AI safety and alignment

Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.

10,474 stories · RSS feed

arXiv AI

Jun 30

Digitizing Coaching Intelligence: An Agentic Framework for Holistic Athlete Profiling using VLM and RAG

arXiv:2606. 28570v1 Announce Type: cross Abstract: Athlete assessment is a critical process for tracking physical progress and identifying elite talent.

By Deep Ghosal, Ishani Sen, Wazib Ansar, Amlan Chakrabarti

llms rag agents computer-vision multimodal safety data-engineering

arXiv AI

Jun 30

MammoFlow: Multiview Mammogram Synthesis with Anatomically Consistent Flow Matching

arXiv:2606. 28537v1 Announce Type: cross Abstract: Multiview mammography relies on paired craniocaudal (CC) and mediolateral oblique (MLO) views to provide complementary projections of a 3D breast volume, enabling precise anomaly localization.

By Yuexi Du, Leya Barrientos, Laura Sheiman, John Lewin, Hemant D. Tagare, Nicha C. Dvornek

diffusion safety

arXiv AI

Jun 30

Evidence-Based Text-Conditioned 3D CT Synthesis for Ovarian Cancer

arXiv:2606. 28980v1 Announce Type: cross Abstract: Ovarian cancer is frequently diagnosed at an advanced stage, making preoperative contrast-enhanced computed tomography (CT) central to staging and surgical planning; yet the scarcity of annotated imaging data, compounded by privacy regulations, limits the development of generalizable computational models in this domain.

By Francesca Pia Panaccione, Eugenio Lomurno, Francesca Fati, Carlotta Pecchiari, Marina Rosanu, Luigi De Vitis, Lucia Ribero, Gabriella Schivardi, Giovanni Damiano Aletti, Nicoletta Colombo, Maria Francesca Spadea, Francesco Multinu, Matteo Matteucci, Elena De Momi

diffusion fine-tuning multimodal benchmarks safety

arXiv AI

Jun 30

Modification-Considering Value Learning for Reward Hacking Mitigation in RL

arXiv:2606. 28955v1 Announce Type: cross Abstract: Reinforcement learning agents can exploit misspecified reward signals to achieve high apparent returns while failing on the intended objective, a failure mode known as reward hacking.

By Evgenii Opryshko, Umangi Jain, Igor Gilitschenski

agents reinforcement-learning safety

arXiv Machine Learning

Jun 30

FinInvest-GTCN: Explainable Graph-Temporal-Causal Modeling for Risk-Aware Investment Decision Optimization

arXiv:2606. 28933v1 Announce Type: cross Abstract: Venture capital (VC) investment decisions face distinct challenges, such as multi-source heterogeneous data, non-stationary time series, and the demand for explainable predictions in high-stakes, low-data settings.

By Junyan Tan, Yifan Li, Minghao Wang, Zihan Chen, Haoyu Zhang

fine-tuning benchmarks safety

arXiv AI

Jun 30

Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks

arXiv:2504. 17421v2 Announce Type: replace-cross Abstract: Large language models (LMs) offer broad generalization capabilities but require vast amounts of data and computational resources for domain-specific tasks; small models (SMs), in contrast, are more efficient and tailored to specific domains yet lack general-purpose coverage.

By Yang Liu, Kejia Zhang, Bingjie Yan, Tianyuan Zou, Jianqing Zhang, Zixuan Gu, Xiangsen Chen, Jianbing Ding, Xidong Wang, Jingyi Li, Xiaozhou Ye, Ye Ouyang, Qiang Yang, Ya-Qin Zhang

llms fine-tuning safety

arXiv Machine Learning

Jun 30

Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration

arXiv:2509. 21530v2 Announce Type: replace Abstract: Data augmentation is a widely used strategy to improve model robustness and generalization by enriching training datasets with synthetic examples.

By Dongkyu Cho, Miao Zhang, Rumi Chunara

llms safety

arXiv AI

Jun 30

Unlocking the Visual Record of Materials Science: A Large-Scale Multimodal Dataset from Scientific Literature

arXiv:2606. 29667v1 Announce Type: cross Abstract: The materials science literature encodes decades of experimental knowledge in figures, yet this visual record remains locked away and inaccessible to AI at scale.

By Subham Ghosh, Shubham Tiwari, Mohammad Ibrahim, Abhishek Tewari

llms fine-tuning multimodal safety

arXiv AI

Jun 30

ReactiveBFM: Reactive Closed-Loop Motion Planning Towards Universal Humanoid Whole-Body Control

arXiv:2606. 30362v1 Announce Type: cross Abstract: While current Behavior Foundation Models (BFMs) provide robust control priors for humanoids, they only execute pre-defined reference motions.

