The paper presents a data‑driven study of male domestic violence (MDV) in Bangladesh, using exploratory data analysis to uncover patterns such as verbal abuse prevalence and the influence of financial dependency. It evaluates 10 traditional ML models, 3 deep learning models, and 2 ensemble models, ultimately proposing a stacking ensemble with ANN and CatBoost base classifiers and Logistic Regression meta‑model that achieves 95% accuracy and 99.29% AUC. Explainable AI techniques (SHAP, LIME) and statistical validation confirm the model’s superior performance and highlight key features driving predictions.
By Md Abrar Jahin, Saleh Akram Naife, Fatema Tuj Johora Lima, M. F. Mridha, Md. Jakir Hossen
The paper investigates how Engram-style hashed memory can be transferred between different language model backbones. By freezing a memory table trained on a source model and attaching it to a target model with only a lightweight reader, the authors find that both the memory content and correct addressing are important, but the reader must be aligned to the target to make the memory useful. In question‑answering experiments, a dual‑layer, four‑branch reader nearly matches same‑model performance, and when the reader interface is directly compatible, the frozen memory alone provides substantial benefit, with optional reader adaptation offering further gains.
By Mingyuan Li, Guangsheng Yu, Xu Wang, Shaoxiong Ji
arXiv:2608. 17434v1 Announce Type: new Abstract: We study Gaussian regression over the explicit vector-valued Parhi--Nowak deep-RBV^2 architecture with depth L, width w, layer-sum variation budget A, and output bound B.
By Tao Jiang, Minbo Gao, Shaowei Cai
The paper introduces MCTH (Monte Carlo Tree Hallucination), an inference-only framework that performs all‑atom biomolecular sequence‑structure co‑design by treating pretrained folding and inverse‑folding models as black‑box operators. MCTH uses Monte Carlo Tree Search to allocate a fixed inference budget across competing design trajectories, incorporating model confidence, uncertainty, and cross‑expert consensus. Experiments across protein‑RNA, protein‑DNA, protein‑protein, and protein‑ligand design show that adaptive search outperforms simpler sampling strategies, and evaluations with AlphaFold3 and Chai‑1 demonstrate transferability beyond the search‑time oracle.
By Xuefeng Liu, Mingxuan Cao, Xiao Luo, Songhao Jiang, Tobin Sosnick, Jinbo Xu, Louis Maher, Rick Stevens
The paper examines how multi‑level fairness techniques—combining several bias‑mitigation steps—can reduce biases across patient demographics in health informatics. It reviews current literature, identifies gaps in implementation and reporting of health equity outcomes, and evaluates the role of reporting standards such as MINIMAR and TRIPOD in enhancing transparency. The authors conclude with recommendations to improve reporting transparency, broaden adoption of multi‑level fairness methods, and explicitly prioritize health equity in future research.
By Nick Souligne, Vignesh Subbian
The paper presents an optimal‑transport based generative model that learns the distributional differences between healthy and diseased patients, producing per‑patient counterfactuals and label‑free attribution heatmaps. On tabular breast cancer data the model achieves high malignancy scoring (AUROC ≈ 0.91) and its attributions correlate moderately with a supervised classifier, yet it does not surpass logistic regression. In chest X‑ray experiments the transport heatmaps capture population‑level signals but fail to localize real lesions, revealing a synthetic‑to‑real gap that challenges the reliability of label‑free explanations.
By Lalit Kumar
TokEval is a tokenizer evaluation suite that introduces metrics beyond traditional fertility and compression rate, capturing linguistically and structurally meaningful properties such as UTF‑8 character boundary integrity and digit place‑value alignment for mathematics. The authors validate these metrics by pretraining language models with varied tokenizers and measuring downstream performance on bits‑per‑byte and benchmarks covering linguistic understanding, mathematical reasoning, and code generation. Their results show that information‑theoretic metrics predict language modeling performance, while structure‑sensitive metrics correlate with task accuracy, suggesting TokEval can guide tokenizer selection more principledly.
