Beyond Text and Tables: Vision-Language Model Integration in ComProScanner for Extracting Materials Data from Scientific Figures with High Accuracy
Paper • 2606.00065 • Published
AI & ML interests
Nanochat, fine-tuning, LLMs, post-training
aritraroy24
authored a
paper 2 months ago
rajkumarrawal
submitted a
paper to Daily Papers 3 months ago
Post
3150
🙋🏻♂️ Hey there folks ,
Turns out : if we predict 🌏 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 🛰️basically 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 📡earth-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 🌏 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 🛰️basically 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 📡earth-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
aritraroy24
authored a
paper 3 months ago
rajkumarrawal
posted an update 3 months ago
Post
2150
LLMs aren’t just answering questions anymore, they’re learning to evolve. Self evolving AI is the true endgame.
AI has shifted from short tasks to long missions. The breakthrough isn’t just automation, it’s machines learning human methods and applying them at machine speed. From cybersecurity to finance, from OPCs to NPCs, the wave is irreversible.
Read the full article: Self Evolving is the Endgame or final destiny
https://huggingface.co/blog/rajkumarrawal/self-evolving-is-the-endgame-or-final-destiny
What’s your definition of true AGI? Comment below.
AI has shifted from short tasks to long missions. The breakthrough isn’t just automation, it’s machines learning human methods and applying them at machine speed. From cybersecurity to finance, from OPCs to NPCs, the wave is irreversible.
Read the full article: Self Evolving is the Endgame or final destiny
https://huggingface.co/blog/rajkumarrawal/self-evolving-is-the-endgame-or-final-destiny
What’s your definition of true AGI? Comment below.
- 1 reply
rajkumarrawal
posted an update 3 months ago
Post
234
I submitted a "Learning to Act and Cooperate for Distributed Black-Box Consensus Optimization" Paper by Zi-Bo Qin, Feng-Feng Wei, Tai-You Chen, Wei-Neng Chen to Daily Papers on huggingface.
A trajectory-driven framework uses large language models to guide agent behavior and cooperation patterns in distributed black-box consensus optimization, improving solution quality and efficiency.
Learning to Act and Cooperate for Distributed Black-Box Consensus Optimization (2605.00691)
A trajectory-driven framework uses large language models to guide agent behavior and cooperation patterns in distributed black-box consensus optimization, improving solution quality and efficiency.
Learning to Act and Cooperate for Distributed Black-Box Consensus Optimization (2605.00691)
rajkumarrawal
submitted a
paper to Daily Papers 3 months ago
Post
4402
🙋🏻♂️ 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 ! 🚀
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 ! 🚀
- 2 replies
Post
3711
🙋🏻♂️ 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 🚀
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 🚀
rajkumarrawal
posted an update 4 months ago
Post
1585
I submitted a "Context-Value-Action Architecture for Value-Driven Large Language Model Agents" Paper by TianZe Zhang, Sirui Sun, Yuhang Xie, Xin Zhang Zhiqiang Wu Guojie Song· From 
PekingUniversity to Daily Papers on 
huggingface .
Large language models exhibit behavioral rigidity that worsens with intensified reasoning, prompting the development of a Context-Value-Action architecture that decouples action generation from cognitive reasoning using a Value Verifier trained on human data.
Context-Value-Action Architecture for Value-Driven Large Language Model Agents (2604.05939)
Large language models exhibit behavioral rigidity that worsens with intensified reasoning, prompting the development of a Context-Value-Action architecture that decouples action generation from cognitive reasoning using a Value Verifier trained on human data.
Context-Value-Action Architecture for Value-Driven Large Language Model Agents (2604.05939)
rajkumarrawal
submitted a
paper to Daily Papers 4 months ago
Post
3847
🤔 Who would win ?
- a fully subsidized ai lab
- 3 random students named
kurakurai ?
demo : Tonic/fr-on-device
if you like it give the demo a little star and send a shoutout to : @MaxLSB @jddqd and @GAD-cell for absolutely obliterating the pareto frontier of the french language understanding .
- a fully subsidized ai lab
OR - 3 random students named
demo : Tonic/fr-on-device
if you like it give the demo a little star and send a shoutout to : @MaxLSB @jddqd and @GAD-cell for absolutely obliterating the pareto frontier of the french language understanding .
