Yume-1.5: A Text-Controlled Interactive World Generation Model
Paper
•
2512.22096
•
Published
•
55
AI & ML interests
Computer Vision
Recent Activity
View all activity
Papers
InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision
ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution
kpzhang996
submitted
a
paper
to Daily Papers
4 days ago
lll2343
updated
3
models
7 days ago
revliter
updated
a
collection
10 days ago
Eurayka
authored
a
paper
15 days ago
Post
1853
🚨 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
revliter
updated
a
collection
about 1 month ago
Qingyun
authored
a
paper
about 1 month ago
Post
5106
🚀 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
ZeqiangLai
authored
a
paper
about 1 month ago
cyyang822
authored
a
paper
about 1 month ago
zyliu
updated
a
collection
about 2 months ago
Eurayka
authored
4
papers
about 2 months ago
InternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding
Paper
•
2403.15377
•
Published
•
27
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
Paper
•
2410.19702
•
Published
•
1
Make Your Training Flexible: Towards Deployment-Efficient Video Models
Paper
•
2503.14237
•
Published
•
5
ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
Paper
•
2510.11606
•
Published
•
4