FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation
Paper
•
2512.24724
•
Published
•
4
AI & ML interests
None defined yet.
Recent Activity
View all activity
akhaliq
submitted
2
papers
to Daily Papers
4 days ago
Post
1916
🚨 New tool for the
Nymbo/Tools MCP server: The new
How it works: The tool exposes the standard discover/info/resources/validate actions. Skills live in
I've included a
Caveat: On HF Spaces,
Try it out ~ https://www.nymbo.net/nymbot
Agent_Skills tool provides full support for Agent Skills (Claude Skills but open-source).How it works: The tool exposes the standard discover/info/resources/validate actions. Skills live in
/Skills under the same File_System root, and any bundled scripts run through Shell_Command, no new infrastructure required.Agent_Skills(action="discover") # List all available skills
Agent_Skills(action="info", skill_name="music-downloader") # Full SKILL.md
Agent_Skills(action="resources", skill_name="music-downloader") # Scripts, refs, assetsI've included a
music-downloader skill as a working demo, it wraps yt-dlp for YouTube/SoundCloud audio extraction.Caveat: On HF Spaces,
Shell_Command works for most tasks, but some operations (like YouTube downloads) are restricted due to the container environment. For full functionality, run the server locally on your machine.Try it out ~ https://www.nymbo.net/nymbot
akhaliq
submitted
a
paper
to Daily Papers
20 days ago
kenobi
authored
3
papers
21 days ago
On Invariance Penalties for Risk Minimization
Paper
•
2106.09777
•
Published
Generating (Factual?) Narrative Summaries of RCTs: Experiments with Neural Multi-Document Summarization
Paper
•
2008.11293
•
Published
Bayesian Deep Learning for Exoplanet Atmospheric Retrieval
Paper
•
1811.03390
•
Published
akhaliq
submitted
a
paper
to Daily Papers
25 days ago
akhaliq
submitted
a
paper
to Daily Papers
27 days ago
DavidVivancos
posted
an
update
about 1 month ago
Post
265
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
Post
5155
🚀 I've just shipped a major update to the
Nymbo/Tools MCP server: the
Anthropic found 98.7% context savings using code execution with MCP, Cloudflare published similar findings. This is my open-source implementation of the same idea.
# The Problem
Traditional MCP exposes every tool definition directly to the model. With 12 tools, that's thousands of tokens consumed *before the conversation even starts*. Each tool call also passes intermediate results through the context window — a 10,000-row spreadsheet? That's all going into context just to sum a column.
# The Solution: One Tool to Rule Them All
Instead of the model making individual tool calls, it writes Python code that orchestrates the tools directly:
Don't know what tools are available? The agent can discover them at runtime:
The individual direct tool calls are all still there, but they can be disabled if using the
Agent_Terminal, a single "master tool" that cuts token usage by over 90%!Anthropic found 98.7% context savings using code execution with MCP, Cloudflare published similar findings. This is my open-source implementation of the same idea.
# The Problem
Traditional MCP exposes every tool definition directly to the model. With 12 tools, that's thousands of tokens consumed *before the conversation even starts*. Each tool call also passes intermediate results through the context window — a 10,000-row spreadsheet? That's all going into context just to sum a column.
# The Solution: One Tool to Rule Them All
Agent_Terminal wraps all 12 tools (Web_Search, Web_Fetch, File_System, Generate_Image, Generate_Speech, Generate_Video, Deep_Research, Memory_Manager, Obsidian_Vault, Shell_Command, Code_Interpreter) into a single Python code execution gateway.Instead of the model making individual tool calls, it writes Python code that orchestrates the tools directly:
# Search for Bitcoin price
result = Web_Search("current price of bitcoin", max_results=3)
print(result)Don't know what tools are available? The agent can discover them at runtime:
print(search_tools('image')) # Find tools by keyword
print(usage('Generate_Image')) # Get full docs for a specific toolThe individual direct tool calls are all still there, but they can be disabled if using the
Agent_Terminal. Try it now - https://www.nymbo.net/nymbot
- 1 reply
Lupin1998
authored
2
papers
about 1 month ago
Kameshr
authored
a
paper
about 2 months ago
DavidVivancos
posted
an
update
about 2 months ago
Post
318
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
abidlabs
authored
3
papers
about 2 months ago
DavidVivancos
posted
an
update
about 2 months ago
Post
981
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
8884
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 “smarter” 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 won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll 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 “smarter” 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 won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
- 8 replies