February 2026

Collaborative clinical decision support is often constrained by governance and privacy rules that prevent pooling patient-level records across institutions. We present a hybrid privacy-preserving framework that combines Federated Learning (FL) and Split Learning (SL) to support decision-oriented healthcare modeling without raw-data sharing. The approach keeps feature-extraction trunks on clients while hosting prediction heads on a coordinating server, enabling shared representation learning and exposing an explicit collaboration boundary where privacy controls can be applied. Rather than assuming distributed training […]

Ver mais

Ver mais

Virtual screening aims to efficiently identify active ligands from massive chemical libraries for a given target pocket. Recent CLIP-style models such as DrugCLIP enable scalable virtual screening by embedding pockets and ligands into a shared space. However, our analyses indicate that such representations can be insensitive to fine-grained binding interactions and may rely on shortcut correlations in training data, limiting their ability to rank ligands by true binding compatibility. To address these issues, we propose BindCLIP, a unified […]

Ver mais

Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it remains unclear how to jointly learn reward functions from heterogeneous feedback types such as demonstrations, comparisons, ratings, and stops that provide qualitatively different signals. We address this challenge by formulating reward learning from multiple feedback types as Bayesian inference over a shared latent reward function, where each feedback type contributes information through an explicit likelihood. We introduce […]

Ver mais

A new study introduces the “self-evolution trilemma,” proving that AI systems cannot simultaneously remain autonomous, isolated from external input, and perfectly aligned with human values. Experiments in a closed AI community called Moltbook demonstrate how consensus bias, safety drift, collusion, and hidden behaviors emerge naturally under isolation. The paper argues that safety is not a patchable feature but a structural design choice — forcing builders of autonomous AI to decide which constraint they are willing to relax.

Ver mais

The shape of a planet’s orbit around a star is an ellipse. To put it another way, a plot of the position of a planet’s orbit over time forms an ellipse. What about the velocity? Is it’s plot also an ellipse? Surprisingly, a plot of the velocity forms a circle even if a plot of the position is an ellipse. If an object is in a circular orbit, it’s velocity vector traces out a circle too, with the […]

Ver mais

ChatGPT grew from zero to 100 million users in two months. Today it has over 800 million. That makes it one of the fastest-growing applications in history. And their database? PostgreSQL. The same 30-year-old relational database running your side project. Most engineering teams would have panicked at 10 million users and started a multi-year migration to Cassandra, DynamoDB, or some other NoSQL system. OpenAI did not. They scaled PostgreSQL itself. And the techniques they used are not exotic […]

Ver mais

TL;DR: Is our reality a simulation? Maybe. But if you look at the oldest documentation we have—specifically the Book of Job—it looks less like a “sim” and more like a chaotic production environment where the Lead Architect is running stress tests on the user base. Here is why your suffering might just be a feature, not a bug. I’ve been thinking a lot about Simulation Theory lately. Not because I watched The Matrix again, monitoring a chaotic situation, […]

Ver mais