By Clara Meister
The paper introduces a comprehensive privacy evaluation framework for genomic language models (GLMs) that quantifies memorization risks using perplexity-based detection, canary sequence extraction, and membership inference. By planting canary sequences at different repetition rates in synthetic and real datasets, the authors systematically assess how repetition, model capacity, and training dynamics affect memorization across various GLM architectures. The study demonstrates that GLMs do memorize training data to varying degrees and that no single attack method fully captures this risk, highlighting the necessity of multi-vector privacy auditing for genomic AI systems.
By Alexander Nemecek, Wenbiao Li, Xiaoqian Jiang, Jaideep Vaidya, Erman Ayday
The paper introduces COMIC, a reference‑aware safety gate designed for multimodal large language models (MLLMs). COMIC detects the operation requested by a user, identifies visual targets through OCR and open‑vocabulary proposals, and evaluates safety on explicit operation‑target pairs, using max‑risk aggregation and quality‑aware routing to decide whether to allow or block a request. Experiments on several open‑source MLLMs and jailbreak benchmarks show that COMIC improves robustness while maintaining benign utility and efficiency.
By Md Abdullahil Oaphy, Anhao Xiang, Zongxing Xie, Huayue Gu, Chenyu Wang, Honghui Xu
The paper introduces TiMi, a framework that enhances time series transformers with a Multimodal Mixture-of-Experts (MMoE) module to incorporate multimodal data, especially textual information, into forecasting. TiMi leverages large language models to generate future inferences that guide predictions, eliminating the need for explicit representation alignment. Experiments show TiMi achieves state‑of‑the‑art performance on sixteen real‑world multimodal forecasting benchmarks, outperforming advanced baselines while maintaining adaptability and interpretability.
By Jiafeng Lin, Yuxuan Wang, Huakun Luo, Jianmin Wang, Zhongyi Pei
The paper introduces QWM, a framework that integrates world models with standard Q‑learning to perform test‑time search over imagined trajectories. By training the policy and value function solely on real transitions, QWM avoids compounding model bias while still benefiting from predictive search. Experiments on the Robomimic and LIBERO manipulation benchmarks show that QWM outperforms strong prior state‑of‑the‑art methods in both sample efficiency and performance.
By Perry Dong, Yueru Jia, Chelsea Finn, Dorsa Sadigh
The paper introduces MemJack, a memory‑augmented multi‑agent framework that automatically generates jailbreak attacks on Vision‑Language Models (VLMs) using benign natural images as visual anchors. MemJack discovers visual anchors, camouflages them semantically, evaluates responses, repairs via reflection, and replans dynamically, forming a closed‑loop attack pipeline. The authors also create MemJack‑Bench, a dataset of over 113,000 interactive multimodal jailbreak trajectories, and show that MemJack achieves a 71.48% attack success rate against Qwen3‑VL‑Plus, reaching 90% under extended budgets, outperforming other baselines on natural‑image evaluation.
By Jianhao Chen, Haoyang Chen, Hanjie Zhao, Haozhe Liang, Zheng Wang, Tieyun Qian
This paper reports on a seven‑weekend AI storytelling program for Black girls aged 10‑12 that blends Afrofuturism and Black feminist thought with AI‑enabled counter‑storytelling. Participants brainstormed AI topics, crafted characters and plots, and presented collaborative stories, developing core AI literacies such as prompt engineering, bias critique, and data‑privacy awareness. The study found that the girls produced Afrofuturist narratives grounded in their identities and everyday experiences, demonstrating the program’s effectiveness in engaging them in computer science education.
By Chun Li, Lauren Brown, Hubert Asare, Shawna Patterson, Dennis Henderson, Ericka Roland, tara Nkrumah, Angela E. B. Stewart
The paper shows that fine‑tuning a large language model (LLM) with a debate framework—where a generator and a critic compete and a weaker LLM judge adjudicates—reduces reward hacking compared to standard reinforcement learning from AI feedback (RLAIF). In experiments on mathematics tasks, the debate approach keeps the judge’s performance stable, achieving a 45% higher peak validation accuracy than the RLAIF baseline and mitigating the rapid exploitation of judge errors. Additional findings indicate that weakening the judge speeds hacking unless countered by extra debate rounds, that debate can override misalignment prompts, and that word‑limit constraints on critiques help balance the game and prevent judge hacking.
whyItMatters":"The study demonstrates a practical method to curb reward hacking in RL‑based AI systems, addressing a key obstacle for safely scaling AI oversight."
