Search: “safety”

EU finds that Meta breached bloc’s rules with its social network interfaces

The European Union has tentatively found that Meta Platforms Inc. breached the bloc’s DSA tech industry law. The European Commission, the EU’s executive arm, published its conclusions today. The DSA,

safetysiliconangle

Safety

Expressivity and Statistical Trade-offs in Diffusion Policy Learning

DGX agent

arXiv:2607.07967v1 Announce Type: cross Abstract: Diffusion-based policies have recently emerged as powerful policy parameterizations for reinforcement learning, representing state-conditioned action

safetyarxiv-cs-lg

10 Jul 2026

Geometry-Aware Deep Congruence Networks for Manifold Learning in Cross-Subject Motor Imagery

arXiv:2511.18940v3 Announce Type: replace Abstract: Cross-subject motor imagery decoding remains a fundamental challenge in EEG-based brain-computer interfaces due to substantial inter-subject variabi

HairWeaver: Few-Shot Photorealistic Hair Motion Synthesis with Sim-to-Real Guided Video Diffusion

arXiv:2602.11117v2 Announce Type: replace Abstract: We present HairWeaver, a diffusion-based pipeline that animates a single human image with realistic and expressive hair dynamics. While existing met

HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

arXiv:2601.22448v2 Announce Type: replace-cross Abstract: RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cos

safetyarxiv-cs-cl

HSA: Hierarchical Slot Attention for Multi-granularity Scene-Decomposition

arXiv:2607.08249v1 Announce Type: new Abstract: Slot attention is a powerful framework for object-centric learning, decomposing visual scenes into latent slots through iterative competitive attention.

Improving RCT-Based Treatment Effect Estimation Under Covariate Mismatch via Calibrated Alignment

arXiv:2603.19186v3 Announce Type: replace Abstract: Randomized controlled trials (RCTs) are the gold standard for estimating treatment effects, yet they are often underpowered for detecting effect het

In a hotel room in northeast Nigeria, I opened a leading AI chatbot, turned my laptop toward a former Boko Haram commander, and asked if he'…

In a hotel room in northeast Nigeria, I opened a leading AI chatbot, turned my laptop toward a former Boko Haram commander, and asked if he'd used it. He nodded. 'You type in the question… like 'How c

Incredible work by Daniel and team! I agree with much of it. All 'uncontrolled' paths are extremely likely to end in human extinction. Plan …

Incredible work by Daniel and team! I agree with much of it. All 'uncontrolled' paths are extremely likely to end in human extinction. Plan A offers many good ideas for preventing ASI development whil

safetyconnor-leahy--x

Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition

arXiv:2607.08374v1 Announce Type: cross Abstract: Personality recognition has traditionally been constrained by theory-dependent formulations, where models are trained to fit predefined psychological

Latent Memory Palace: Reasoning for Control as Autoregressive Variational Inference

arXiv:2607.08724v1 Announce Type: new Abstract: Human decision-making is highly flexible -- some actions are taken immediately; others require longer deliberation. Language models have exhibited a sim

Learning Adaptive Solvers for Distributed Factor Graph Optimization on Matrix Lie Groups

arXiv:2607.08735v1 Announce Type: new Abstract: Modern robotic perception increasingly involves large-scale geometric optimization problems distributed across multiple robots or sessions. However, exi

LESV: Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding

arXiv:2604.01388v2 Announce Type: replace Abstract: Recent advancements in open-vocabulary 3D scene understanding heavily rely on 3D Gaussian Splatting (3DGS) to register vision-language features into

LiteOdyssey: A Lightweight Reasoning AI Agent for Interpretable Rare-Disease Diagnosis

arXiv:2606.16149v2 Announce Type: replace Abstract: Rare disease diagnosis involves interpreting clinical and genetic findings through complex diagnostic reasoning. We investigated whether this reason

LLT: Local Linear Transformer for PDE Operator Learning

arXiv:2607.07718v1 Announce Type: cross Abstract: Neural operators have become a common approach for learning PDE solution maps and accelerating numerical simulations. Transformer-based neural operato

LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models

arXiv:2607.08770v1 Announce Type: new Abstract: Recovering high-quality video from sparse event streams is a challenging task. Regression methods often blur textures, while existing generative models

LTM: Large-scale Terrain Model for Wildfire-prone Landscapes

arXiv:2607.08711v1 Announce Type: new Abstract: Accurate 3D terrain maps are essential for emergency response when assessing wildfire hazards. However, wildfire-prone regions often span vast areas whe

MatBind: A Shared Embedding Space for Multimodal Materials Characterization

arXiv:2607.08470v1 Announce Type: new Abstract: Fully characterizing a crystalline material requires integrating heterogeneous data sources -- atomic structures, diffraction patterns, electronic densi

Maybe @GaryMarcus is on to something…

Maybe @GaryMarcus is on to something… The Branching Dendrite Secret Behind Human Cognitive Superiority | Neuroscience News Summary: Researchers have discovered that the fundamental building blocks of

MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters

arXiv:2607.08257v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong performance on isolated psychiatric tasks, including dialogue, diagnosis, and treatment planning, yet exi

MPFlow: Learning Budgeted Max-Flow Optimization on the Lightning Network with Deep Graph Reinforcement Learning

arXiv:2607.08703v1 Announce Type: new Abstract: We address liquidity placement in the Bitcoin Lightning Network (LN): given a fixed budget, which channels should a node open to maximize its routing ca

Multi-Distribution Robust Conformal Prediction

arXiv:2601.02998v2 Announce Type: replace Abstract: In many fairness and distribution robustness problems, one has access to labeled data from multiple source distributions yet the test data may come

MultiFair: Multimodal Balanced Fairness-Aware Medical Classification with Dual-Level Gradient Modulation

arXiv:2510.07328v2 Announce Type: replace-cross Abstract: Medical decision systems increasingly rely on data from multiple sources to ensure reliable and unbiased diagnosis. However, existing multimod

Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

arXiv:2607.07907v1 Announce Type: cross Abstract: With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or

Native Video-Action Pretraining for Generalizable Robot Control

arXiv:2607.08639v1 Announce Type: cross Abstract: The advent of video-action models offers a promising path for robot control. Nevertheless, we argue that repurposing video generative models designed

NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL

arXiv:2607.07855v1 Announce Type: new Abstract: Hierarchical Implicit Q-Learning (HIQL), an offline goal-conditioned RL method, selects subgoals by value-function advantages alone. This rule has two c

One of the biggest threats to US innovation isn’t just research funding - it’s losing the next generation of scientists. Phd admissions at l…

One of the biggest threats to US innovation isn’t just research funding - it’s losing the next generation of scientists. Phd admissions at leading research universities fell 15% this year. Scientific

Open-ended Multi-agent Autocurricula via Visual Inspection of Policies with Multi-modal LLMs

arXiv:2607.08193v1 Announce Type: cross Abstract: Open-ended curricula in Reinforcement Learning (RL) aim to train generally-capable agents by identifying tasks that facilitate learning increasingly c

OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators

arXiv:2607.08766v1 Announce Type: new Abstract: We propose OPSD-V, an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models. Existing few-step AR v

PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided LLM

arXiv:2505.16456v3 Announce Type: replace Abstract: Recent advances in 3D content generation have amplified demand for dynamic models that are both visually realistic and physically consistent. Howeve

Physics-Guided Biomechanical Gait Adaptation for Humanoid Locomotion on Extreme Sloped Terrains

arXiv:2607.07830v1 Announce Type: new Abstract: Model-free reinforcement learning has enabled impressive humanoid locomotion; however, control on steep slopes remains largely unexplored. Unlike flat o

PLURAL: A Global Dataset for Value Alignment

arXiv:2607.08034v1 Announce Type: cross Abstract: Large language models (LLMs) are used worldwide, yet disproportionately reflect Western values, limiting their ability to represent diverse value syst

