OpenAI Blog
Jul 20
Safety and alignment in an era of long-horizon models
OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
Hugging Face Trending Papers
Jul 20
FlowSonic: Stable Zero-Shot Music Editing via High-Order Trajectory Integration
Zero-shot text-guided editing of real-world music recordings requires balancing semantic modification with faithful preservation of the original musical structure. Although recent diffusion transformers trained with rectified flow have achieved remarkable success in text-to-music generation, extending them to edit existing recordings remains challenging because editing requires accurate deterministic inversion, reliable structural preservation, and numerically stable integration throughout the inversion and generation processes.
arXiv AI
Jul 20
MAnchors: Memorization-Based Acceleration of Anchors via Rule Reuse and Transformation
arXiv:2502. 11068v3 Announce Type: replace-cross Abstract: Anchors is a popular local model-agnostic explanation technique whose applicability is limited by its computational inefficiency.
arXiv AI
Jul 20
Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
arXiv:2602. 24009v4 Announce Type: replace-cross Abstract: Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols.
arXiv AI
Jul 20
S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation
arXiv:2607. 15686v1 Announce Type: new Abstract: We present S1-Omni, a unified multimodal reasoning model for scientific understanding, prediction, and generation.
arXiv AI
Jul 20
AI Trading: Evaluating Large Language Models for Technical Market Analysis
arXiv:2607. 15414v1 Announce Type: cross Abstract: Large Language Models (LLMs) have emerged as powerful tools for processing the heterogeneous information environments of modern financial markets.
arXiv Machine Learning
Jul 20
DELUGE: Towards Continental-Scale Daily Pluvial Flood Damage Prediction via Interpretable Conditioning on Foundation Model Embeddings
arXiv:2607. 16050v1 Announce Type: new Abstract: Pluvial (rainfall-driven) flooding accounts for 45% of National Flood Insurance Program (NFIP) claims in the United States and is harder to predict than its riverine and coastal counterparts, with existing approaches limited to coarse resolution, regional domains, or computationally intensive process-based models unsuitable for daily continental-scale use.
arXiv AI
Jul 20
Structure of the Circular-Dyadic Convolution Error
arXiv:2607. 15293v1 Announce Type: cross Abstract: Dyadic and circular convolution can both be computed in $O(N\log N)$ time using the Hadamard transform and the FFT-computed discrete Fourier transform (DFT), respectively.
arXiv Machine Learning
Jul 20
Cluster-Aware Matching via Laplacian Optimal Transport
arXiv:2607. 16178v1 Announce Type: cross Abstract: In many applications of matching, the point clouds to be matched are not merely unstructured sets of points but rather samples from distributions with an intrinsic cluster structure.
arXiv Machine Learning
Jul 20
From hyperplanes to hyperellipsoids: characterizing the inherent interpretability of linear and single-qubit mixed-state binary classification models
arXiv:2607. 15433v1 Announce Type: new Abstract: We characterize and compare the inherent interpretability offerings of a standard linear model with a single qubit mixed state model for the task of supervised binary classification.
arXiv Machine Learning
Jul 20
Pretrained Event Classification Model for High Energy Physics Analysis
arXiv:2412. 10665v3 Announce Type: replace-cross Abstract: We introduce a foundation model for event classification in high-energy physics, built on a Graph Neural Network architecture and trained on 120 million simulated proton-proton collision events spanning 12 distinct physics processes.
arXiv Machine Learning
Jul 20
Robust Peak-cost Constrained Reinforcement Learning
arXiv:2607. 15457v1 Announce Type: new Abstract: We study robust peak-cost constrained reinforcement learning (RP-CRL), where the objective is to maximize expected reward while controlling the maximum cost encountered along a trajectory.
arXiv AI
Jul 20
Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability
arXiv:2510. 12229v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have been shown to internalize human-like biases during finetuning, yet the mechanisms by which these biases manifest remain unclear.
arXiv AI
Jul 20
LVSum: A Benchmark for Timestamp-Aware Long Video Summarization
arXiv:2604. 10024v2 Announce Type: replace-cross Abstract: Long video summarization presents significant challenges for multimodal large language models (MLLMs), particularly in maintaining temporal fidelity over extended durations and producing summaries that are both semantically and temporally grounded.
arXiv Machine Learning
Jul 20
ASK-NN: An Asymmetric Nearest-Neighbor Test that detects Distribution Drifts in Natural Language
arXiv:2607. 15607v1 Announce Type: new Abstract: Hallucinations and artificial text in LLM-generated outputs often appear as distributional deviations between prompt and response hidden-state distributions.
arXiv Machine Learning
Jul 20
Code-Poisoning Property Inference Attacks
arXiv:2607. 15970v1 Announce Type: cross Abstract: The flourishing code hosting platforms and coding agents enable even beginners with private data to build tailored Machine Learning (ML) models using available code quickly.
arXiv Machine Learning
Jul 20
A Transportable Threshold-Based Framework for Interpretable Classification of Medical Data
arXiv:2607. 15394v1 Announce Type: new Abstract: Black-box models limit the adoption of artificial intelligence in medicine due to their lack of interpretability and reproducibility.
arXiv Machine Learning
Jul 20
More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe
arXiv:2607. 15942v1 Announce Type: cross Abstract: Remote sensing vision-language models are increasingly expected to support open-ended reasoning over Earth Observation data and a variety of tasks.
arXiv AI
Jul 20
Closing the AI Trust Gap: The Case for Independent Certification for Trustworthy AI
arXiv:2607. 15992v1 Announce Type: new Abstract: Over the past decade, responsible AI (RAI) has produced a substantial body of practice for identifying and mitigating the risks AI poses in high-stakes settings.
arXiv AI
Jul 20
AV-JEPA: Extending LeJEPA to Audio-Visual Self-Supervised Learning
arXiv:2607. 15295v1 Announce Type: cross Abstract: We present AV-JEPA, an elegant multimodal extension of LeJEPA to audio-visual self-supervised learning.