arXiv:2601.10820v1 Announce Type: new Abstract: Recent advances in code generation models have unlocked unprecedented opportunities for automating feature engineering, yet their adoption in real-world ML teams remains constrained by critical challenges: (i) the scarcity of datasets capturing the iterative and complex coding processes of production-level feature engineering, (ii) limited integration and personalization of widely used coding agents, such as CoPilot and Devin, with a team’s unique tools, codebases, workflows, and practices, and (iii) suboptimal human-AI collaboration due to […]

Ver mais

arXiv:2601.15331v1 Announce Type: new Abstract: The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common misuse, they remain vulnerable to automated jailbreaking methods such as GCG, PEZ, and GBDA, which generate adversarial suffixes via training and gradient-based search. Although effective, these methods particularly GCG are computationally expensive, limiting their practicality for organisations with constrained resources. This […]

Ver mais

I have implemented dreamer but cannot get it to solve the walker2d environment. I copied and pasted much of the code from public repositories, but wrote the loss computation part myself. I’ve spent several days trying to debug the code and would really appreciate your help.. I’ve put a github link to the code. I’m suspecting the indexing might be wrong in the computation of lambda returns, but there could many other mistakes. I usually don’t post anything […]

Ver mais

arXiv:2601.14287v1 Announce Type: new Abstract: External memory systems are pivotal for enabling Large Language Model (LLM) agents to maintain persistent knowledge and perform long-horizon decision-making. Existing paradigms typically follow a two-stage process: computationally expensive memory construction (e.g., structuring data into graphs) followed by naive retrieval-augmented generation. However, our empirical analysis reveals two fundamental limitations: complex construction incurs high costs with marginal performance gains, and simple context concatenation fails to bridge the gap between retrieval recall and reasoning accuracy. […]

Ver mais

arXiv:2601.20015v1 Announce Type: new Abstract: DBTuneSuite is a suite of experiments on four widely deployed free database systems to test their performance under various query/upsert loads and under various tuning options. The suite provides: (i) scripts to generate data and to install and run tests, making it expandable to other tests and systems; (ii) suggestions of which systems work best for which query types; and (iii) quantitative evidence that tuning options widely used in practice can behave very […]

Ver mais

arXiv:2601.20868v1 Announce Type: new Abstract: Large Language Models (LLMs) have advanced the field of Combinatorial Optimization through automated heuristic generation. Instead of relying on manual design, this LLM-Driven Heuristic Design (LHD) process leverages LLMs to iteratively generate and refine solvers to achieve high performance. However, existing LHD frameworks face two critical limitations: (1) Endpoint-only evaluation, which ranks solvers solely by final quality, ignoring the convergence process and runtime efficiency; (2) High adaptation costs, where distribution shifts necessitate re-adaptation […]

Ver mais

arXiv:2601.21018v1 Announce Type: new Abstract: We consider a (sub)diffusion equation with a nonlinearity of the form $pf(u)-qu$, where $p$ and $q$ are space dependent functions. Prominent examples are the Fisher-KPP, the Frank-Kamenetskii-Zeldovich and the Allen-Cahn equations. We devise a fixed point scheme for reconstructing the spatially varying coefficients from interior observations a) at final time under two different excitations b) at two different time instances under a single excitation. Convergence of the scheme as well as local uniqueness […]

Ver mais

arXiv:2410.18164v3 Announce Type: replace-cross Abstract: Tabular data is one of the most ubiquitous sources of information worldwide, spanning a wide variety of domains. This inherent heterogeneity has slowed the development of Tabular Foundation Models (TFMs) capable of fast generalization to unseen datasets. In-Context Learning (ICL) has recently emerged as a promising solution for TFMs, enabling dynamic adaptation to new tasks without additional tuning. While many studies have attempted to re-purpose large language models for tabular ICL, they have […]

Ver mais

arXiv:2601.16363v1 Announce Type: new Abstract: The software engineering research community is productive, yet it faces a constellation of challenges: swamped review processes, metric-driven incentives, distorted publication practices, and increasing pressures from AI, scale, and outright scams. These issues are often treated in isolation, yet they arise from deep structural dynamics within the research ecosystem itself and distract us from the larger role of research in society. Meaningful progress requires a holistic system-level view. We sketch such a framework […]

Ver mais