AI safety and alignment

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

17,808 stories · RSS feed

arXiv Computer Vision

Sep 16

Hyper-RED: Scalable Event Pre-training via Semantic Hypergraph Distillation

Hyper-RED introduces a scalable image-to-event pretraining framework that transfers high‑order semantic structures via hypergraphs, avoiding rigid pixel‑wise alignment. By constructing image, event, and cross‑modal hypergraphs and applying a hypergraph relational distillation loss, the method preserves local relational consistency and event‑specific characteristics while inheriting image‑derived semantic organization. Experiments across five event datasets show consistent scaling from ViT‑S to ViT‑L and state‑of‑the‑art performance.

By Meisen Wang, Zhiqiang Tian, Wei Bao, Chengjie Wang, Shaoyi Du, Siqi Li

efficiency multimodal benchmarks safety

arXiv Computer Vision

Sep 16

ORCA: Occlusion-Aware Refinement and Completion for Novel View Synthesis

arXiv:2609.17450v1 Announce Type: new Abstract: Novel-view synthesis from a single image is a fundamentally ambiguous problem. As the camera moves away from the input viewpoint, previously hidden reg...

By Weronika Jakubowska, Maciej Zi\k{e}ba, Przemys{\l}aw Spurek

safety

arXiv Computer Vision

Sep 16

HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning

arXiv:2604.15678v2 Announce Type: replace Abstract: Pretrained Vision-Language Models (VLMs) like CLIP show promise in continual learning, but existing Few-Shot Class-Incremental Learning (FSCIL) met...

By Eunju Lee, MiHyeon Kim, JuneHyoung Kwon, Yoonji Lee, JiHyun Kim, Soojin Jang, YoungBin Kim

llms rag multimodal benchmarks safety

arXiv Statistics ML

Sep 16

Covariate Selection for Doubly Robust Double/debiased Machine Learning Estimators for Causal Inference

arXiv:2609.17238v1 Announce Type: cross Abstract: High-dimensional data create challenges for causal effect estimation because identifying the covariates needed for correct model specification become...

By Muwon Kwon, Peter M. Steiner

safety

arXiv Machine Learning

Sep 16

Structure-Aware Masking for Protein Representation Learning

arXiv:2605.16581v2 Announce Type: replace Abstract: Masked language modeling (MLM) is the standard objective for training protein language models, typically implemented by randomly masking individual...

By Thomas Walton, Ayan Goel, Amirali Aghazadeh

llms safety

arXiv Machine Learning

Sep 16

AllShowers: One model for all calorimeter showers

arXiv:2601.11716v2 Announce Type: replace-cross Abstract: Accurate and efficient detector simulation is essential for modern collider experiments. To reduce the high computational cost, various fast...

By Thorsten Buss, Henry Day-Hall, Frank Gaede, Gregor Kasieczka, Katja Kr\"uger

llms rag safety

arXiv Computation and Language

Sep 16

A Data-free Universal Prior over Syntactic Structures

arXiv:2609.16854v1 Announce Type: new Abstract: Probability is fundamental to theories of language comprehension, production, acquisition, and evolution, as well as to large language models. Existing...

By Ferm\'{\i}n Moscoso del Prado Mart\'{\i}n

llms safety

arXiv Computer Vision

Sep 16

What Do Hallucinations Reveal About Multimodal Reasoning? Diagnosing Visual Grounding Failures via Contrastive Decoding Probes

arXiv:2609.16646v1 Announce Type: new Abstract: When strong multimodal models are widely available, progress requires new scientific methodologies beyond benchmark scores---using models as instrument...

By Zhipeng Zhao, Wenxu Wang, Peishun Liu, Ruichun Tang

llms multimodal benchmarks safety

arXiv Machine Learning

Sep 16

A Systematic Evaluation of Machine Learning Methods for Fault Detection and Line Identification in Electrical Power Grids

arXiv:2609.16744v1 Announce Type: new Abstract: The integration of renewable energy sources into the electrical grid introduces complex challenges in fault detection and coordination of grid recovery...