By Zachary Kenton, Lili Janzer, Rory Greig, Tian Huey Teh, Kirill Tyshchuk, Jonah Brown-Cohen, Harri Edwards, Senthooran Rajamanoharan, Noah Y. Siegel, Natasha Jaques, Rohin Shah
The paper introduces TSN4PI, a unified framework for tracking the evolution of political ideologies on social media. It combines a PIDN module that uses large language models, style transfer, and unsupervised domain adaptation to detect ideologies and filter noise, with a PIPN module that employs temporal graph neural networks to predict future ideological shifts. The authors release two large-scale datasets and validate the approach on platforms such as X and Truth Social, offering empirical insights into political polarization and online ideology evolution.
By Yijie Xu, Chao Wang, Hui Xiong
The paper introduces GraphGAN, a Graph-based Generative Adversarial Network designed to detect Distributed Denial-of-Service (DDoS) attacks in next-generation networks. It transforms sequential traffic flows into k‑nearest neighbor graphs, uses a generator to create realistic minority samples, and employs Graph Convolutional Networks for both discrimination and final classification. Experiments on four benchmark datasets demonstrate that GraphGAN outperforms existing methods in accuracy, precision, and recall, especially when data are scarce.
By Mohammad Arif Hossain, Yeahia Sarker, Md Jafrin Hossain, Most. Humayra Khanom Rime, Nirwan Ansari
The paper introduces FlightLLM, a prior-guided semantic approach that uses large language models to explain flight safety events. It tackles challenges such as modal inconsistency, limited classification ability, and scarce domain data by combining feature engineering, semantic discretization, a CatBoost statistical expert, contrastive few-shot learning, and structured prompts. Evaluated on 704 real‑world A320 flights, FlightLLM achieves competitive classification and produces clear, aviation‑specific explanations for hard landing events.
By Lu Xu, Xu Li, Linjiang Zheng, Fan Li, Riquan Zhang, Jiaxing Shang
The paper introduces a conformal prediction framework designed for molecular property prediction under label shift. By weighting conformal scores with marginal label probability ratios, it generates statistically rigorous prediction intervals without retraining, enabling robust uncertainty quantification when property distributions change. This approach provides actionable confidence measures that improve the reliability of AI-driven predictions in drug discovery.
By Hyeonsu Lee, Juyeon Kim, Erkhembayar Jadamba, Seungjin Choi, Hyunjin Shin
LEGO-RL is a framework that connects native coding-agent harnesses with scalable policy‑gradient training without altering the harnesses’ internal flow. It achieves faithful optimization through in‑process LLM proxying, reliable execution via sandbox orchestration, and observable training with automated validation and a Live UI. Experiments show LEGO‑RL improves the Qwen3.5‑35B‑A3B model’s performance on three native harnesses while preserving high rollout‑training probability correlation.
By Yiming Du, Yuxin Jiang, Tao Yuan, Jianbo Dai, Shaowei Wang, Jierun Chen, Chaofan Tao, Xianzhi Yu, Lifeng Shang, Kam-Fai Wong, Xiaohui Li, Haoli Bai
The paper presents RuntimeGuard‑AI, a prototype that links each deterministic AI policy decision to its source code, writes a privacy‑minimizing record at a chosen synchronization point, and returns an Ed25519‑signed receipt indicating whether the write succeeded. After a crash, the system validates the integrity of records, manifests, shard placement, sequence continuity, and replay identity, while an independent attestation path chains committed records into signed Merkle epochs for auditor verification. Performance results on an Apple M4 Pro show high throughput (up to 27,193 requests/s) with low latency when buffering, but throughput drops and latency rises when per‑record data and full synchronization are used, illustrating a clear durability‑latency trade‑off.
By Neeraj Kumar Singh Beshane