AI safety and alignment

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

10,646 stories · RSS feed

arXiv Machine Learning

Jun 18

Investigation of Neural Network Methods for Reconstruction and Classification of Texture Images Under Conditions of Incomplete Information

arXiv:2204. 14224v3 Announce Type: replace-cross Abstract: The automated analysis of heterogeneous natural textures is frequently hindered by physical damage and data loss, presenting a significant challenge to computer vision.

By Galymzhan Abdimanap, Kairat Bostanbekov, Abdelrahman Abdallah, Anel Alimova, Darkhan Kurmangaliyev, Daniyar Nurseitov, Tatyana Dedova, Larissa Balakay, Serik Nurakynov

llms agents diffusion computer-vision benchmarks safety

arXiv Machine Learning

Jun 18

Adaptive Speech-to-Spike Encoding for Spiking Neural Networks

arXiv:2606. 19039v1 Announce Type: cross Abstract: The mismatch between continuous acoustic signals and discrete event-driven processing remains a fundamental bottleneck for neuromorphic speech processing.

By Taharim Rahman Anon, Jakaria Islam Emon

benchmarks safety

arXiv Machine Learning

Jun 18

Complementary Attention Head Pruning for Efficient Transformers

arXiv:2606. 19150v1 Announce Type: new Abstract: The remarkable success of Transformer-based models in natural language processing stems from architectural scaling, which leads to a large number of parameters and hinders deployment in resource-constrained environments.

By Yaniv Livertovsky, Shahar Somin, Gonen Singer

llms nlp efficiency benchmarks safety

arXiv AI

Jun 18

ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection

arXiv:2606. 18988v1 Announce Type: new Abstract: Multimodal deception detection is critical for identifying fraudulent intentions, yet existing approaches predominantly rely on end to end black--box paradigms.

By Jinhao Song, Shan Liang, Yiqun Yue, Zhuhuayang Zhang, Tianqi Gao

llms reinforcement-learning multimodal benchmarks safety

arXiv AI

Jun 18

AdsMind: A Physics-Grounded Multi-Agent System for Self-Correcting Discovery of Adsorption Configurations on Heterogeneous Catalyst Surfaces

arXiv:2606. 19152v1 Announce Type: cross Abstract: Identifying the lowest-energy surface-adsorbate configuration is critical for modeling heterogeneous catalysis, yet exhaustive exploration with ab initio calculations is computationally prohibitive.

By Zongmin Zhang, Yuyang Lou, Bowen Zhang, Junwu Chen, Ryo Kuroki, Xuan Vu Nguyen, Edvin Fako, Lixue Cheng, Philippe Schwaller

llms agents benchmarks safety

arXiv AI

Jun 18

A Technical Taxonomy of LLM Agent Communication Protocols

arXiv:2606. 19135v1 Announce Type: cross Abstract: As large language models (LLMs) advance and multi-agent systems aim to overcome the limits of standalone agents, robust communication protocols are becoming essential infrastructure for distributed agent networks.

By Linus Sander, Habtom Kahsay Gidey, Alexander Lenz, Alois Knoll

llms agents safety

arXiv Machine Learning

Jun 18

OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing

arXiv:2606. 19149v1 Announce Type: cross Abstract: Automated vulnerability discovery in large codebases remains challenging: traditional static analysis produces high false-positive rates, while dynamic approaches such as fuzzing require substantial infrastructure and often target narrow classes of bugs.

By Nahum Korda, Gadi Evron

llms safety

arXiv Machine Learning

Jun 18

Self-Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale

arXiv:2605. 07022v3 Announce Type: replace Abstract: Manually curated biomedical repositories -- spanning bioactivity, genomics, and chemistry -- are expensive to maintain, lag behind primary literature, and discard experimental context, obscuring nuances needed to assess data correctness and coverage.

By Haydn Jones, Yimeng Zeng, Alden Rose, Li S. Yifei, Yining Huang, Kaiwen Wu, Jiaming Liang, Maggie Ziyu Huan, Yoseph Barash, Cesar de la Fuente-Nunez, Osbert Bastani, Zachary Ives, Mark Yatskar, Jacob R. Gardner

llms agents robotics safety

arXiv AI

Jun 18

TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology

arXiv:2606. 19245v1 Announce Type: new Abstract: Artificial intelligence (AI) agents promise to accelerate drug discovery by compressing interpretation and decision-making loops, but practical deployment requires trusted evaluation on realistic program decisions.

