arXiv:2411.03387v3 Announce Type: replace-cross Abstract: Estimating causal quantities from observational data is crucial for understanding the safety and effectiveness of medical treatments. However, to make reliable inferences, medical practitioners require not only estimating averaged causal quantities, such as the conditional average treatment effect, but also understanding the randomness of the treatment effect as a random variable. This randomness is referred to as aleatoric uncertainty and is necessary for understanding the probability of benefit from treatment or quantiles of […]

Ver mais

Causal discovery with latent variables is a fundamental task. Yet most existing methods rely on strong structural assumptions, such as enforcing specific indicator patterns for latents or restricting how they can interact with others. We argue that a core obstacle to a general, structural-assumption-free approach is the lack of an equivalence characterization: without knowing what can be identified, one generally cannot design methods for how to identify it. In this work, we aim to close this gap for […]

Ver mais

Large Language Models (LLMs) are the world’s best mimics, but when it comes to the cold, hard logic of updating beliefs based on new evidence, they are surprisingly stubborn. A team of researchers from Google argue that the current crop of AI agents falls far short of ‘probabilistic reasoning’—the ability to maintain and update a ‘world model’ as new information trickles in. The solution? Stop trying to give them the right answers and start teaching them how to […]

Ver mais

Reinforcement Learning from Human Feedback (RLHF) is a widely used approach to align large-scale AI systems with human values. However, RLHF typically assumes a single, universal reward, which overlooks diverse preferences and limits personalization. Variational Preference Learning (VPL) seeks to address this by introducing user-specific latent variables. Despite its promise, we found that VPL suffers from posterior collapse. While this phenomenon is well known in VAEs, it has not previously been identified in preference learning frameworks. Under sparse […]

Ver mais

For a while I’ve been looking for a good format to practice implementing ML algorithms. LeetCode feels too disconnected from real work, but in actual projects you just use existing libraries. What worked for me was breaking real algorithms into progressive steps and implementing them piece by piece. I’ve been using this approach for myself, and recently decided to clean up some of it with tests and hints in case others find it useful. Currently covers: attention, BPE […]

Ver mais

The prediction of critical heat flux (CHF) using machine learning (ML) approaches has become a highly active research activity in recent years, the goal of which is to build models more accurate than current conventional approaches such as empirical correlations or lookup tables (LUTs). Previous work developed and deployed tube-based pure and hybrid ML models in the CTF subchannel code, however, full-scale reactor core simulations require the use of rod bundle geometries. Unlike isolated subchannels, rod bundles experience […]

Ver mais

Unprocessed emotions act like background apps hogging your brain’s limited working memory, slowing you down even in quiet moments. This fresh lens recasts cognitive overload as emotional RAM drain—and introduces introspection as the ultimate cleaner. Some cognitive models suggest that unprocessed emotions can waste 20–30% of our thinking bandwidth. It’s like trying to ship code while a background process silently occupies one-third of your CPU. This “emotional residue”—the stuff we suppress to get through the day—doesn’t go away; […]

Ver mais

arXiv:2603.12414v1 Announce Type: new Abstract: State Space Models (SSMs) such as Mamba achieve linear-time sequence processing through input-dependent recurrence, but this mechanism introduces a critical safety vulnerability. We show that the spectral radius rho(A-bar) of the discretized transition operator governs effective memory horizon: when an adversary drives rho toward zero through gradient-based Hidden State Poisoning, memory collapses from millions of tokens to mere dozens, silently destroying reasoning capacity without triggering output-level alarms. We prove an Evasion Existence Theorem […]

Ver mais