The study investigates whether multimodal large language models (MLLMs) report bistable images, like the duck‑rabbit, in a manner similar to humans. Using the LLaVA family, researchers examined two dimensions: modulability (the influence of visual cues and linguistic priors) and exclusivity (whether responses commit to a single interpretation). Results show that both visual and linguistic manipulations shift reports in human‑consistent ways while maintaining predominantly exclusive responses, driven by competing image‑token representations and distinct bottom‑up and top‑down pathways.
By Ryota Takatsuki, Tomoki Doi, Amane Watahiki, Anil K. Seth, Hitomi Yanaka
The paper compares human group discussions with large language model (LLM) deliberation traces on various reasoning tasks, finding that both humans and LLMs exhibit an assembly bonus asymmetry where discussion benefits the average member more than the best initial member. While LLM groups mirror some outcome-level patterns of human deliberation, they differ in process-level behaviors: they tend to follow majorities, surface less unique information, and converge earlier. Interventions inspired by human group‑decision research yield modest outcome improvements but do not eliminate coordination bottlenecks.
By Ala N. Tak, Teruhisa Misu, Kumar Akash, Zhaobo K. Zheng, Kevin H. Joo, Jonathan Gratch
The paper introduces PR-IMM, a data‑driven state predictor‑based Interacting Multiple Model tracking method that integrates a transformer‑based prediction model with radar Doppler measurements. PR-IMM combines this prediction model with conventional CV, CA, and CT motion models, dynamically weighting their prior positions according to mode probabilities. Experiments demonstrate that PR-IMM reduces position‑estimation error by 57.3% compared to the standard IMM and by 16.5% compared to the prediction model alone, while also lowering ID switches by 25.3% and improving IDF1 by 9.6%.
By Chan-Bin Lim, Dong-Hee Paek, Seung-Hyun Kong
The paper introduces a three‑layer diagnostic framework that separates errors in Graph‑RAG systems into reasoning loss, Knowledge Graph defects, and Cypher generation errors. Experiments on a spatio‑temporal ecological KG from southeastern Tibet show that data integrity issues, especially structural defects, are the main cause of performance drops, reducing accuracy from 0.93 to 0.39. The study also identifies a Parametric Knowledge Masking Effect where LLMs hide retrieval path failures, masking over 70 % of query generation errors and raising the risk of false negatives in automated monitoring.
By Shuai Yan, Yuhang Wu, Xiaodong Huang, Ke Wang
The paper introduces a ROS-Agent architecture that enhances task reliability and execution efficiency for open‑source LLM‑powered robotic agents. It adds a MetaTool that forces the LLM to produce a structured pseudo‑code plan before any action, storing this plan in a scratchpad to separate planning from execution. Experiments on a custom mobile robot show up to ~24% improvement in complex task completion and contextual consistency compared to the baseline.
By Kazi Abrar Mahmud, Nilotpaul Kundu Dhurubo, Tamal Kirttonia, Sabbir Hossain Ujjal, Mohammad Ariful Haque
The paper introduces FedTAR, a task-aware federated fine‑tuning approach for Mixture‑of‑Experts (MoE) large language models. FedTAR links local client updates to task preferences using routing outputs and Singular Value Decomposition to extract low‑dimensional task coordinates and update directions. It then aggregates updates within and across task clusters, reconstructing the final update to preserve expert specialization and reduce interference, achieving state‑of‑the‑art performance on four benchmark tasks under non‑IID settings.
By Tingqi Wang, Hongyu Ke, Haoxin Wang, Rafal Angryk, Zhipeng Cai
ReCAST is a method for assigning credit to multiple rewards during diffusion model training by using a reward-by-timestep weight matrix that respects user-specified reward budgets while ensuring equal total weight per denoising step. It allocates weight based on each reward’s informativeness, measured by its Rényi discriminability gain at each step, allowing rewards to contribute more when they are most informative. Experiments on SD3.5‑Medium with two four‑reward settings show that ReCAST improves or matches training rewards, enhances held‑out judges, and is preferred by an independent LLM‑as‑a‑Judge, indicating generalizable benefits.
By Yihang Chen, Yuanhao Ban, Kuei-Chun Kao, Cho-Jui Hsieh
The paper introduces a paired benchmark to detect hindsight bias in clinical language models by comparing model responses to questions posed at a clinically relevant cutoff versus the full timeline. It uses 171 case reports (40 sepsis, 131 GLP‑1/diabetes) with both human‑annotated and LLM‑generated time‑series data, evaluating accuracy, hindsight trap rate, answer instability rate, and hindsight bias rate. Results show that exposing models to the full timeline consistently increases hindsight bias, while truncating the timeline mitigates bias without sacrificing accuracy.
By Misaki Matsuura, Sayantan Kumar, Ojas Kadam, Jeremy C. Weiss
The study compares XGBoost and RoBERTa‑LoRA for network intrusion detection across three evaluation axes: same‑dataset performance, cross‑dataset transfer, and adversarial evasion. Both models perform similarly on the same dataset, but XGBoost outperforms RoBERTa‑LoRA by 15 F1 points and 25 balanced accuracy points when transferred to a different network, while RoBERTa‑LoRA wins by about 17 F1 points under adversarial evasion. Feature‑leakage ablation shows that cross‑dataset transfer improvements are non‑monotonic and directional, suggesting leakage is spread across features rather than isolated.
