arXiv:2601.21070v1 Announce Type: new Abstract: Large language models for code are advancing fast, yet our ability to evaluate them lags behind. Current benchmarks focus on narrow tasks and single metrics, which hide critical gaps in robustness, interpretability, fairness, efficiency, and real-world usability. They also suffer from inconsistent data engineering practices, limited software engineering context, and widespread contamination issues. To understand these problems and chart a path forward, we combined an in-depth survey of existing benchmarks with insights gathered […]

Ver mais

arXiv:2603.00565v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable performance but remain vulnerable to jailbreak attacks that can induce harmful content and undermine their secure deployment. Previous studies have shown that introducing additional inference steps, which disrupt security attention, can make MLLMs more susceptible to being misled into generating malicious content. However, these methods rely on single-image masking or isolated visual cues, which only modestly extend reasoning paths and thus achieve limited effectiveness, particularly […]

Ver mais

I’ve been on-and-off working on this project for a few months, just wanted to share it: https://www.2drl.com/ TLDR – It’s kinda like Unity but for reinforcement learning and much more lightweight. It lets you visually design Box2D (2D rigid body physics) gym environments using a drag-and-drop interface. It also has scripting support, so in principle you can define any environment with any custom behaviour. From your scene and script, it will automatically generate the full environment code, which […]

Ver mais

We often treat current LLMs as massive “reflex” engines (Model-Free policies) – they react to the context based on training habits, but they don’t really “plan” or verify their moves unless we force them with Chain-of-Thought. I’ve been looking at the architecture behind the new Logical Intelligence lab, which is pivoting to Energy-Based Models. From an RL perspective, this feels exactly like the shift from “habit-based” action to “planning-based” control. Instead of just guessing the next token, the […]

Ver mais

By Gigi Sohn, Chair, EFF Board of Directors  With the impending departure of longtime, renowned, and beloved Executive Director Cindy Cohn, EFF and leadership advisory firm Russell Reynolds Associates have developed a profile for her successor.  While Cindy is irreplaceable, we hope that everyone who knows and loves EFF will help us find our next leader.   First and foremost, we are looking for someone who’ll meet this pivotal moment in EFF’s history. As authoritarian surveillance creeps around […]

Ver mais

arXiv:2603.05483v1 Announce Type: cross Abstract: Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applications such as precision medicine and individualized policy-making. Yet, the survival analysis setting poses unique challenges for HTE estimation due to censoring, unobserved counterfactuals, and complex identification assumptions. Despite recent advances, from Causal Survival Forests to survival meta-learners and outcome imputation approaches, evaluation practices remain fragmented and inconsistent. We introduce SurvHTE-Bench, the first comprehensive benchmark for HTE estimation with censored […]

Ver mais

arXiv:2601.09037v1 Announce Type: new Abstract: Probabilistic computers built from p-bits offer a promising path for combinatorial optimization, but the dense connectivity required by real-world problems scales poorly in hardware. Here, we address this through graph sparsification with auxiliary copy variables and demonstrate a fully on-chip parallel tempering solver on an FPGA. Targeting MIMO detection, a dense, NP-hard problem central to wireless communications, we fit 15 temperature replicas of a 128-node sparsified system (1,920 p-bits) entirely on-chip and achieve […]

Ver mais

In this quiz, you’ll test your understanding of How to Use Note-Taking to Learn Python. By working through this quiz, you’ll revisit how to take structured handwritten notes, define unfamiliar terms, and summarize what you’ve learned with labeled code examples. [ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Ver mais

arXiv:2602.05395v1 Announce Type: new Abstract: A simple strategy for improving LLM accuracy, especially in math and reasoning problems, is to sample multiple responses and submit the answer most consistently reached. In this paper we leverage Bayesian prior information to save on sampling costs, stopping once sufficient consistency is reached. Although the exact posterior is computationally intractable, we further introduce an efficient “L-aggregated” stopping policy that tracks only the L-1 most frequent answer counts. Theoretically, we prove that L=3 […]

Ver mais

:::info Authors: Fernando Spade Oshani Seneviratne ::: Table of Contents Abstract Introduction Background The Sandbox The Data A: Transaction Graph B: Bow-tie Model C: The Sandbox Support D: The Sandbox Scandals E: Whales Methodology Results Related Work Conclusion Resource Contributions Acknowledgements and References ABSTRACT We explore the burgeoning field of GameFi through a detailed network analysis of The Sandbox, a prominent decentralized application (dApp) in this domain. Utilizing the bowtie model, we map out transaction data within The Sandbox, providing […]

Ver mais