By Hannah Le, Ramesh Ramasamy, Alex Urrutia, Mahsa Yazdani, Tim Proctor, Kenny Workman

llms agents benchmarks safety

arXiv AI

Jun 18

Learning Patient-Specific Disease Dynamics with Latent Flow Matching for Longitudinal Imaging Generation

arXiv:2512. 09185v4 Announce Type: replace-cross Abstract: Understanding disease progression is a central clinical challenge with direct implications for early diagnosis and personalized treatment.

By Hao Chen, Rui Yin, Yifan Chen, Qi Chen, Chao Li

diffusion benchmarks safety

arXiv AI

Jun 18

SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding

arXiv:2601. 12805v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown growing promise in biomedical research, particularly for knowledge-driven interpretation tasks.

By Xiaohan Huang, Meng Xiao, Chuan Qin, Qingqing Long, Jinmiao Chen, Yuanchun Zhou, Hengshu Zhu

llms benchmarks safety

arXiv AI

Jun 18

Practical Anonymous Two-Party Gradient Boosting Decision Tree

arXiv:2605. 26903v2 Announce Type: replace-cross Abstract: Structured data is well handled by gradient-boosted decision trees (GBDT), which are usually trained on vertically partitioned features across mutually distrustful parties.

By Chenyu Huang, Fan Zhang, Minxin Du, Sherman S. M. Chow, Huangxun Chen, Huaming Rao, Danqing Huang, Bo Qian, Peng Chen

safety

arXiv AI

Jun 18

Generalized Kullback-Leibler Divergence Loss

arXiv:2503. 08038v2 Announce Type: replace-cross Abstract: In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of (1) a weighted Mean Square Error (wMSE) loss and (2) a Cross-Entropy loss incorporating soft labels.

By Jiequan Cui, Beier Zhu, Qingshan Xu, Zhuotao Tian, Xiaojuan Qi, Bei Yu, Hanwang Zhang, Richang Hong

efficiency multimodal benchmarks safety

arXiv AI

Jun 18

From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization

arXiv:2508. 09191v2 Announce Type: replace-cross Abstract: Time series forecasting plays a vital role in supporting decision-making across a wide range of critical applications, including energy, healthcare, and finance.

By Xiaoyu Tao, Shilong Zhang, Mingyue Cheng, Daoyu Wang, Tingyue Pan, Bokai Pan, Changqing Zhang, Shijin Wang

llms nlp fine-tuning safety

arXiv Machine Learning

Jun 18

RNN(p) for Power Consumption Forecasting

arXiv:2209. 01378v3 Announce Type: replace Abstract: An elementary Recurrent Neural Network that operates on p time lags, called an RNN(p), is the natural generalisation of a linear autoregressive model ARX(p).

By Roberto Baviera, Pietro Manzoni

safety

arXiv Machine Learning

Jun 18

How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?

arXiv:2603. 04895v2 Announce Type: replace-cross Abstract: Overparameterized ML models, including neural networks, typically induce underdetermined training objectives with multiple global minima.

By Kuo-Wei Lai, Guanghui Wang, Molei Tao, Vidya Muthukumar

safety

arXiv Machine Learning

Jun 18

KEPLA: A Knowledge-Enhanced Deep Learning Framework for Accurate Protein-Ligand Binding Affinity Prediction

arXiv:2506. 13196v5 Announce Type: replace Abstract: Accurate prediction of protein-ligand binding affinity is critical for drug discovery.

By Han Liu, Keyan Ding, Peilin Chen, Yinwei Wei, Liqiang Nie, Dapeng Wu, Shiqi Wang

rag benchmarks safety

arXiv AI

Jun 18

Language Models as Interfaces, Not Oracles: A Hybrid LLM-ML System for Pediatric Appendicitis

arXiv:2606. 19183v1 Announce Type: cross Abstract: Large language models (LLMs) can make clinical decision support more accessible by interpreting free-text documentation, but their direct use as diagnostic engines is limited by sensitivity to prompts, information order, and plausible but incorrect outputs.

By Soheyl Bateni, Maryam Abdolali

llms safety

arXiv AI

Jun 18

Dual-Channel Grounded World Modeling (DCGWM): Structural Prevention of Objective Interference Collapse via Heterogeneous External Grounding with Inward-Only Gradient Flow

arXiv:2606. 18688v1 Announce Type: cross Abstract: Joint Embedding Predictive Architectures (JEPAs) are a leading approach to world model representation learning.

By Akshay Hazare

rag agents diffusion safety

arXiv AI

Jun 18

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

arXiv:2606. 18322v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) decompose residual-stream activations into interpretable features.

By Mingyue Cui, Linghui Shen, Xingyi Yang

safety

Get the daily briefing