I have to confess: recently I did not get to do a lot of horsing around with new, hot neural network architectures. I do not have as much time to fully reimplement papers as I used to as a university student. But luckily, I found out that if one has access to very good code, one can gain deep knowledge of an algorithm solely by running the code through my debugger, analyzing what is going on step-by-step, and […]
arXiv:2604.05114v1 Announce Type: new Abstract: We study a pipeline that curates reasoning data from initial structured data for improving long-context reasoning in large language models (LLMs). Our approach, $pi^2$, constructs high-quality reasoning data through rigorous QA curation: 1) extracting and expanding tables from Wikipedia, 2) from the collected tables and relevant context, generating realistic and multi-hop analytical reasoning questions whose answers are automatically determined and verified through dual-path code execution, and 3) back-translating step-by-step structured reasoning traces as […]
arXiv:2602.02566v1 Announce Type: new Abstract: There are ongoing discussions about predictive policing systems, such as those deployed in Los Angeles, California and Baltimore, Maryland, being unfair, for example, by exhibiting racial bias. Studies found that unfairness may be due to feedback loops and being trained on historically biased recorded data. However, comparative studies on predictive policing systems are few and are not sufficiently comprehensive. In this work, we perform a comprehensive comparative simulation study on the fairness and […]
Welcome to Edition 8.24 of the Rocket Report! We’re back from a restorative holiday, and there’s a great deal Eric and I look forward to covering in 2026. You can get a taste of what we’re expecting this year in this feature. Other storylines are also worth watching this year that didn’t make the Top 20. Will SpaceX’s Starship begin launching Starlink satellites? Will United Launch Alliance finally get its Vulcan rocket flying at a higher cadence? Will […]
I assumed the flicker was SAM3 being temperamental. I watched masks snap on and off across consecutive frames, and my first instinct was to reach for the usual bag of excuses: “it’s a hard scene,” “video is noisy,” “the model needs more context.” What actually broke was simpler and more embarrassing: I was letting the model’s outputs live in the wrong coordinate system, and then I tried to stabilize a tracker on top of that. Once I fixed […]
We study Constrained Online Convex Optimization (COCO), where a learner chooses actions iteratively, observes both unanticipated convex loss and convex constraint, and accumulates loss while incurring penalties for constraint violations. We introduce CLASP (Convex Losses And Squared Penalties), an algorithm that minimizes cumulative loss together with squared constraint violations. Our analysis departs from prior work by fully leveraging the firm non-expansiveness of convex projectors, a proof strategy not previously applied in this setting. For convex losses, CLASP achieves […]
While much of the current research in deep learning-based vulnerability detection relies on disassembled binaries, this paper explores the feasibility of extracting features directly from raw x86-64 machine code. Although assembly language is more interpretable for humans, it requires more complex models to capture token-level context. In contrast, machine code may enable more efficient, lightweight models and preserve all information that might be lost in disassembly. This paper approaches the task of vulnerability detection through an exploratory study […]
arXiv:2602.15872v1 Announce Type: new Abstract: Designing dense reward functions is pivotal for efficient robotic Reinforcement Learning (RL). However, most dense rewards rely on manual engineering, which fundamentally limits the scalability and automation of reinforcement learning. While Vision-Language Models (VLMs) offer a promising path to reward design, naive VLM rewards often misalign with task progress, struggle with spatial grounding, and show limited understanding of task semantics. To address these issues, we propose MARVL-Multi-stAge guidance for Robotic manipulation via Vision-Language […]
OpenAI and PwC are partnering to help enterprises use AI agents to automate finance workflows, improve forecasting, strengthen controls, and modernize the CFO function.
arXiv:2603.28802v1 Announce Type: new Abstract: Systematic reviews provide comprehensive syntheses of research fields. As a result, systematic reviews often emphasize synthesizing across the large bodies of literature rather than just describing the studies from which the conclusions were drawn. This risks an incomplete description of the sample – encouraging overgeneralization of the findings, obscuring connections between existing work, or overshadowing gaps in the literature. To address this challenge, we introduce interactive evidence maps; an accessible visualization tool that […]