NeST is a framework that adapts large language models (LLMs) for continuous time‑series forecasting by creating neighborhood‑aware text prototypes and aligning them with temporal representations through a nearest‑neighbor contrastive objective. It retrieves the most relevant prototypes and uses them to conditionally modulate time‑series features, enabling more effective integration of textual and temporal information. Experiments show that NeST outperforms state‑of‑the‑art methods on eight benchmarks, reduces MSE by 1.2% for long‑term forecasting, improves zero‑shot forecasting by 4.9%, and boosts R² by 3.3% on a real‑world photovoltaic power forecasting task.
By Jayanie Bogahawatte, Sachith Seneviratne, Maneesha Perera, Saman Halgamuge
arXiv:2608.22329v1 Announce Type: cross
Abstract: Emotion-aware artistic image generation requires a model to satisfy semantic content, artistic style, and target emotion simultaneously. The key chal...
By Qianqian Tang, Jiayi Gao, Ting Lei, Yang Liu
arXiv:2608.22490v1 Announce Type: new
Abstract: Safety alignment helps models adhere to human values, but it often reduces response utility. We ask a critical but understudied question: Does safety a...
By Chanwoong Yoon, Jungsoo Park, Alan Ritter
The paper introduces Scaling Electronic Health Record Foundation Models for Population Health Management, a large‑scale model trained on billions of medical events from over 5 million patients in Taiwan and the United States. By aligning ICD codes across different health systems, the model achieves strong scaling and generalization across 11 chronic disease prediction tasks, outperforming tree‑based, general, and biomedical language models with high sensitivity at 99% specificity. It also demonstrates superior few‑shot performance on the EHRShot benchmark and shows that cross‑system alignment provides a stronger pretraining signal than single‑site duplication in data‑limited scenarios.
By Liwen Sun, Hao-Ren Yao, Ophir Frieder, Xiang Qian, Chenyan Xiong
The paper evaluates using large language model (LLM) juries to review code generated from natural language queries, focusing on MySQL text-to-SQL tasks. It benchmarks 15 open models, selects the top six, and constructs unanimous committees of varying sizes to accept a query only when all members agree. The study finds that single-model judges are inconsistent, while small unanimous committees of strong models can reduce false accepts without discarding many correct queries, and that committee composition significantly influences performance.
By Muhammad Aziz Ullah, Abdul Serwadda
arXiv:2603.02229v2 Announce Type: replace-cross
Abstract: Safety post-training has been studied extensively in single-step "chat" settings where safety typically refers to refusing harmful requests....
By Benjamin Plaut
arXiv:2605.17610v2 Announce Type: replace-cross
Abstract: The rapid growth of online video platforms and AI-generated content has made reliable video guardrails a key challenge for safety and real-wo...
By Shahriar Kabir Nahin, Hadi Askari, Muhao Chen, Anshuman Chhabra
arXiv:2607.02486v2 Announce Type: replace
Abstract: Descriptor-free visual localization eliminates high-dimensional descriptor storage, preserves scene privacy, and simplifies map maintenance, yet it...
By Yejun Zhang, Xinjue Wang, Zihan Wang, Esa Rahtu, Juho Kannala
The paper surveys how Large Foundation Models (LFMs) can be integrated into Human‑AI Collaboration (HAI) to enhance problem‑solving and decision‑making. It outlines four key areas—human‑guided model development, collaborative design principles, ethical and governance frameworks, and high‑stakes applications—while emphasizing that effective HAI systems arise from careful, human‑centered design rather than merely stronger models. The survey also identifies open challenges related to safety, fairness, and control, aiming to guide future research toward reliable, trustworthy, and beneficial LFM‑based partnerships.
By Vanshika Vats, Marzia Binta Nizam, Minghao Liu, Ziyuan Wang, Richard Ho, Mohnish Sai Prasad, Vincent Titterton, Sai Venkat Malreddy, Riya Aggarwal, Yanwen Xu, Lei Ding, Jay Mehta, Nathan Grinnell, Li Liu, Sijia Zhong, Devanathan Nallur Gandamani, Xinyi Tang, Rohan Ghosalkar, Celeste Shen, Rachel Shen, Nafisa Hussain, Kesav Ravichandran, James Davis
arXiv:2608.16466v2 Announce Type: replace-cross
Abstract: Bayesian optimal experimental design (BOED) aims to collect informative data by optimizing an expected utility reflecting the goals of an exp...
By David Chen, Michael Evans, Xinwei Li, Prateek Bansal, David J. Nott
arXiv:2608.10503v2 Announce Type: replace
Abstract: As Large Language Models (LLMs) are increasingly deployed as autonomous agents, accurately evaluating their latent values and biases is critical. T...
