lulavc PRO
lulavc
AI & ML interests
None yet
Recent Activity
repliedto their post about 4 hours ago
To the Deepseek Team
I had some issues with my Google Workspace account (DNS got all messes up) and basically im not able to access my Gmail and im not able to fix my DNS because hostingeris not helping too much on that. I gave all my documents, IDs, payment receipts etc... But i still not able to access.
WHY im asking for help... Because Deepseek is one of the models that i PAY The API for long time and im not able to access my account. I have one API that i dont know if Will work with v4 and i would like tô the Deepseek Team tô help me. The e-mail registered is the same email i use on Huggingface. I have IDs payment receipts from top ups... Everything but i already sent like 5 e-mails tô Deepseek support with no answer. Sorry for talking about that here but i had no other way tô reach you up.
And for Huggingface...i iwe you about 2 USD that i Will PAY... But im waiting my New CC arrive. Im a long time user and i wont do any wrong thing like not paying but you could please reactivate some of my services. I go tô Hospital every week for radiotherapy and sometimes i dont feel good and basically i forgot some hardware on and charged me those 2 USD. I promess all Will be resolved soon.
Thank you all!!! reacted to salma-remyx's post with 🔥 about 4 hours ago
The space of possible improvements for your AI model is large while evaluation is costly.
So I was excited to discover the ICML 2026 paper from Kobalczyk, Lin, Letham, Zhao, Balandat, and Bakshy titled "LILO: Bayesian Optimization with Natural Language Feedback."
The method learns efficiently from expert preferences, balancing exploration and exploitation in a principled way with Bayesian Optimization for expensive-to-evaluate black-box objectives.
Experimenting with the technique, I trained a Gaussian Process proxy model on the implicit preferences in my code repo's commit history at VQASynth.
The result: I used the model's preference scores to re-rank candidate papers recommended based on my interests in spatial reasoning and multimodal data synthesis.
Semantic relevance is a high-recall method for finding arXiv papers personalized to your interests. Adding contributor preferences, extracted from the merge history of your code offers a high-precision filter.
So what's next? I'm using the model to synthesize a larger volume of preference data to finetune an open-weight coding model with DPO and LoRA. Tuning Coding Agents via Implicit Preference Distillation
arXiv: https://arxiv.org/pdf/2510.17671
Substack: https://remyxai.substack.com/p/lilo-and-myx
VQASynth: https://github.com/remyxai/VQASynth reacted to espejelomar's post with ❤️ about 4 hours ago
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:
`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-ai`
`uv run --extra harness worldforge-harness --flow robotics-compare`
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.Organizations
