Personalizing large language models (LLMs) to individual users is essential for improving user experience, yet existing approaches typically rely on explicit preference supervision such as pairwise comparisons or demographic attributes, limiting their applicability in natural interaction settings. We propose IRIS, a framework that learns dynamic user personas directly from implicit interaction streams by extracting behavioral signals from everyday conversations and iteratively refining persona representations through a prediction-driven closed loop without requiring explicit feedback.
Audio deepfake detectors often degrade when generators, corpora, or recording conditions change. We use a Diffusion Transformer (DiT), trained only on bona fide speech, as a frozen reconstruction probe.
Traffic prediction is a core task in intelligent transportation systems, supporting applications such as adaptive signal control, route guidance, and ride-hailing dispatch. Deep learning models, including graph convolutional networks, recurrent networks, and Transformers, achieve strong results on standard benchmarks, but their architectures are designed by hand, requiring significant expert effort and producing models that often generalize poorly across cities and datasets.
Multimodal Large Language Models have sparked significant interest due to their potential for social intelligence; however, their ability to perform sequential motivation reasoning remains insufficiently studied. Existing evaluations predominantly examine static text or isolated visual snapshots, which do not reflect the cumulative nature of real-world behavioral drivers.
Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquired knowledge under repeated updates remains insufficiently understood. Existing evaluation paradigms primarily focus on single-step reasoning or static knowledge editing, which fail to capture the temporal dynamics of knowledge retention and degradation during continual model modification.
arXiv:2607. 24769v1 Announce Type: new Abstract: With the growing capabilities of frontier models, AI alignment becomes increasingly critical in high-risk deployment settings.
By Nathan Truong, Aryan Panda, Rayming Ye, Zoe Sun, Maheep Chaudhary
arXiv:2607. 24774v1 Announce Type: new Abstract: Nuclear radiation, the energy released during atomic decay, poses persistent risks to public health and the environment, and concerns have only grown since the Fukushima accident and the recent commencement of treated-water discharge.
By Tengfei Lyu, Jindong Han, Hao Liu
arXiv:2607. 24794v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) demonstrate superior generalization in fundamental video tasks, restricted context windows limit their long video understanding.
By Linghao Meng, Qiankun Li, Junyuan Mao, Pujin Liao, Zhicheng He, Enbo Zhang, Kun Wang, Yang Liu, Huazhu Fu, Yueming Jin
arXiv:2607. 24783v1 Announce Type: new Abstract: Job understanding is critical to LinkedIn's mission of connecting talent with opportunity.
By Dan Xu, Baofen Zheng, Jianqiang Shen, Qi Xiao, Benjamin Hoan Le, Wen Pu, Saurabh Gupta, Ran Zhou, Neha Saraf, Alice Leung, Qianqi Shen, Liangjie Hong, Jingwei Wu, Wenjing Zhang
arXiv:2607. 24873v1 Announce Type: new Abstract: Recent advances in AI music generation have enabled users to create complete musical pieces from natural-language prompts.
By Callie C. Liao, Duoduo Liao, Ellie L. Zhang
arXiv:2607. 25292v1 Announce Type: new Abstract: Silicon sampling uses language models as proxies for human survey respondents, treating each model call as an independent draw from the persona's response distribution.
By Chaemin Jang, Dongman Lee, Jihee Kim
arXiv:2607. 14137v2 Announce Type: cross Abstract: To answer a question about a program, move the program to where the question is decidable.
By Christoph Kirsch
arXiv:2607. 24767v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems have emerged as a powerful process for allowing large language models (LLMs) to retrieve relevant information to use as source material during text generation.
By German Garrido-Lestache Belinchon, Hugo Garrido-Lestache Belinchon
arXiv:2607. 24838v1 Announce Type: cross Abstract: In medical multiple-choice question answering (MCQA), Retrieval-Augmented Generation (RAG) can supplement the domain knowledge of language models (LMs).
By Seongwon Seo, Seung Hwan Cho, Young-Min Kim
arXiv:2607. 24887v1 Announce Type: cross Abstract: Existing theories of neural-network width characterize asymptotic limits, but provide limited guidance on whether an expansion direction identified from finite training data remains beneficial on unseen data.
By Jinhao Zhang, Zeyu Liu, Zicheng Yan, Yunquan Zhang, Guangming Tan, Fangming Liu, Daning Cheng
arXiv:2607. 25145v1 Announce Type: cross Abstract: We implement an agentic AI workflow built around a large language model (LLM) agent for autonomous experiments with nitrogen-vacancy (NV) centers in diamond.
By Takuya Isogawa, Ryotaro Okabe, Nutdech Phadetsuwannukun, Mingda Li, Paola Cappellaro
arXiv:2607. 25209v1 Announce Type: cross Abstract: Generative recommendation commonly represents items using fixed-length semantic identifiers (SIDs) constructed through clustering and quantization.
By Shutong Qiao, Wei Yuan, Tong Chen, Hao Wang, Quoc Viet Hung Nguyen, Hongzhi Yin
arXiv:2607. 25357v1 Announce Type: cross Abstract: Long-context recall in linear-time sequence models highlights a tradeoff in how they write to memory.
By Arshia Afzal, Aviv Bick, Eric P. Xing, Volkan Cevher, Albert Gu
arXiv:2607. 25459v1 Announce Type: cross Abstract: Mechanistic interpretability has largely focused on language models and deterministic toy tasks.
By Xiaoyu Huang, Lulu Wang
arXiv:2607. 25504v1 Announce Type: cross Abstract: Fine-grained weight pruning and activation sparsification have emerged as effective approaches for reducing the compute and memory cost of inference for Transformer models.
By Bowen Wang, Chi Zhang, Diyou Shen, Renzo Andri, Navaneeth Kunhi Purayil, Luca Benini