SemanticMoments: Training-Free Motion Similarity via Third Moment Features
Paper
β’ 2602.09146 β’ Published
β’ 21
AI & ML interests
CVPR Demo Track @ CVPR 2022
Recent Activity
View all activity
noamrotΒ
submitted a paper to Daily Papers 27 days ago
gagan3012Β
authored 2 papers 2 months ago
noamrotΒ
authored a paper 2 months ago
DavidVivancosΒ
posted an
update 3 months ago
Post
349
Need a new challenging Dataset? Now that #NeurIPS2025 is almost over.
DavidVivancos/NeuraxonLife2-1M
1 Million #Neuraxon Artificial Lives, from almost 10000 Research Game runs, with more than 21 Million Neurons and almost 4 years of Simulated Life.
Read the preprint here https://www.researchgate.net/publication/397331336_Neuraxon
And here you have all the code: https://github.com/DavidVivancos/Neuraxon
DavidVivancos/NeuraxonLife2-1M
1 Million #Neuraxon Artificial Lives, from almost 10000 Research Game runs, with more than 21 Million Neurons and almost 4 years of Simulated Life.
Read the preprint here https://www.researchgate.net/publication/397331336_Neuraxon
And here you have all the code: https://github.com/DavidVivancos/Neuraxon
yumingjΒ
authored a paper 4 months ago
DavidVivancosΒ
posted an
update 4 months ago
Post
388
Hi all!,
Neuraxon Game of Life is also live in demo at HuggingFace
DavidVivancos/NeuraxonLife
Preprint Paper: https://www.researchgate.net/publication/397331336_Neuraxon
Source Code of the Research verision: https://github.com/DavidVivancos/Neuraxon
HuggingFace Models are in the oven!
Hope you like it!
@DavidVivancos
Neuraxon Game of Life is also live in demo at HuggingFace
DavidVivancos/NeuraxonLife
Preprint Paper: https://www.researchgate.net/publication/397331336_Neuraxon
Source Code of the Research verision: https://github.com/DavidVivancos/Neuraxon
HuggingFace Models are in the oven!
Hope you like it!
@DavidVivancos
noamrotΒ
authored a paper 4 months ago
abidlabsΒ
authored 3 papers 4 months ago
Persistent Anti-Muslim Bias in Large Language Models
Paper
β’ 2101.05783 β’ Published
β’ 3
STG-MTL: Scalable Task Grouping for Multi-Task Learning Using Data Map
Paper
β’ 2307.03374 β’ Published
β’ 2
Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild
Paper
β’ 1906.02569 β’ Published
β’ 2
DavidVivancosΒ
posted an
update 4 months ago
Post
994
Hi all!,
Neuraxon ( a novel Neural Growth & Computation Blueprint) is live in demo at HuggingFace DavidVivancos/Neuraxon
Paper: https://www.researchgate.net/publication/397331336_Neuraxon (on its way to arxiv too)
Code: https://github.com/DavidVivancos/Neuraxon
HuggingFace Model in the oven!
Hope you like it!
@DavidVivancos
Neuraxon ( a novel Neural Growth & Computation Blueprint) is live in demo at HuggingFace DavidVivancos/Neuraxon
Paper: https://www.researchgate.net/publication/397331336_Neuraxon (on its way to arxiv too)
Code: https://github.com/DavidVivancos/Neuraxon
HuggingFace Model in the oven!
Hope you like it!
@DavidVivancos
- 2 replies
Post
10156
Why I think local, open-source models will eventually win.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly βsmarterβ closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users wonβt accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are βgood enoughβ and the expectation will shift toward everything running locally. Itβll happen sooner than most people think.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly βsmarterβ closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users wonβt accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are βgood enoughβ and the expectation will shift toward everything running locally. Itβll happen sooner than most people think.
