arXiv:2607. 17575v1 Announce Type: new Abstract: We propose ARBITER, a novel LLM guardrail framework that introduces two key ideas: (i) dual-hypothesis reasoning, a reasoning method for LLM guardrails that explicitly considers both safe and unsafe interpretations of a prompt before making a safety decision, and (ii) multi-component supervised fine-tuning (MC-SFT), a structured training loss for reasoning-based guardrails that decomposes LLM outputs into logical components and weights them according to their importance.
By Md Asiful Islam, Mihai Surdeanu
arXiv:2607. 16727v1 Announce Type: new Abstract: Autoregressive multimodal large language models (MLLMs) suffer from error snowballing: a single incorrect inference early in a chainof-thought (CoT) trace corrupts all downstream reasoning.
By Zehua Cheng, Wei Dai, Jiahao Sun
arXiv:2607. 17382v1 Announce Type: cross Abstract: Existing research shows that AI-generated text detection classifiers achieve strong in-distribution (ID) performance but do not maintain the same performance on out-of-distribution (OOD) texts, suggesting overfitting to dataset-specific features.
By Shantanu Thorat
arXiv:2607. 17620v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) makes finetuning large language models cheaper by adding to each weight matrix a trainable low-rank update parameterized as the product of two matrices.
By Nikhil Ghosh, Tetiana Parshakova, Robert M. Gower
arXiv:2607. 18130v1 Announce Type: new Abstract: Most parameter-efficient finetuning (PEFT) methods adapt weights or activations, thus leaving one of the key Transformer components unchanged: residual connections.
By Valentijn Oldenburg, Floris de Kam, Bente Zuijdam, Lieve Eberson, Nicky van Zutphen, Stef de Wildt, Ivo Verhoeven
arXiv:2607. 16635v1 Announce Type: cross Abstract: We present TellTale, a text-only approach to ambivalence/hesitancy (A/H) recognition in interview videos, evaluated on the BAH dataset as part of the 3rd A/H Video Recognition Challenge (11th ABAW Workshop, ECCV 2026).
By Abdel-Karim Al-Tamimi, Ali Rodan
arXiv:2607. 16273v1 Announce Type: cross Abstract: In forensic environments, automated identification of perpetrators is difficult due to pose changes, changes in light, occlusion, and lack of labeled data.
By Savitha N J, Lata B T
arXiv:2607. 18199v1 Announce Type: cross Abstract: Not all training samples contribute equally to large language model fine-tuning.
By Hang Zhang, Warren J. Gross
arXiv:2607. 18046v1 Announce Type: new Abstract: Graphical User Interface (GUI) agents powered by vision-language models hold promise for automating real-world mobile tasks.
By Zhuohang Fan, Beichen Zhang, Yuanfa Li, Changqiao Wu, Wei Liu, Jian Luan, Weigang Zhang
arXiv:2509. 09371v2 Announce Type: replace-cross Abstract: Distributionally robust optimization (DRO) protects statistical learning against distributional shifts by optimizing the worst-case performance over a set of perturbed distributions.
By Zitao Wang, Nian Si, Molei Liu
arXiv:2607. 17377v1 Announce Type: new Abstract: The paper presents a new parameter-efficient adaptation method called ChebyMA (Chebyshev Manifold Adaptation).
By Jiawen Li
arXiv:2604. 15699v2 Announce Type: replace Abstract: Graph self-supervised learning can reduce the need for labeled graph data and has been widely used in recommendation, social networks, and other web applications.
By Haojie Li, Mengjiao Zhang, Guanfeng Liu, Qiang Hu, Yan Wang, Junwei Du
arXiv:2506. 07691v2 Announce Type: replace-cross Abstract: Sparse Autoencoders (SAEs) are a cornerstone of mechanistic interpretability.
By Jiaming Li, Haoran Ye, Yukun Chen, Xinyue Li, Lei Zhang, Hamid Alinejad-Rokny, Jimmy Chih-Hsien Peng, Min Yang
arXiv:2607. 18209v1 Announce Type: cross Abstract: This paper considers a multi-environment factor model in which high-dimensional covariates are collected from heterogeneous environments, with auxiliary labels available in a subset of these environments.
By Yihong Gu, Katherine Liao, Tianxi Cai
arXiv:2607. 16681v1 Announce Type: new Abstract: Early sepsis prediction from electronic health records is challenged by irregular sampling, high missingness, and class imbalance.
By Umair bin Mansoor, Munaf Rashid, Roomi Naqvi
Safety interventions on dual-use knowledge typically choose between destroying hazardous content (e. g.
Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones. However, MambaOut demonstrates that a Gated CNN block can match or exceed VMamba on image classification, questioning the necessity of SSMs for vision.
Pretrained dense visual features from Vision Transformers (ViTs) are powerful yet have been underutilized in robot learning. Modern robot policies either compress each observation into a single global token, or rely on visual backbones trained from scratch, sacrificing both fine-grained spatial detail and the benefits of large-scale visual pre-training.
This paper considers a multi-environment factor model in which high-dimensional covariates are collected from heterogeneous environments, with auxiliary labels available in a subset of these environments. The joint distribution of the covariates may vary across environments, whereas the latent structure is decomposed into invariant factors with shared loadings and heterogeneous factors with environment-specific loadings.
Structural fidelity is essential to scientific methodology diagrams. To communicate research logic, these diagrams must faithfully render components, directional relations, and textual annotations.