Not Truly Multilingual: Script Consistency as a Missing Dimension in VLM Evaluation
Paper โข 2606.17188 โข Published โข 1
Dev Mode Explorers
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Prabhjotschughย
authored 4
papers about 5 hours ago
FirstPass: Grounding AI Scientific Judgment in Multi-Round Editorial Outcomes
Paper โข 2606.20769 โข Published โข 1
Beyond 'One Language, One Script': Quantifying Orthographic Bias in Multilingual VLMs with PuMVR
Paper โข 2606.20770 โข Published โข 1
AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion
Paper โข 2605.26130 โข Published โข 1
eienmojikiย
posted an update 4 days ago
Post
105
Hi everyone,
I've created a Gradio space for embedding and extracting invisible watermarks in images:
๐ eienmojiki/blind-watermark-studio
It supports hiding text, images, and bit arrays using the DWT-DCT-SVD algorithm.
Credits:
- Original library: https://github.com/guofei9987/blind_watermark
- Author: Guo Fei
:).
I've created a Gradio space for embedding and extracting invisible watermarks in images:
๐ eienmojiki/blind-watermark-studio
It supports hiding text, images, and bit arrays using the DWT-DCT-SVD algorithm.
Credits:
- Original library: https://github.com/guofei9987/blind_watermark
- Author: Guo Fei
:).
Post
4301
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
- 2 replies
Post
223
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.
DongfuJiangย
authored 3
papers 24 days ago
RewardHarness: Self-Evolving Agentic Post-Training
Paper โข 2605.08703 โข Published โข 10
Cosmos 3: Omnimodal World Models for Physical AI
Paper โข 2606.02800 โข Published โข 136
AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?
Paper โข 2606.05080 โข Published โข 30
alielfilali01ย
posted an update about 1 month ago
Post
563
Plans in HTML > Plans in Markdown
Post
2972
๐๐ปโโ๏ธ Hey there folks ,
Turns out : if we predict ๐ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery ๐ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐กearth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
Turns out : if we predict ๐ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery ๐ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐กearth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
- 2 replies
DongfuJiangย
authored 4
papers about 2 months ago
Watch Before You Answer: Learning from Visually Grounded Post-Training
Paper โข 2604.05117 โข Published โข 36
ClawBench: Can AI Agents Complete Everyday Online Tasks?
Paper โข 2604.08523 โข Published โข 265
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
Paper โข 2604.12374 โข Published โข 37
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
Paper โข 2605.05242 โข Published โข 126
Prabhjotschughย
authored a
paper about 2 months ago
Post
4351
๐๐ปโโ๏ธ Hey there folks,
since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !
Check this one out :
NuTonic/sat-bbox-metadata-sft-v1
the goal is to be able to train vision models on multiple images for remote sensing analysis with one shot .
hope you like it ! ๐
since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !
Check this one out :
NuTonic/sat-bbox-metadata-sft-v1
the goal is to be able to train vision models on multiple images for remote sensing analysis with one shot .
hope you like it ! ๐
- 2 replies
Post
3681
๐๐ปโโ๏ธ Hey there folks ,
I'm sharing huggingface's largest dataset of annotated statelite images today.
check it out here : NuTonic/sat-image-boundingbox-sft-full
I hope you like it , the idea is to be able to use this with small vision models ๐
I'm sharing huggingface's largest dataset of annotated statelite images today.
check it out here : NuTonic/sat-image-boundingbox-sft-full
I hope you like it , the idea is to be able to use this with small vision models ๐
1aurentย
authored a
paper 3 months ago