- 8 replies
gagan3012Β
authored a paper 5 months ago
yuna0x0Β
authored a paper 6 months ago
yumingjΒ
authored a paper 6 months ago
Post
1591
What other features would you like to see on the Trackio Dashboard? ( gradio-templates/trackio-dashboard)
yumingjΒ
authored a paper 6 months ago
Post
3304
π Ever dreamed of training your own Large Language Model from scratch? What if I told you it doesn't require a supercomputer or PhD in ML? π€―
Introducing LLM Trainer - the educational framework that makes LLM training accessible to EVERYONE! Whether you're on a CPU-only laptop or scaling to distributed GPUs, we've got you covered. π»β‘οΈπ₯οΈ
Why LLM Trainer? Because existing tools are either too simplistic (hiding the magic) or too complex (requiring expert knowledge). We bridge the gap with:
π Educational transparency - every component built from scratch with clear code
π» CPU-first approach - start training immediately, no GPU needed
π§ Full customization - modify anything you want
π Seamless scaling - from laptop to cluster without code changes
π€ HuggingFace integration - works with existing models & tokenizers
Key highlights:
β Built-in tokenizers (BPE, WordPiece, HF wrappers)
β Complete Transformer implementation from scratch
β Optimized for CPU training
β Advanced features: mixed precision, gradient checkpointing, multiple generation strategies
β Comprehensive monitoring & metrics
Perfect for:
- Students learning transformers
- Researchers prototyping new ideas
- Developers building domain-specific models
Ready to train your first LLM? It's easier than you think!
π Check it out: https://github.com/HelpingAI/llm-trainer
π Docs: Getting Started Guide
π¬ Join the community: GitHub Discussions
#AI #MachineLearning #LLM #DeepLearning #OpenSource #Python #HuggingFace #NLP
Special thanks to HuggingFace and PyTorch teams for the amazing ecosystem! π
Introducing LLM Trainer - the educational framework that makes LLM training accessible to EVERYONE! Whether you're on a CPU-only laptop or scaling to distributed GPUs, we've got you covered. π»β‘οΈπ₯οΈ
Why LLM Trainer? Because existing tools are either too simplistic (hiding the magic) or too complex (requiring expert knowledge). We bridge the gap with:
π Educational transparency - every component built from scratch with clear code
π» CPU-first approach - start training immediately, no GPU needed
π§ Full customization - modify anything you want
π Seamless scaling - from laptop to cluster without code changes
π€ HuggingFace integration - works with existing models & tokenizers
Key highlights:
β Built-in tokenizers (BPE, WordPiece, HF wrappers)
β Complete Transformer implementation from scratch
β Optimized for CPU training
β Advanced features: mixed precision, gradient checkpointing, multiple generation strategies
β Comprehensive monitoring & metrics
Perfect for:
- Students learning transformers
- Researchers prototyping new ideas
- Developers building domain-specific models
Ready to train your first LLM? It's easier than you think!
π Check it out: https://github.com/HelpingAI/llm-trainer
π Docs: Getting Started Guide
π¬ Join the community: GitHub Discussions
#AI #MachineLearning #LLM #DeepLearning #OpenSource #Python #HuggingFace #NLP
Special thanks to HuggingFace and PyTorch teams for the amazing ecosystem! π
- 1 reply
Post
4171
π Dhanishtha-2.0-preview-0825 Is Here
The Intermediate Thinking Model just leveled up again.
With sharper reasoning, better tool use, and expanded capabilities, Dhanishtha-2.0-preview-0825 is now live and ready to impress.
π§ What Makes Dhanishtha Special?
Unlike typical CoT models that only thinks one time, Dhanishtha thinks iteratively:
> Think β Answer β Rethink β Improve β Rethink again if needed.
π Try it now: HelpingAI/Dhanishtha-2.0-preview-0825
π Dhanishtha NSFW Preview
For those exploring more expressive and immersive roleplay scenarios, weβre also releasing:
HelpingAI/Dhanishtha-nsfw
A specialized version tuned for adult-themed interactions and character-driven roleplay.
π Explore it here: HelpingAI/Dhanishtha-nsfw
π¬ You can also try all of these live at chat.helpingai.co
The Intermediate Thinking Model just leveled up again.
With sharper reasoning, better tool use, and expanded capabilities, Dhanishtha-2.0-preview-0825 is now live and ready to impress.
π§ What Makes Dhanishtha Special?
Unlike typical CoT models that only thinks one time, Dhanishtha thinks iteratively:
> Think β Answer β Rethink β Improve β Rethink again if needed.
π Try it now: HelpingAI/Dhanishtha-2.0-preview-0825
π Dhanishtha NSFW Preview
For those exploring more expressive and immersive roleplay scenarios, weβre also releasing:
HelpingAI/Dhanishtha-nsfw
A specialized version tuned for adult-themed interactions and character-driven roleplay.
π Explore it here: HelpingAI/Dhanishtha-nsfw
π¬ You can also try all of these live at chat.helpingai.co
- 4 replies