arXiv:2606. 07712v1 Announce Type: cross Abstract: Progress in AI-driven crystal materials science has so far been carried by narrow architectures purpose-built for individual tasks -- graph neural networks for property prediction, diffusion and flow-matching models for crystal generation -- each excelling within its niche yet unable to act as a shared backbone across the full spectrum of materials problems.
By Zhan'ao Yao, Boxuan Zhang, Jingyuan Shu, Xiaoyu Wu, Rongyan Wang, Linjing Li, Dajun Zeng, Yudong Yao, Tingwei Chen, Youwei Wang, Xiaolin Zhao, Jiahui Shi, Jianjun Liu
arXiv:2606. 09475v1 Announce Type: new Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misaligned behavior.
By Guillermo Del Pinal, Youngchan Lee, Cameron McNamara, Alejandro Perez Carballo
arXiv:2606. 07713v1 Announce Type: cross Abstract: The attention mechanism is the dominant computational bottleneck in modern transformer-based AI.
By Lenore Mullin, Gaetan Hains
arXiv:2604. 09967v2 Announce Type: replace-cross Abstract: Muon has emerged as a promising optimizer for large-scale foundation model pre-training by exploiting the matrix structure of neural network updates through iterative orthogonalization.
By Ziyue Liu, Ruijie Zhang, Zhengyang Wang, Yequan Zhao, Yupeng Su, Zi Yang, Zheng Zhang
arXiv:2606. 08021v1 Announce Type: cross Abstract: As large language model (LLM) agents are integrated into autonomous cloud operations, distributed systems face a semantic reliability problem: proposer agents can generate production mutations, such as modifying IAM policies, opening firewall security groups, or executing data exports, that are syntactically valid and statically authorized but operationally unsafe.
By Jun He, Deying Yu
arXiv:2606. 09371v1 Announce Type: new Abstract: Tool learning enables LLMs to invoke external tools to accomplish tasks.
By Haotong Yang, Ting Long, Yi Chang
arXiv:2606. 08364v1 Announce Type: cross Abstract: Temporomandibular joint osteoarthritis (TMJ OA) is a prevalent degenerative condition whose osseous changes are often subtle on cone-beam CT (CBCT), making automated detection challenging.
By Shradhdha Trivedi, Vrundan Sojitra, Mariela Padilla
arXiv:2606. 09749v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks.
By Seongbin Park, Fan Zhang, Baharan Mirzasoleiman, Shahriar Talebi, Nader Sehatbakhsh
arXiv:2606. 08529v1 Announce Type: new Abstract: Published agent capability scores conflate what a model can do with what its scaffold lets it do, and the magnitude of this elicitation gap is not well characterized under controlled conditions.
By Jason Starace
arXiv:2511. 18676v2 Announce Type: replace-cross Abstract: Current vision-language models (VLMs) in medicine are primarily designed for categorical question answering (e.
By Yongcheng Yao, Yongshuo Zong, Raman Dutt, Yongxin Yang, Sotirios A Tsaftaris, Timothy Hospedales
arXiv:2606. 07520v1 Announce Type: cross Abstract: Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints, ranging from verifiable ones (e.
By Yirong Zeng, Yufei Liu, Xiao Ding, Yutai Hou, Yuxian Wang, Wu Ning, Haonan Song, Dandan Tu, Qixun Zhang, Yuxiang He, Bibo Cai, Ting Liu
arXiv:2404. 02039v5 Announce Type: replace Abstract: Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity.
By Sihao Hu, Tiansheng Huang, Gaowen Liu, Ramana Rao Kompella, Fatih Ilhan, Selim Furkan Tekin, Yichang Xu, Zachary Yahn, Ling Liu
arXiv:2606. 09520v1 Announce Type: cross Abstract: Can a general-purpose large language model design molecules with the precision of a seasoned chemist?
By Junyi Gong, Zijie Qiu, Ben Zhong Tang
arXiv:2602. 08222v2 Announce Type: replace Abstract: As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow highly confident, further training yields diminishing returns.
By Zehao Chen, Gongxun Li, Tianxiang Ai, Zixuan Huang, Xiaodong Liu, Yifei Li, Wang Zhou, Fuzhen Zhuang, Xianglong Liu, Jianxin Li, Deqing Wang, Yikun Ban
arXiv:2606. 08158v1 Announce Type: cross Abstract: Large language models (LLMs) can generate factually inconsistent claims, motivating accurate and scalable hallucination detectors.
By Shanshan Lin, Dongsheng Hong, Sibo Ju, Chao Chen, Xi Zhang, Xiangwen Liao
arXiv:2606. 07897v1 Announce Type: new Abstract: Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user.
By Alejandro Botas, Paul de Font-Reaulx, Luke Hewitt
arXiv:2606. 07631v1 Announce Type: cross Abstract: Emergent misalignment (EM) occurs when narrow finetuning causes a model to behave dangerously outside the finetuning task.
By Huy Nghiem, Sy-Tuyen Ho, Sarah Wiegreffe, Hal Daum\'e III
arXiv:2605. 17254v3 Announce Type: replace Abstract: Property prediction and inverse structural design of catalytic materials are typically modeled as two independent tasks: the former predicts target properties from given structures, whereas the latter generates candidate structures according to desired properties.
By Yanjie Li, Jian Xu, Xu-Yao Zhang, Shiming Xiang, Nian Ran, Weijun Li, Cheng-Lin Liu
arXiv:2602. 00238v2 Announce Type: replace-cross Abstract: Existing retrieval-augmented generation (RAG) systems often assume that each query has a single correct answer.
By Tianyi Hu, Niket Tandon, Akhil Arora
arXiv:2606. 08565v1 Announce Type: cross Abstract: Tensor networks provide efficient representations for compressing large neural networks.
By Toshiaki Koike-Akino, Jing Liu, Ye Wang