By Julian Oelhaf, Georg Kordowich, Paula Andrea P\'erez-Toro, Tom\'as Arias-Vergara, Andreas Maier, Johann J\"ager, Siming Bayer

safety

arXiv Machine Learning

Sep 16

Noise2Noise Revisited: Training Pair Distributions Dominate Loss Choice in Self-Supervised Denoising

arXiv:2609.16788v1 Announce Type: new Abstract: Noise2Noise (N2N) trains denoisers on pairs of independently corrupted observations, eliminating clean references. We stress-test two natural conjectur...

By Dingyan Shang, Zhenyu Xu, Youting Wang, Bonan Shen, Bowen Liu

efficiency benchmarks safety

arXiv AI

Sep 16

Managing Action Preconditions in Neuro-Symbolic RL: Three Placement Strategies for Embodied Agents

arXiv:2609.16056v1 Announce Type: cross Abstract: Humans carry behaviour knowledge of how to act in familiar situations into every new task rather than relearning it from scratch. There is no reason...

By Norbert Oswald, Fabian Deuser, Thomas Br\"aunl

agents reinforcement-learning robotics benchmarks safety

arXiv AI

Sep 16

FairLint-DL: An IDE-Native Tool for Fairness Debugging of Deep Learning Software

arXiv:2609.16321v1 Announce Type: cross Abstract: Existing fairness analysis tools predominantly operate as post-training evaluation frameworks, requiring practitioners to complete the full model dev...

By Archit Rathod, Saeid Tizpaz-Niari

benchmarks safety

arXiv AI

Sep 16

Interpreting and Steering LLM Agents for Social Simulations

arXiv:2609.16436v1 Announce Type: cross Abstract: Simulations based on large language models (LLMs) have proven to be powerful for understanding human behavior, making them valuable additions to the...

By Jiayue Gaveal Fan, Arul Murugan, Shreyas Krishnan, Abhishek Nagaraj

llms agents robotics safety

arXiv AI

Sep 16

What Does Layer-Importance Reveal About Transformers and State-Space Models?

arXiv:2609.16537v1 Announce Type: cross Abstract: Transformers and state-space models (SSMs) are the two dominant families of sequence models, and a central open question is how far the analytical kn...

By Istabrak Abbes, Nizar Islah, Irina Rish, Sarath Chandar

llms fine-tuning safety

arXiv AI

Sep 16

DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow

arXiv:2509.12626v4 Announce Type: replace-cross Abstract: Aligning agentic AI with user intent is critical for delegating complex, socially embedded tasks, yet user preferences are often implicit, ev...

By Tao Long, Xuanming Zhang, Sitong Wang, Zhou Yu, Lydia B Chilton

agents safety

arXiv Machine Learning

Sep 16

Anatomy of Associative Recall in Fixed-State Recurrences: A Matched-State Decomposition, an Interference Wall, and a Curriculum That Breaks It

arXiv:2609.16183v1 Announce Type: new Abstract: Fixed-state recurrences--linear attention and state-space models--are reported to lag behind attention on associative recall, but whole-architecture co...

By Julian Boesch, Andrew Wee

benchmarks safety

arXiv Machine Learning

Sep 16

Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration

arXiv:2609.16204v1 Announce Type: new Abstract: Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a technique that identifies and projects...

By Aashiq Muhamed, Mona T. Diab, Virginia Smith

llms fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Sep 16

Certified Uncertainty Propagation in One-Shot Federated Bayesian Models via Posterior Event Transport

arXiv:2609.16373v1 Announce Type: new Abstract: Probabilistic certification of Bayesian neural networks lower-bounds the posterior probability that a model satisfies a verifier-defined safety propert...

By Mahyar Mohammadi, Mohammad Hossein Badiei, Abolfazl Yaghmaei, Hamed Kebriaei

safety

arXiv AI

Sep 16

BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents

arXiv:2609.16305v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and...

By Sadia Asif, Mohammad Mohammadi Amiri, Momin Abbas, Tejaswini Pedapati, Prasanna Sattigeri

llms agents benchmarks safety

arXiv AI

Sep 16

SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing

arXiv:1906.07927v4 Announce Type: cross Abstract: Deep neural networks (DNNs) have achieved great success in various applications due to their strong expressive power. However, recent studies have sh...

By Haonan Qiu, Chaowei Xiao, Lei Yang, Xinchen Yan, Honglak Lee, Bo Li

robotics safety

Get the daily briefing