Prismata: Confining Cross-Site Prompt Injection in Web Agents

arXiv:2607.08147v1 Announce Type: cross Abstract: Autonomous web agents promise to automate everyday browsing tasks, but inherit one of the web's oldest attack surfaces. Cross-Site Scripting proved th

reminds me of the time Greg Brockman personally downloaded YouTube videos for training purposes, as reported in NYT.

reminds me of the time Greg Brockman personally downloaded YouTube videos for training purposes, as reported in NYT. 🦔Apple is suing OpenAI for systematic trade secret theft weeks before the IPO. The

SASGeo: Stability-Aware Semantic Map Localization for GNSS-Denied UAVs -- A Framework and Synthetic Proof of Concept

arXiv:2607.07737v1 Announce Type: cross Abstract: GNSS-denied unmanned aerial vehicles require occasional absolute position fixes to bound the drift of visual-inertial odometry. Cross-view image retri

Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration

arXiv:2607.07895v1 Announce Type: new Abstract: Research on stereotypes in large language models (LLMs) has largely focused on English-speaking contexts, due to the lack of datasets in other languages

safetyarxiv-cs-cl

SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment

arXiv:2511.08583v2 Announce Type: replace-cross Abstract: Developing efficient and accurate visuomotor policies poses a central challenge in robotic imitation learning. While recent rectified flow app

SkillPlug: Unsupervised Skill Mining for Few-Shot Adaptation in Robotic Manipulation

arXiv:2607.08354v1 Announce Type: new Abstract: Learning transferable visuomotor imitation policies that generalize across diverse manipulation tasks and adapt rapidly to new tasks from only a handful

Soft Robotic Exogloves for Dexterous Mobility -- Towards Personalized Rehabilitation

arXiv:2607.07968v1 Announce Type: new Abstract: Soft robotic exogloves can provide hand rehabilitation and assistance. Fitting these gloves often relies on standardized measurements not tailored to th

Spatio-Temporal Scheduling Prediction Under Backhaul Delay for Resilient Coordinated Beamforming

arXiv:2607.08454v1 Announce Type: cross Abstract: Coordinated beamforming in distributed 5G networks relies on the timely exchange of inter-cell scheduling information, but backhaul latency makes this

SPHINX: First Explain, Then Explore

arXiv:2606.17482v2 Announce Type: replace Abstract: Generating adversarial driving scenarios is critical for evaluating and improving autonomous vehicle decision-making systems in simulation. Recent a

Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning

arXiv:2607.08444v1 Announce Type: cross Abstract: In this paper, we study quantile-based distributional reinforcement learning from the perspective of statistical efficiency. We focus on distributiona

Texture Representations in Deep Vision Models: Comparing CNNs, Vision Transformers, and Human Perception

arXiv:2607.08321v1 Announce Type: new Abstract: In computational vision science, Convolutional Neural Networks (CNNs) have emerged as a popular model of biological vision because of the alignment they

The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis

arXiv:2408.02379v2 Announce Type: replace-cross Abstract: Developing and certifying safe - or so-called trustworthy - AI has become an increasingly salient issue, especially in light of upcoming regul

Trustworthy Machine Learning through the Lens of Combinatorial Optimization: Survey and Research Perspectives

arXiv:2607.07762v1 Announce Type: new Abstract: Modern machine learning (ML) increasingly relies on complex models whose behavior is difficult to characterize beyond empirical performance metrics. Acr

Two Axes of LLM Abstention: Answer Correctness and Question Answerability

arXiv:2607.08456v1 Announce Type: cross Abstract: A model should refuse two different things: answers it would get wrong, and questions it should not answer at all, such as unanswerable ones or ones r

UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing

arXiv:2607.08646v1 Announce Type: cross Abstract: As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish. Consequently, improving Large Language Model

Unified Face Attack Detection via Fine-Grained Semantic Guidance

arXiv:2607.08156v1 Announce Type: new Abstract: The growing applications of facial recognition systems are accompanied by increasingly diverse security threats. Existing datasets lack detailed textual