By Xiao Chen, Weishuai Zeng, Xiaojie Niu, Zirui Wang, Jianan Li, Huayi Wang, Furui Xu, Jiahe Chen, Weixiang Zhong, Lihe Ding, Kailin Li, Jiangmiao Pang, Tai Wang, Tianfan Xue, Jingbo Wang

rag benchmarks safety

arXiv AI

Jun 30

Pose-Based Fall Detection System: Efficient Monitoring on Standard CPUs

arXiv:2503. 19501v2 Announce Type: replace-cross Abstract: Falls among elderly residents in assisted living homes pose significant health risks, often leading to injuries and a decreased quality of life.

By Vinayak Mali, Saurabh Jaiswal

computer-vision safety

arXiv AI

Jun 30

Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions

arXiv:2606. 28770v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated the ability to simulate human-like OCEAN personality traits in generated text.

By David Courtis, Ting Hu

llms fine-tuning benchmarks safety

arXiv AI

Jun 30

The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning

arXiv:2606. 28843v1 Announce Type: cross Abstract: Fine-tuning a large language model is a ubiquitous method for enhancing its capability on a specific downstream task.

By Will Hawkins, Kaivalya Rawal, Jonathan Rystr{\o}m, Stratis Tsirtsis, Zihao Fu, Greta Warren, Ryan Brown, Eoin Delaney, Sandra Wachter, Brent Mittelstadt, Chris Russell

llms fine-tuning safety

arXiv AI

Jun 30

Interpretable Clustering: A Survey

arXiv:2409. 00743v4 Announce Type: replace-cross Abstract: In recent years, much of the research on clustering algorithms has primarily focused on enhancing their accuracy and efficiency, frequently at the expense of interpretability.

By Lianyu Hu, Mudi Jiang, Junjie Dong, Xinying Liu, Zengyou He

agents safety

arXiv AI

Jun 30

A Large-Scale Dataset for Molecular Structure-Language Description via a Rule-Regularized Method

arXiv:2602. 02320v4 Announce Type: replace-cross Abstract: Molecular function is largely determined by structure.

By Feiyang Cai, Guijuan He, Yi Hu, Jingjing Wang, Joshua Luo, Tianyu Zhu, Srikanth Pilla, Gang Li, Ling Liu, Feng Luo

llms safety

arXiv AI

Jun 30

Agile Reinforcement Learning through Separable Neural Architecture and Applications

arXiv:2601. 23225v2 Announce Type: replace-cross Abstract: Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet go-to function approximators - multilayer perceptrons (MLPs) - are often parameter-inefficient due to an imperfect inductive bias for the smooth structure of many value functions.

By Rajib Mostakim, Reza T. Batley, Sourav Saha

reinforcement-learning efficiency benchmarks safety

arXiv Machine Learning

Jun 30

Structured Proper Loss Geometries for Multiclass Classification: Theory and Controlled Empirical Evaluation

arXiv:2606. 29471v1 Announce Type: new Abstract: Strictly proper scoring rules identify the true conditional class distribution at population level, but their curvature can alter optimization and finite-sample behavior.

By Soumyadip Sarkar

safety

arXiv Machine Learning

Jun 30

BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language

arXiv:2606. 30319v1 Announce Type: cross Abstract: Modeling the bidirectional correspondence between external sensory stimuli and internal neural activity has emerged as a critical frontier in neuroscience.

By Haitao Wu, Qirui Zhang, Zhouheng Yao, Shangquan Sun, Qihao Zheng, Mianxin Liu, Chi Zhang, Wanli Ouyang, Chunfeng Song, Changqing Zhang, Jiamin Wu

nlp multimodal benchmarks safety

arXiv Machine Learning

Jun 30

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

arXiv:2602. 09305v2 Announce Type: replace Abstract: Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable.

By Pei-Chi Pan, Yingbin Liang, Sen Lin

llms reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jun 30

Synthetic Interaction Data for Scalable Personalization in Large Language Models

arXiv:2602. 12394v2 Announce Type: replace Abstract: Personalized prompting offers large opportunities for deploying large language models (LLMs) to diverse users, yet existing prompt optimization methods primarily focus on task-level optimization while largely overlooking user-specific preferences and latent constraints of individual users.

By Yuchen Ma, Yue Huang, Wenjie Wang, Xiaonan Luo, Xiangliang Zhang, Stefan Feuerriegel

llms agents reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 30

LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing

arXiv:2507. 07056v2 Announce Type: replace-cross Abstract: The proliferation of Low-Rank Adaptation (LoRA) models has democratized personalized text-to-image generation, enabling users to share lightweight models (e.

By Jiahao Chen, Junhao Li, Yiming Wang, Yong Yang, Yi Jiang, Chunyi Zhou, Qingming Li, Tianyu Du, Shouling Ji

llms diffusion fine-tuning safety

Get the daily briefing