Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision
Paper • 2609.07099 • Published • 3
AI & ML interests
Flax / JAX community event for sentence-embeddings
Recent Activity
View all activity
infinitylogesh
authored 2
papers about 16 hours ago
infinitylogesh
submitted 2
papers to Daily Papers about 17 hours ago
minsik-oh
updated 3
models about 1 month ago
minsik-oh
updated a
dataset about 1 month ago
espejelomar
posted an update 4 months ago
Post
4765
Sharing WorldForge with @abdelstark
It's an open-source Python project for evaluating and replaying robotics and world-model workflows.
The useful part is not only calling a model. WorldForge records the run, validates action shapes, translates outputs into actions, and keeps replay artifacts you can inspect later.
The current demo uses LeRobot + LeWorldModel on PushT through the official loader:
The harness also has replay-only paths for Cosmos-Policy and GR00T-style outputs, so you can inspect the provider contract from saved artifacts without keeping a GPU server online.
Try it:
Repo: https://github.com/AbdelStark/worldforge
Docs: https://abdelstark.github.io/worldforge/
Pre-1.0, MIT, and actively looking for contributors. Good areas:
- robotics provider adapters
- replay artifacts
- eval flows
- docs & first-run demos
Good first issues: https://github.com/AbdelStark/worldforge/contribute
If you're building robot policy evals or model adapters, would love a PR — or an issue describing what's missing.
It's an open-source Python project for evaluating and replaying robotics and world-model workflows.
The useful part is not only calling a model. WorldForge records the run, validates action shapes, translates outputs into actions, and keeps replay artifacts you can inspect later.
The current demo uses LeRobot + LeWorldModel on PushT through the official loader:
stable_worldmodel.policy.AutoCostModel("pusht/lewm")The harness also has replay-only paths for Cosmos-Policy and GR00T-style outputs, so you can inspect the provider contract from saved artifacts without keeping a GPU server online.
Try it:
pip install worldforge-aiuv run --extra harness worldforge-harness --flow robotics-compareRepo: https://github.com/AbdelStark/worldforge
Docs: https://abdelstark.github.io/worldforge/
Pre-1.0, MIT, and actively looking for contributors. Good areas:
- robotics provider adapters
- replay artifacts
- eval flows
- docs & first-run demos
Good first issues: https://github.com/AbdelStark/worldforge/contribute
If you're building robot policy evals or model adapters, would love a PR — or an issue describing what's missing.
vinid
submitted a
paper to Daily Papers 8 months ago
infinitylogesh
authored a
paper almost 2 years ago
vinid
authored 6
papers over 2 years ago
Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
Paper • 2211.03759 • Published
Contrastive Language-Image Pre-training for the Italian Language
Paper • 2108.08688 • Published • 2
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
Paper • 2308.01263 • Published
Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
Paper • 2309.07875 • Published
When and why vision-language models behave like bags-of-words, and what to do about it?
Paper • 2210.01936 • Published
TextGrad: Automatic "Differentiation" via Text
Paper • 2406.07496 • Published • 31
manandey
authored 2
papers over 2 years ago
infinitylogesh
authored a
paper about 3 years ago