Automated feature engineering (AFE) enables AI systems to autonomously construct high-utility representations from raw tabular data. However, existing AFE methods rely on statistical heuristics, yielding brittle features that fail under distribution shift. We introduce CAFE, a framework that reformulates AFE as a causally-guided sequential decision process, bridging causal discovery with reinforcement learning-driven feature construction. Phase I learns a sparse directed acyclic graph over features and the target to obtain soft causal priors, grouping features as direct, indirect, or […]

Ver mais

I’ve been building a system to create physics-based humanoid characters in Unity that can learn through reinforcement learning — and you can physically interact with them in mixed reality on Quest. Today I’m open-sourcing the three packages that make it up. What it does: synth-core — Take any Daz Genesis 8 or Mixamo character, run it through an editor wizard (or one-click right-click menu), and get a fully physics-simulated humanoid with MuJoCo rigid-body dynamics, mesh-based collision geometry, configurable […]

Ver mais

arXiv:2503.19874v2 Announce Type: replace-cross Abstract: We consider the problem of selecting a subset of points from a dataset of $n$ unlabeled examples for labeling, with the goal of training a multiclass classifier. To address this, we build upon the regret minimization framework introduced by Allen-Zhu et al. in “Near-optimal design of experiments via regret minimization” (ICML, 2017). We propose an alternative regularization scheme within this framework, which leads to a new sample selection objective along with a provable […]

Ver mais

Published on January 6, 2026 4:31 PM GMT On Thinkish, Neuralese, and the End of Readable Reasoning In September 2025, researchers released the internal monologue of OpenAI’s GPT-o3 as it decided to lie about scientific data. Here’s what it was thinking: “We can glean disclaim disclaim synergy customizing illusions”? Pardon? This reads like someone had a stroke during a meeting they didn’t want to be in, but their hand kept taking notes. The transcript comes from a recent […]

Ver mais

arXiv:2602.13212v1 Announce Type: new Abstract: We study language-in-the-loop control for multi-drone systems that execute evolving, high-level missions while retaining formal robustness guarantees at the physical layer. We propose a three-layer architecture in which (i) a human operator issues natural-language instructions, (ii) an LLM-based supervisor periodically interprets, verifies, and corrects the commanded task in the context of the latest state and target estimates, and (iii) a distributed inner-loop controller tracks the resulting reference using only local relative information. We […]

Ver mais

arXiv:2602.15836v1 Announce Type: new Abstract: Large Action Models (LAMs) have shown immense potential in autonomous navigation by bridging high-level reasoning with low-level control. However, deploying these multi-billion parameter models on edge devices remains a significant challenge due to memory constraints and latency requirements. In this paper, we propose EdgeNav-QE, a novel framework that integrates Quantized Low-Rank Adaptation (QLoRA) with a dynamic early-exit (DEE) mechanism to optimize LAMs for real-time edge navigation. By quantizing the backbone to 4-bit precision […]

Ver mais

arXiv:2601.00987v1 Announce Type: cross Abstract: Transfer learning aims to improve performance on a target task by leveraging information from related source tasks. We propose a nonparametric regression transfer learning framework that explicitly models heterogeneity in the source-target relationship. Our approach relies on a local transfer assumption: the covariate space is partitioned into finitely many cells such that, within each cell, the target regression function can be expressed as a low-complexity transformation of the source regression function. This localized […]

Ver mais

arXiv:2601.12283v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) achieve state-of-the-art performance in text-to-image synthesis but remain computationally expensive due to the iterative nature of denoising and the quadratic cost of global attention. In this work, we observe that denoising dynamics are spatially non-uniform-background regions converge rapidly while edges and textured areas evolve much more actively. Building on this insight, we propose SDiT, a Semantic Region-Adaptive Diffusion Transformer that allocates computation according to regional complexity. SDiT introduces a training-free […]

Ver mais

Elon Musk has merged SpaceX and xAI, creating what might be the blueprint for a new Silicon Valley power structure. With his $800 billion net worth already rivaling historic conglomerate GE’s peak market cap, and Musk being vocal about his view that “tech victory is decided by velocity of innovation,” the question isn’t whether a personal conglomerate can be built, but rather how far Musk himself is […]

Ver mais

arXiv:2602.05172v1 Announce Type: new Abstract: We derive finite-particle rates for the regularized Stein variational gradient descent (R-SVGD) algorithm introduced by He et al. (2024) that corrects the constant-order bias of the SVGD by applying a resolvent-type preconditioner to the kernelized Wasserstein gradient. For the resulting interacting $N$-particle system, we establish explicit non-asymptotic bounds for time-averaged (annealed) empirical measures, illustrating convergence in the emph{true} (non-kernelized) Fisher information and, under a $mathrm{W}_1mathrm{I}$ condition on the target, corresponding $mathrm{W}_1$ convergence for […]

Ver mais