"whyItMatters":"The findings demonstrate that a model’s superiority depends on the specific robustness axis evaluated, underscoring the need for multi‑axis, multi‑metric testing in network intrusion detection research."
By Muhammad Ebad Atif, Muhammad Haider Ali
This study develops a rolling day‑wise mortality prediction model for critically ill patients with acute kidney injury on continuous renal replacement therapy (CRRT) by incorporating minute‑level machine pressure waveforms alongside electronic health record (EHR) data. After cleaning the raw machine data—aligning it with therapy intervals, removing priming and downtime minutes, and denoising artifacts—the authors trained a transformer‑based stacked ensemble that fuses a sequence transformer with classical models using circuit‑instability features and clinical variables. In a multi‑center benchmark of 976 patients, the combined model achieved a one‑day mortality AUROC of 0.766, outperforming machine‑only (0.625) and EHR‑only (0.717) models, and SHAP analysis highlighted key pressure‑related features such as filter pressure, transmembrane pressure, and access‑to‑return difference.
whyItMatters":"By integrating previously discarded CRRT machine data, the study provides a continuous, real‑time risk signal that could enable earlier detection of patient deterioration and improve mortality prediction in a high‑risk population."
By Shehan Irteza Pranto, Joanna Yang, Joshua Lambert, Stuart L. Goldstein, Lili Chan, Girish N. Nadkarni, Tiago K. Colicchio, Javier A. Neyra, Jin Chen
The paper introduces a new evaluation method called "same-input rerun" to assess the consistency of clinical language‑model agents across repeated runs. By replaying 1,000 MedAgentBench tasks with identical inputs, the authors find that action‑level outputs—such as test orders, medication requests, and referrals—vary significantly, even when benchmark scores remain unchanged. The study demonstrates that current benchmarks, which typically evaluate only a single run per task, can miss substantial behavioral divergence.
By Rohith Reddy Bellibatlu, Manpreet Singh, Zhoutian Han, Wenbin Zhang
arXiv:2609.13718v1 Announce Type: cross
Abstract: AI-powered gameplay support agents hold promise for game-based learning, yet grounding generative models in structured game data remains an open chal...
By Jiahong Li, Sai Siddartha Maram, Atieh Kashani, Ulia Zaman, Zhiyu Lin, Cameron Marano, Roger Azevedo, Jichen Zhu, Magy Seif El-Nasr
arXiv:2609.13816v1 Announce Type: cross
Abstract: JavaScript powers approximately 98.8% of all websites, making vulnerabilities in its code a significant security risk, yet existing detection approac...
By Manit Kaushik, Ishir Bhardwaj, Pranav Gupta, Pankaj Jalote, Arun Balaji Buduru
arXiv:2609.13842v1 Announce Type: cross
Abstract: Recent advances in speech synthesis and voice conversion have made deepfake speech increasingly realistic, making generalization to unseen spoofing a...
By Minh-Xuan Phan, Khalid Zaman, Candy Olivia Mawalim, Masashi Unoki
arXiv:2609.13909v1 Announce Type: cross
Abstract: Continuous-latent Autoregressive Diffusion Transformer (AR-DiT) models have demonstrated immense potential in zero-shot speech generation. However, t...
By Ziyu Zhang, Tianlun Zuo, Hanzhao Li, Haoyu Zhang, Lei Xie
arXiv:2609.13942v1 Announce Type: cross
Abstract: The CRITICS project addresses science accessibility and literacy by converging advanced Machine Translation (MT) based on Large Language Models (LLMs...
By Rodrigo Agerri, Itziar Aldabe, Elena Cabrio, Mark Cieliebak, Jan Deriu, Mariana Flores, Jurgita Kapociute-Dzikiene, Dovile Kuiziniene, Arantza Rico, Aritz Ruiz-Gonzalez, Aitor Soroa, Mantas Vaskevicius, Serena Villata
arXiv:2609.13980v1 Announce Type: cross
Abstract: Arabic large-language-model (LLM) evaluation has matured around Modern Standard Arabic (MSA): aggregated leaderboards such as the Open Arabic LLM Lea...
By Nawar S. Alseelawi, Mustafa S. Aljumaily
arXiv:2609.14003v1 Announce Type: cross
Abstract: Personal AI agents built on large language models (LLMs) are increasingly given access to a user's private data and communications in order to provid...
By Minsun Shim, Ramisha Raida Karim, Ruthwik Jakkula, Kaiwen Zhou, Xin Liu, Xin Eric Wang, Zhou Li
arXiv:2609.14060v1 Announce Type: cross
Abstract: Quantization is one of the default deployment paths for open-weight LLM agents, but it is not behavior-preserving: an adversary can release a full-pr...
By Xiaoqun Liu, Qiben Yan
arXiv:2609.14100v1 Announce Type: cross
Abstract: Fashion Image Captioning (FIC) plays a vital role in enhancing user experience and product search in e-commerce platforms. Unlike natural scene image...
By Abhirama Subramanyam Penamakuri, Shreya Shukla, Anand Mishra