arXiv:2601.02496v1 Announce Type: new Abstract: We introduce APoW, a novel proof-of-work (PoW) construction inspired by Hashcash-style nonce searching, which enables the auditing of other miners’ work through accountable re-scanning of the nonce space. The proposed scheme allows a miner to probabilistically attest to having searched specified regions of the nonce space in earlier mining rounds, while concurrently earning rewards for performing productive work for a new block or pool share. This capability enables miners belonging to a mining […]

Ver mais

As AI agents begin executing trades, managing risk, and interacting with markets through natural language, exchanges are quietly undergoing one of their most significant architectural shifts since the invention of the order book itself. The platforms that win the next cycle may not be the ones with the deepest order books, they may be the ones that are the most programmable, the most interoperable, and the most agent-ready. Victor Wu is building that shift from the inside at […]

Ver mais

Hi, all! I’m the lead author on this ambitious (14-author!) perspective paper on deep learning theory. We’ve all been working seriously, and more or less exclusively, on deep learning for many years now. We believe that a theory is emerging, and we pull together five lines of evidence in recent research into a portrait of the nascent science. Hoping to galvanize better scientific research into how and why these wild, huge learning systems work at all. Explanatory tweet […]

Ver mais

arXiv:2601.05488v1 Announce Type: new Abstract: Maintaining consistency in long-term dialogues remains a fundamental challenge for LLMs, as standard retrieval mechanisms often fail to capture the temporal evolution of historical states. While memory-augmented frameworks offer a structured alternative, current systems rely on static prompting of closed-source models or suffer from ineffective training paradigms with sparse rewards. We introduce MemBuilder, a reinforcement learning framework that trains models to orchestrate multi-dimensional memory construction with attributed dense rewards. MemBuilder addresses two key […]

Ver mais

arXiv:2603.03322v1 Announce Type: new Abstract: Recent advancements in Large Language Model (LLM) agents have demonstrated remarkable potential in automatic knowledge discovery. However, rigorously evaluating an AI’s capacity for knowledge discovery remains a critical challenge. Existing benchmarks predominantly rely on static datasets, leading to inevitable data contamination where models have likely seen the evaluation knowledge during training. Furthermore, the rapid release cycles of modern LLMs render static benchmarks quickly outdated, failing to assess the ability to discover truly new […]

Ver mais

Introduction Disclaimer: This article is a cross post from Pytorch Medium Blog Post. One of the most exciting advancements, that has pushed the frontier of the Artificial Intelligence (AI) in recent years, is Deep Reinforcement Learning (DRL). DRL belongs to the family of machine learning algorithms. It assumes that intelligent machines can learn from their actions similar to the way humans learn from experience. Over the recent years we could witness some impressive real-world applications of DRL. The […]

Ver mais

arXiv:2601.03401v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly trained on massive, heterogeneous text corpora, raising serious concerns about the unauthorised use of proprietary or personal data during model training. In this work, we address the problem of data protection against unwanted model learning in a realistic black-box setting. We propose Disclaimer Injection, a novel data-level defence that renders text unlearnable to LLMs. Rather than relying on model-side controls or explicit data removal, our approach exploits […]

Ver mais

arXiv:2602.10160v1 Announce Type: new Abstract: End-to-end autonomous driving systems have achieved significant progress, yet their adversarial robustness remains largely underexplored. In this work, we conduct a closed-loop evaluation of state-of-the-art autonomous driving agents under black-box adversarial threat models in CARLA. Specifically, we consider three representative attack vectors on the visual perception pipeline: (i) a physics-based blur attack induced by acoustic waves, (ii) an electromagnetic interference attack that distorts captured images, and (iii) a digital attack that adds ghost […]

Ver mais

Bayesian active learning relies on the precise quantification of predictive uncertainty to explore unknown function landscapes. While Gaussian process surrogates are the standard for such tasks, an underappreciated fact is that their posterior variance depends on the observed outputs only through the hyperparameters, rendering exploration largely insensitive to the actual measurements. We propose to inject observation-dependent feedback by warping the input space with a learned, monotone reparameterization. This mechanism allows the design policy to expand or compress regions […]

Ver mais