๐Gemma-4 F32 GGUF- https://huggingface.co/collections/prithivMLmods/gemma-4-f32-gguf
๐ค > To learn more, visit the app page or the respective model pages.
๐Gemma 4 Compression(s)- https://huggingface.co/collections/prithivMLmods/gemma-4-compressions
๐Gemma 4 Uncensored [MAX] + Compression(s) - [`ฮฒ ]- https://huggingface.co/collections/prithivMLmods/gemma-4-uncensored-max-compressions
๐Gemma 4 Compression(s) - MoE- https://huggingface.co/collections/prithivMLmods/gemma-4-compressions-moe
๐Gemma-4 F32 GGUF- https://huggingface.co/collections/prithivMLmods/gemma-4-f32-gguf
๐ค > To learn more, visit the app page or the respective model pages.
prithivMLmodsย
posted an update 3 months ago
Post
2364
Now the demo for image detection based on SAM3 and Gemma-4 (*Filter) is available on Spaces, using full-fledged Transformers inference with multimodal reasoning for processed images. It also supports video segmentation (mask), video segmentation (annotation), and image click segmentation.
๐ค Demo Space: prithivMLmods/SAM3-Gemma4-CUDA
๐ฅฝ SAM3: facebook/sam3
๐ gemma-4-E2B-it: google/gemma-4-E2B-it
To learn more, visit the app page or the respective model pages.
๐ค Demo Space: prithivMLmods/SAM3-Gemma4-CUDA
๐ฅฝ SAM3: facebook/sam3
๐ gemma-4-E2B-it: google/gemma-4-E2B-it
To learn more, visit the app page or the respective model pages.
- 1 reply