OpenAI Blog
Jul 8
Our approach to government and national security partnerships
Learn how OpenAI approaches government and national security partnerships, with principles for responsible AI use, democratic accountability, and public safety.
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 8
R^3: Advertisement Compliance Rectification via Group-Relative Experience Extractor and Curriculum Reinforcement
Rigorous content moderation is crucial for online advertising but leads to millions of daily rejections. This scale renders manual rectification infeasible, particularly for video advertisements.
Hugging Face Trending Papers
Jul 8
FedCVESA: Taking Away Training Data in Federated Learning via Correlation Value Encoding and Segmented Aggregation
Federated learning (FL) avoids explicit data exposure by keeping raw data on local clients, yet privacy risks remain in the training process and the learned model itself. Recently, centralized Taking Away Training Data (TATD) attacks have shown that malicious training could abuse the memorization capacity of deep models to store and later recover training data.
Hugging Face Trending Papers
Jul 8
Safe Reinforcement Learning using Ideas from Model Predictive Control
Reinforcement learning (RL) enables the synthesis of control policies directly from data, making it highly appealing for complex cyber-physical systems (CPSs) and robotics. A persistent challenge, however, is ensuring strict, hard safety constraints during the active learning phase.
Hugging Face Trending Papers
Jul 8
`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation
Video object segmentation (VOS) is a fundamental task in video understanding, requiring accurate delineation and consistent tracking of objects across frames. While supervised methods achieve strong performance, they rely on densely annotated datasets that are costly to obtain and have limited domain coverage.
Hugging Face Trending Papers
Jul 8
DiffCVE: Diffusion-based Compressed Video Enhancement
Perceptual quality enhancement of severely compressed videos remains challenging due to complex artifact patterns and substantial information loss. Recent diffusion models have demonstrated strong generative capability for visual restoration, but directly applying them to compressed video often ignores compression degradation characteristics and may introduce structure-inconsistent hallucinations.
Hugging Face Trending Papers
Jul 8
Predicting LLM Safety Before Release by Simulating Deployment
Pre-deployment safety evaluations aim to inform the downstream risks of releasing a new AI model. Yet most evaluations provide limited evidence about how often undesired model behavior will occur in deployment: they generally have insufficient coverage, are unrepresentative, and are generally recognizable as tests.
Hugging Face Trending Papers
Jul 8
Stage-Aware Adaptation and Distribution Calibration for Subject-Driven Personalized Text-to-Image Generation
Subject-driven personalized text-to-image generation requires a pretrained diffusion model to acquire a specific subject from a few reference images while preserving subject identity, following novel text prompts, and maintaining sample diversity. Existing optimization-based methods instantiate subject adaptation through full fine-tuning, textual embedding optimization, or low-rank parameter updates; PaRa further constrains personalization from the perspective of parameter rank reduction.
Hugging Face Trending Papers
Jul 8
TACoS: Weakly Supervised Learning of Two-Dimensional Materials from Scribble Annotations to Precise Segmentation
The precise pixel-level localization of 2D material flakes is crucial for high-throughput screening. However, traditional fully supervised methods rely on dense annotations, which are costly and time-consuming, severely limiting the practical deployment of segmentation models.
Hugging Face Trending Papers
Jul 8
ASFR-Net: Adversarial Alignment and Spatio-Frequency Refinement Network for Heterogeneous Remote Sensing Image Change Detection
The core challenge of heterogeneous change detection in remote sensing imagery lies in effectively decoupling genuine land-cover changes from significant modal disparities caused by distinct imaging mechanisms. These intrinsic inconsistencies are prone to introducing pseudo-changes, thereby constraining detection accuracy.
Hugging Face Trending Papers
Jul 8
A knowledge-augmented dataset of high-risk driving scenarios with LLM annotations for autonomous driving
Safe autonomous driving requires both rapid responses to common high-risk events and deeper reasoning over rare, extreme long-tail scenarios in traffic safety. These scenarios are severely under-represented in naturalistic driving data, and existing trajectory and language-augmented datasets seldom provide high-risk event labels, semantic annotations, and verifiable safety signals.
Hugging Face Trending Papers
Jul 8
GeoProp: Grounding Robot State in Vision for Generalist Manipulation
Proprioception is fundamental to robotic manipulation, yet standard fusion methods often treat it as an isolated vector lacking explicit alignment with visual tokens. Without a direct correspondence between 3D kinematics and 2D feature maps, manipulation policies struggle to ground the robot's state within the scene, frequently underperforming even vision-only baselines.
Hugging Face Trending Papers
Jul 8
Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints
Relational Deep Learning (RDL) has become a standard methodology for machine learning on relational databases: the database is encoded as a heterogeneous temporal graph in which tuples become nodes and primary-key to foreign-key (PK-FK) dependencies become typed edges, over which a graph neural network is trained for downstream prediction. We study the adversarial robustness of this pipeline.
Hugging Face Trending Papers
Jul 8
Online Data Selection Is Implicit Alignment
Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinforcement learning. This separation is incomplete: when examples are scored and kept online during fine-tuning, the choice of which data to train on already changes the model's behavioral preferences.
Hugging Face Trending Papers
Jul 8
SHTA: Semantic Hard Token Correction and Center Alignment for Semi-Supervised Medical Image Segmentation
Recent advances in semi-supervised medical image segmentation have achieved remarkable performance through prediction consistency, pseudo-label supervision, and hard-region supervision. However, these methods primarily improve supervision quality rather than explicitly enforcing semantic consistency in the learned representations of hard regions.
arXiv AI
Jul 8
Is Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference
arXiv:2607. 05475v1 Announce Type: cross Abstract: Deploying Large Language Models (LLMs) on mobile devices enhances privacy and reduces latency, but is severely bottlenecked by hardware inefficiency.
arXiv AI
Jul 8
Automated Recommendation of Programming Learning Content Using Pattern-based Knowledge Components
arXiv:2607. 05409v1 Announce Type: cross Abstract: Introductory programming instruction relies on hands-on practice and short learning activities to support mastery of foundational concepts.
arXiv AI
Jul 8
Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty?
arXiv:2508. 01109v3 Announce Type: replace Abstract: We investigate whether socioeconomic indicators, like household wealth, leave recoverable informational imprints in both satellite imagery (capturing features like buildings and roads) and Internet-sourced text (reflecting historical, cultural, and narratives of neighborhoods).
arXiv Machine Learning
Jul 8
SHARC: SHAP-Based Interpretability in Machine Learning Risk Models for Regulatory Capital under ICAAP and CCAR
arXiv:2607. 05484v1 Announce Type: cross Abstract: The adoption of non-parametric machine learning models for regulatory capital estimation introduces a fundamental governance challenge: the inability to explain model outputs in a manner auditable by supervisory bodies.
arXiv AI
Jul 8
K-ABENA: K-Adaptive Backpropagation with Error-based N-exclusion Algorithm : (Compensated Loss-Based Sample Exclusion with Unbiased Gradient Estimation)
arXiv:2607. 05903v1 Announce Type: cross Abstract: We present K-ABENA (K-Adaptive Backpropagation with Error-based N-exclusion Algorithm), a selective gradient computation framework that reduces per-iteration training cost by excluding a fraction of low-loss ("minor") observations from the backward pass.