Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
nielsrย  submitted a paper 3 days ago
RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs
nielsrย  submitted a paper 25 days ago
One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows
nielsrย  submitted a paper about 1 month ago
PixRestore: Unified Image Restoration via Pixel Diffusion Transformer
View all activity
fffiloniย 
posted an update 4 days ago
view post
Post
80
Been pushing Viggle Animate a bit further ๐Ÿ‘€

Viggle Mine is my take on longer, harder character replacement shots โ€” crowds, distance changes, characters turning their back and reappearing.

Still experimental, but itโ€™s getting surprisingly robust.

Try it : fffiloni/Viggle-Mine ๐Ÿค—
fffiloniย 
posted an update 26 days ago
view post
Post
2157
If an agent can build the obvious demo, the obvious demo probably isnโ€™t worth building anymore.
For years, turning a research repo into something people could actually try was valuable by itself.
That part is becoming automated โ€” and thatโ€™s a good thing.

Which means the interesting work moves elsewhere: finding the weird use case, the right interaction, the unexpected model combination โ€” or simply knowing which paper is worth anyoneโ€™s attention.

The demo used to be the product. Now it needs a point of view.
  • 1 reply
ยท
alielfilali01ย 
authored a paper about 1 month ago
Nymboย 
posted an update about 1 month ago
view post
Post
2238
Anthropic gave me six months of Claude Max 20x through the Claude for Open Source program, granted based on my Hugging Face work. Thank you
Anthropic for supporting open source.

So far I've been pointing it at Markdown Minimap, an Obsidian plugin that adds a scrollable IDE-style minimap to your notes. This week I've been clearing a backlog of user-reported issues on it, with Claude often handling them end to end.

https://github.com/Nymbo/Markdown-Minimap โ€” issues and PRs welcome.
julien-cย 
posted an update about 2 months ago
view post
Post
5440
who's working on an NVFP4 version of Kimi-K3?
  • 4 replies
ยท
Nymboย 
posted an update about 2 months ago
view post
Post
5959
Introducing Inflect-v2, two exceptionally small, open-weight English TTS models at just 3.9M and 9.3M parameters. Both generate speech multiple times faster than real-time on CPU. Despite their size, Inflect-v2 delivers quality that is competitive with much larger lightweight TTS systems, including KittenTTS, Piper, and Supertonic-3.

CPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0.

See it for yourselves:
owensong/Inflect-Micro-v2
owensong/Inflect-Nano-v2

Try the Demos:
Nymbo/Inflect-TTS (unlimited CPU usage)
owensong/Inflect-v2 (ultra-fast ZeroGPU usage)
  • 6 replies
ยท
DmitryRyuminย 
authored 2 papers 2 months ago
GeorgeBredisย 
submitted a paper to Daily Papers 2 months ago
DongfuJiangย 
authored 2 papers 3 months ago
fffiloniย 
posted an update 3 months ago
fffiloniย 
posted an update 3 months ago
view post
Post
1904
I made a Hugging Face Space for SCAIL-2 ๐Ÿค—

Reference character + driving motion โ†’ animated result.

A simple demo to explore the paperโ€™s core workflow with curated examples.

๐Ÿ‘‰ fffiloni/SCAIL-2
  • 1 reply
ยท
fffiloniย 
posted an update 3 months ago
view post
Post
857
โฑ๏ธ Built a small Space for Visual Chronometer / Pulse of Motion.

Upload a video and estimate its Physical FPS: the frame rate implied by visual motion, independent of metadata.
Useful to inspect โ€œchronometric hallucinationโ€ in generated videos: clips that look smooth, but move with the wrong physical time scale.

Try it here: fffiloni/Pulse-of-Motion
  • 1 reply
ยท
fffiloniย 
posted an update 3 months ago
view post
Post
1659
A few weeks ago, @victor opened the door: coding agents can now ship Hugging Face Spaces autonomously.

I pulled on that thread.

As someone who builds and ships Gradio demos regularly, I didnโ€™t just want to reproduce the loop. I wanted to see what happens when that loop is plugged into the whole Hugging Face stack.

The interesting part is not only that an agent can ship a Space.

Itโ€™s what happens when Space generation becomes a first-class Hugging Face workflow.

That became Agentic Space Factory.

More soon. ๐Ÿค—
  • 1 reply
ยท
eienmojikiย 
posted an update 3 months ago
KingNishย 
posted an update 3 months ago
view post
Post
4888
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:
๐Ÿค– Demo โ†’ build-small-hackathon/OpenMythos
๐Ÿง  Model โ†’ build-small-hackathon/OpenMythos
๐Ÿ“ฆ CVE Dataset โ†’ build-small-hackathon/CVE_Vulnerailities_Detailed
๐Ÿ“„ ArXiv Dataset โ†’ himanshu17HF/ArvixImport-Filtered-Final

Try it out and let us know where it breaks ๐Ÿ™
  • 2 replies
ยท
Abhaykoulย 
posted an update 3 months ago
view post
Post
436
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.
DongfuJiangย 
authored 2 papers 4 months ago