By Davood Wadi, Mohsen Ghodrat, Matthew Philp
The paper presents a robust multi‑agent reinforcement learning framework for small unmanned aircraft systems (sUAS) to maintain separation assurance when GPS data is degraded or spoofed. By modeling state observation corruption as a zero‑sum game, the authors derive a closed‑form adversarial perturbation that eliminates iterative inner optimization and can be evaluated in linear time. Integrating this perturbation into a policy‑gradient MARL algorithm yields a counter‑policy that achieves near‑zero collision rates in high‑density simulations even with up to 35% observation corruption, outperforming non‑adversarial baselines.
By Alex Zongo, Filippos Fotiadis, Ufuk Topcu, Peng Wei
arXiv:2608.22118v1 Announce Type: new
Abstract: LLM responses are based on the internet (via training or RAG), and AI is now used to generate a significant amount of content online (Paredes et al., 2...
By Gregory Druck, Ethan Smith
Omni‑SafetyBench is a new benchmark designed to evaluate the safety of Omni‑Modal Large Language Models (OLLMs) that process visual, auditory, and textual data. It contains 23,328 test instances across 24 modality variations derived from 972 seed samples, and introduces metrics such as Safety‑score (based on Conditional Attack Success Rate and Conditional Refusal Rate) and Cross‑Modal Safety Consistency score. Evaluation of 11 state‑of‑the‑art OLLMs shows severe vulnerabilities, with only three models achieving a Safety‑score above 0.6 and safety degrading sharply for audio‑visual inputs, underscoring the need for improved safety alignment methods.
By Leyi Pan, Zheyu Fu, Yunpeng Zhai, Shuchang Tao, Sheng Guan, Shiyu Huang, Lingzhe Zhang, Zhaoyang Liu, Bolin Ding, Felix Henry, Aiwei Liu, Lijie Wen
The paper introduces Knowledge-Weighted Fine‑Tuning, a method that estimates an instance‑level knowledge score through multi‑sampled inference and uses it to scale the learning signal. This approach encourages large language models to explicitly say "I don't know" on out‑of‑scope queries while preserving accuracy on known questions. The authors also propose new evaluation metrics for uncertainty, demonstrating that better discrimination between known and unknown instances improves overall performance.
By Joosung Lee, Hwiyeol Jo, Donghyeon Ko, Kyubyung Chae, Cheonbok Park, Jeonghoon Kim
The paper introduces an audio-first triage method for budgeted vision‑language captioning of untrimmed egocentric video. By selecting windows for a vision‑language model based on lightweight audio features before any video decoding, the approach reduces costly model calls. It achieves 4.0–10.8 percentage point improvements in action coverage across call rates, cuts 9–20% of VLM calls at matched coverage on EPIC‑KITCHENS‑100, and outperforms uniform sampling and recent visual keyframe selectors on Ego4D.
By Masoud Jalayer, Changyi Li, Yu Xiao
The paper introduces BanglaSafe, a benchmark of 879 Bengali prompts that covers 17 culturally grounded harm categories and five prompting conditions. Evaluation of 18 frontier LLMs shows that 53.6% of responses are unsafe or partially unsafe, with 14.7% containing strictly harmful content. The study finds that the writing style within Bengali has a stronger impact on safety than the language switch itself, and that current safety classifiers struggle to reliably evaluate Bengali content.
By Naymul Islam, Nusrat Jahan Lia, Shubhashis Roy Dipta, Sabik Bin Sultan, Abdullah Khan Zehady
arXiv:2608.22690v1 Announce Type: new
Abstract: Cell Painting microscopy captures how cells change after a chemical or genetic perturbation. Connecting these images to the perturbations that produced...
By Sukhrobbek Ilyosbekov (Northeastern University), Shubham Gajjar (Northeastern University), Rongfei Jin (Northeastern University)
arXiv:2608.23458v1 Announce Type: cross
Abstract: Interpretability is critical for machine learning models deployed in scientific space missions such as ESA's Ariel, where ground truth is unavailable...
By Nikki Grens, Lu\'is F. Sim\~oes, Kai Hou Yip, Theresa Lueftinger
The paper introduces MemeMind, a large-scale dataset for detecting harmful memes that includes a detailed taxonomy and Chain-of-Thought reasoning annotations. It also proposes MemeGuard, a multimodal framework that uses a three-stage training strategy to improve visual understanding, reasoning, and discrimination of harmful content. Experiments show MemeGuard surpasses current state-of-the-art methods on MemeMind, advancing detection accuracy and interpretability.
By Hexiang Gu, Qifan Yu, Yuan Liu, Zikang Li, Saihui Hou, Jian Zhao, Zhaofeng He