- 4 replies
Post
3491
🙋🏻♂️hello my lovelies ,
it is with great pleasure i present to you my working one-click deploy 16GB ram completely free huggingface spaces deployment.
repo : Tonic/hugging-claw (use git clone to inspect)
literally the one-click link : Tonic/hugging-claw
you can also run it locally and see for yourself :
docker run -it -p 7860:7860 --platform=linux/amd64 \
-e HF_TOKEN="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_TRUSTED_PROXIES="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_PASSWORD="YOUR_VALUE_HERE" \
-e OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS="YOUR_VALUE_HERE" \
registry.hf.space/tonic-hugging-claw:latest
just a few quite minor details i'll take care of but i wanted to share here first
it is with great pleasure i present to you my working one-click deploy 16GB ram completely free huggingface spaces deployment.
repo : Tonic/hugging-claw (use git clone to inspect)
literally the one-click link : Tonic/hugging-claw
you can also run it locally and see for yourself :
docker run -it -p 7860:7860 --platform=linux/amd64 \
-e HF_TOKEN="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_TRUSTED_PROXIES="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_PASSWORD="YOUR_VALUE_HERE" \
-e OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS="YOUR_VALUE_HERE" \
registry.hf.space/tonic-hugging-claw:latest
just a few quite minor details i'll take care of but i wanted to share here first
- 2 replies
Post
364
When an AI Model Solves College-Level Math and Physics — On a Phone
This morning I came across a model called Nanbeige4.1-3B, and what began as simple curiosity quickly became something more significant.
I loaded an already 4-bit quantized version and ran it locally on a phone. No GPU, no cloud support, no hidden infrastructure — just a compact reasoning model operating entirely at the edge.
I started with classical mechanics: acceleration, force, friction on an incline. The model worked through them cleanly and correctly. Then I stepped into calculus and gave it a differential equation. It immediately recognized the structure, chose the proper method, carried the mathematics through without confusion, and verified the result.
It did not behave like a model trying to sound intelligent. It behaved like a system trained to solve problems.
And it was doing this on a phone.
For a long time, we have associated serious reasoning in AI with massive models and enormous compute. Capability was supposed to live inside data centers. Bigger models were expected to mean smarter systems.
But watching Nanbeige4.1-3B handle college-level math and physics forces a rethink of that assumption. Intelligence is not only expanding — it is compressing. Better training and sharper reasoning alignment are allowing smaller models to operate far beyond what their size once suggested.
When structured problem-solving runs locally on pocket hardware, the implications are larger than they first appear. Experimentation becomes personal. Engineers can explore ideas without waiting on infrastructure. Students can access serious analytical capability from a device they already carry. Builders are no longer required to send every complex task into the cloud.
What makes moments like this easy to miss is that they rarely arrive with fanfare. There is no dramatic announceme
The model responses are here
https://fate-stingray-0b3.notion.site/AI-model-Nanbeige4-1-3B-304
This morning I came across a model called Nanbeige4.1-3B, and what began as simple curiosity quickly became something more significant.
I loaded an already 4-bit quantized version and ran it locally on a phone. No GPU, no cloud support, no hidden infrastructure — just a compact reasoning model operating entirely at the edge.
I started with classical mechanics: acceleration, force, friction on an incline. The model worked through them cleanly and correctly. Then I stepped into calculus and gave it a differential equation. It immediately recognized the structure, chose the proper method, carried the mathematics through without confusion, and verified the result.
It did not behave like a model trying to sound intelligent. It behaved like a system trained to solve problems.
And it was doing this on a phone.
For a long time, we have associated serious reasoning in AI with massive models and enormous compute. Capability was supposed to live inside data centers. Bigger models were expected to mean smarter systems.
But watching Nanbeige4.1-3B handle college-level math and physics forces a rethink of that assumption. Intelligence is not only expanding — it is compressing. Better training and sharper reasoning alignment are allowing smaller models to operate far beyond what their size once suggested.
When structured problem-solving runs locally on pocket hardware, the implications are larger than they first appear. Experimentation becomes personal. Engineers can explore ideas without waiting on infrastructure. Students can access serious analytical capability from a device they already carry. Builders are no longer required to send every complex task into the cloud.
What makes moments like this easy to miss is that they rarely arrive with fanfare. There is no dramatic announceme
The model responses are here
https://fate-stingray-0b3.notion.site/AI-model-Nanbeige4-1-3B-304
- 4 replies
rajkumarrawal
posted an update 6 months ago
Post
235
I submitted a "Continual GUI Agents" Paper by Ziwei Liu, Borul Kang, Hangjie Yuan, Zixiang Zhao, Wei li, Yifan Zhu, Tao Feng ,
From
Tsinghua , 
ZhejiangUniversity , 
ethz , 
BUPT2023213296 . to Daily Papers on huggingface .
Continual GUI Agents framework addresses performance degradation in dynamic digital environments through reinforcement fine tuning with novel anchoring rewards that stabilize learning across shifting UI domains and resolutions.
Continual GUI Agents (2601.20732)
From
Continual GUI Agents framework addresses performance degradation in dynamic digital environments through reinforcement fine tuning with novel anchoring rewards that stabilize learning across shifting UI domains and resolutions.
Continual GUI Agents (2601.20732)
Post
2172
GLM-OCR: A Tiny 0.9B-Parameter Model That Punches Far Above Its Weight
Released today by Z.ai, GLM-OCR is a compact vision-language model designed specifically for document understanding. At just 0.9 billion parameters, it belongs to a new generation of lightweight AI systems proving that raw model size is no longer the only path to high performance.
