arXiv:2602.21478v1 Announce Type: new Abstract: We study inference on scalar-valued pathwise differentiable targets after adaptive data collection, such as a bandit algorithm. We introduce a novel target-specific condition, directional stability, which is strictly weaker than previously imposed target-agnostic stability conditions. Under directional stability, we show that estimators that would have been efficient under i.i.d. data remain asymptotically normal and semiparametrically efficient when computed from adaptively collected trajectories. The canonical gradient has a martingale form, and directional stability guarantees […]

Ver mais

Picture this: You just landed in the US. You’ve got a job, a signed lease, and your phone. But you have zero credit history. No SSN yet. And absolutely nobody is walking you through this financial maze. A coworker swears by this finance app, so you download it. You try linking your bank. It fails. The error message is in English. There’s no clear retry path. You close the app. You’re done. Probably for good. That isn’t just […]

Ver mais

arXiv:2603.22030v1 Announce Type: cross Abstract: Bayesian neural network (BNN) posteriors are often considered impractical for inference, as symmetries fragment them, non-identifiabilities inflate dimensionality, and weight-space priors are seen as meaningless. In this work, we study how overparametrization and priors together reshape BNN posteriors and derive implications allowing us to better understand their interplay. We show that redundancy introduces three key phenomena that fundamentally reshape the posterior geometry: balancedness, weight reallocation on equal-probability manifolds, and prior conformity. We validate […]

Ver mais

The stark success of OpenAI’s GPT4 model surprised me shifting my view from “really good autocomplete” (roughly inline with intuitions here) to a dialog agent exhibiting a significant scope of reasoning and intelligence. Some of the MSR folks did a fairly thorough study of capabilities which seems like a good reference. I think of GPT4 as an artificial savant: super-John capable in some language-centric tasks like style and summarization with impressive yet more limited abilities in other domains […]

Ver mais

arXiv:2604.06268v1 Announce Type: new Abstract: RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track reasoning stability. However, entropy only measures diversity within the same input, and cannot tell whether reasoning actually responds to different inputs. In RAGEN-2, we find that even with stable entropy, models can rely on fixed templates that look diverse but are input-agnostic. We call this template collapse, a failure mode invisible […]

Ver mais

arXiv:2604.06178v1 Announce Type: new Abstract: The use of generative AI (genAI) tools as informal tutors is becoming increasingly prevalent among secondary school students in mathematics learning. In many schools, individualized instructional support is limited, and one-on-one human tutoring remains costly in most learning contexts. GenAI has the potential to provide timely, on-demand help to students when teachers or tutors are not available. However, there are still few studies that examine students’ preferences for AI tutor support that enhances […]

Ver mais