Academic Digest: Latest Advances in AAAI, ILRT, IML, and IEEE
Generated: 2026-09-19 19:04
Generated: 2026-09-19 19:04
Monitored Venues: AAAI, ILRT, IML, IEEE
Focus: Continuous Improvement, Verification & Validation, Machine Learning Security, Trace Analysis
Overview: 8 Recent Publications Identified
AAAI (Association for the Advancement of Artificial Intelligence)
1. Which LLM is Best for Translating Natural Language Goals to PDDL
- Authors: Tomas Balyo, Lukas Chrpa, G. Michael Youngblood
- Date/Source: 2026-09-16 ·
arXiv - Abstract / Key Extract:
Bridging the gap between human intent and machine execution remains a challenge in automated planning, where expressing goals in formal languages like PDDL restricts accessibility to non-experts. This paper empirically evaluates whether current Large Language Models (LLMs) can reliably translate nat…
2. Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment
- Authors: Kosuke Kitahara, Nobuhiro Yamaguchi
- Date/Source: 2026-09-16 ·
arXiv - Abstract / Key Extract:
Open-weight large language models are rapidly entering hiring pipelines, yet their discriminatory failure modes – and the regulatory exposure these create under the EU AI Act high-risk classification (Annex III) and U.S. EEOC adverse-impact analysis – remain poorly understood. We present the first…
ILRT (Inductive Logic & Reasoning / Interactive Learning & RL)
1. ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models
- Authors: Shijie Lian, Bin Yu, Zhaolong Shen, Xiaopeng Lin, Yichao Du, Zhirui Zhang, Laurence T. Yang, Kai Chen
- Date/Source: 2026-09-16 ·
arXiv - Abstract / Key Extract:
Action tokenizers play a central role in autoregressive vision-language-action (VLA) models, determining both the targets for policy training and the executable commands recovered from predicted tokens. Their fidelity is commonly evaluated using pointwise reconstruction metrics such as mean squared …
2. Hyperbolic Graph Representation Learning for Differential Diagnosis on Biomedical Knowledge Graphs
- Authors: Pietro Miotto, Lucia Mellini, Tommaso Marzi, Cesare Alippi, Elena Casiraghi, Alberto Paccanaro, Giorgio Valentini, Mauricio Soto-Gomez
- Date/Source: 2026-09-16 ·
arXiv - Abstract / Key Extract:
Biomedical knowledge graphs combine ontology-derived hierarchies with transversal associations among heterogeneous entities such as phenotypes, diseases, genes, proteins, and patients. This hybrid structure raises the question of whether hyperbolic embeddings, which naturally capture tree-like organ…
IML (Interpretable Machine Learning / ICML)
1. Null importance: Disentangling relevance for interpretable machine learning
- Authors: Garvesh Raskutti, Kris Sankaran, Jiaxin Ye
- Date/Source: 2026-09-16 ·
arXiv - Abstract / Key Extract:
Feature importance is central to interpretable machine learning, but the term “importance” encompasses several fundamentally different notions of relevance. We develop a unified perspective based on null importance: a population-level characterization of when a feature is irrelevant under a specifie…
2. Machine-Learning Assessment of the Predictive Value of Inflammatory Biomarkers for Cognitive Impairment in an Older Hispanic Adult Cohort
- Authors: Antony Garcia, Gabrielle Britton, Alcibiades Villarreal, Diana Oviedo, Giselle Rangel, Xinming Huang
- Date/Source: 2026-09-16 ·
arXiv - Abstract / Key Extract:
Small clinical tabular datasets require interpretable machine learning because deep learning is often impractical and ensemble models can be difficult to inspect. A key pitfall is that statistical significance does not necessarily imply predictive utility. Using data from the Panama Aging Research I…
IEEE (Transactions on SE, TPAMI, S&P, ICST)
1. Multi-center Medical Data Mining with FL-Net - A One-stop Shop for Federated Learning
- Authors: Simon Süwer, Julian Klemm, Elisa Acitelli, Mathieu Almeida, Lucia Altucci, Zsolt Bagyura, Michelangela Barbieri, Zsolt-Zoltán Bedő, Rosaria Benedetti, Béla Bihari, Csongor Csalóka, Lucia Dicunta, Stanislav Ehrlich, Bjoern M. Eskofier, Sándor-József Fejér, Georg Fröwis, Walter Hötzendorfer, Alexandra Kautzky-Willer, Jens Johann Georg Lohmann, Marianna Maranghi, Lorenzo Marconi, Rudolf Mayer, Wouter Leonard Megchelenbrink, Monika Moga, Adham Mottalib, Sanjeev Mehta, Madeleine Müller, Thomas Nyström, Balázs-Attila Orbán, Paul O’Toole, Giuseppe Paolisso, Paolo Parini, Matteo Pedrelli, Enrico Petrillo, Philipp Poindl, Niklas Probul, Anastasia Pustozerova, Tanja Šarčević, Lukas Weilguny, Jan Baumbach, Andreas Maier
- Date/Source: 2026-09-17 ·
arXiv - Abstract / Key Extract:
Federated learning enables collaborative training without sharing patient-level data, but most studies remain simulations. Based on five requirements derived from the literature, we analyzed 14 FL frameworks and found that none fully satisfied these requirements. We present FL-Net, a novel federated…
2. Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape
- Authors: Sarah Radway, Andrew Cheng, Vijay Janapa Reddi, James Mickens
- Date/Source: 2026-09-17 ·
arXiv - Abstract / Key Extract:
Frontier AI models are rapidly gaining the ability to exploit vulnerabilities in complex pieces of software. The risk is not theoretical, as evidenced by recent sandbox escapes performed by frontier models at OpenAI and Anthropic. Discussions of how to sandbox inference stack components often focus …
Actionable Insights for Active Projects
- Trace Language & Verification Alignment: Review recent AAAI/IEEE formal verification preprints to check for new automaton reduction techniques or Aho-Corasick state-minimization algorithms.
- Interpretable ML & Guardrails: Assess whether newly published surrogate explainability models can be plugged into the evaluation harness as supplementary runtime verifiers.
- Continuous Benchmarking: Cross-reference state-of-the-art metrics against active Kaggle/benchmark notebooks to identify potential architectural regressions.