Despite its small footprint, GLM-OCR posts exceptionally strong results across major document benchmarks. It scores 94.6 on OmniDocBench, 94.0 on OCRBench, and an impressive 96.5 on UniMERNet for formula recognition—numbers that place it alongside, and in some cases ahead of, significantly larger specialized OCR models. The takeaway is clear: efficiency is rapidly becoming a defining feature of modern AI design.
Developed by Z.ai, a research group focused on advancing multimodal foundation models, GLM-OCR reflects a broader shift toward highly optimized architectures that deliver serious capability without requiring massive compute resources.
In practical testing, the model ran successfully in Google Colab on an NVIDIA L4 GPU, demonstrating that advanced document AI is no longer restricted to large research clusters. Engineers, researchers, and developers can now deploy high-quality OCR workflows from relatively accessible hardware.
GLM-OCR signals an important trend in artificial intelligence: smaller, purpose-built models are beginning to rival heavyweight systems while being dramatically easier to run. For anyone working with scanned documents, PDFs, or structured text extraction, this release is a strong indicator of where efficient multimodal AI is heading next.
The google colab notebook for the model
https://colab.research.google.com/drive/1SiXjxPdb-7UJWhtAjPrMZYqPJhyLk9Rc?usp=sharing
The Huggingface model page
zai-org/GLM-OCR
Released today by Z.ai, GLM-OCR is a compact vision-language model designed specifically for document understanding. At just 0.9 billion parameters, it belongs to a new generation of lightweight AI systems proving that raw model size is no longer the only path to high performance.
Despite its small footprint, GLM-OCR posts exceptionally strong results across major document benchmarks. It scores 94.6 on OmniDocBench, 94.0 on OCRBench, and an impressive 96.5 on UniMERNet for formula recognition—numbers that place it alongside, and in some cases ahead of, significantly larger specialized OCR models. The takeaway is clear: efficiency is rapidly becoming a defining feature of modern AI design.
Developed by Z.ai, a research group focused on advancing multimodal foundation models, GLM-OCR reflects a broader shift toward highly optimized architectures that deliver serious capability without requiring massive compute resources.
In practical testing, the model ran successfully in Google Colab on an NVIDIA L4 GPU, demonstrating that advanced document AI is no longer restricted to large research clusters. Engineers, researchers, and developers can now deploy high-quality OCR workflows from relatively accessible hardware.
GLM-OCR signals an important trend in artificial intelligence: smaller, purpose-built models are beginning to rival heavyweight systems while being dramatically easier to run. For anyone working with scanned documents, PDFs, or structured text extraction, this release is a strong indicator of where efficient multimodal AI is heading next.
The google colab notebook for the model
https://colab.research.google.com/drive/1SiXjxPdb-7UJWhtAjPrMZYqPJhyLk9Rc?usp=sharing
The Huggingface model page
zai-org/GLM-OCR
rajkumarrawal
posted an update 6 months ago
Post
3701
I submitted a "FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning" Paper by Tanyu Chen, Tairan Chen, Kai shen , Zhenghua Bao, Zhihui Zhang, Man Yuan, Yi Shi From 
FlashLabs to Daily Papers on huggingface .
Chroma 1.0 enables real time spoken dialogue with personalized voice cloning through discrete speech representations and interleaved text audio token scheduling.
Chroma 1.0 , the world’s first open source, real time speech to speech model with voice cloning.
FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning (2601.11141)
Chroma 1.0 enables real time spoken dialogue with personalized voice cloning through discrete speech representations and interleaved text audio token scheduling.
Chroma 1.0 , the world’s first open source, real time speech to speech model with voice cloning.
FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning (2601.11141)
rajkumarrawal
submitted a
paper to Daily Papers 6 months ago
Post
3021
KittenTTS Nano — Tiny, Expressive, Practical
KittenTTS Nano is a lightweight, CPU-only text-to-speech model designed to prove that natural, expressive voices don’t require massive cloud stacks or GPUs. At roughly ~15M parameters, it runs fast on modest hardware, supports multiple expressive voices, and exposes simple controls for pacing and tone. This makes it ideal for edge devices, demos, and anyone who wants full control over TTS without latency, lock-in, or infrastructure overhead.
Try it here
Javedalam/KittenTTS
The model page
KittenML/kitten-tts-nano-0.2
KittenTTS Nano is a lightweight, CPU-only text-to-speech model designed to prove that natural, expressive voices don’t require massive cloud stacks or GPUs. At roughly ~15M parameters, it runs fast on modest hardware, supports multiple expressive voices, and exposes simple controls for pacing and tone. This makes it ideal for edge devices, demos, and anyone who wants full control over TTS without latency, lock-in, or infrastructure overhead.
Try it here
Javedalam/KittenTTS
The model page
KittenML/kitten-tts-nano-0.2
- 2 replies
rajkumarrawal
submitted a
paper to Daily Papers 7 months ago