127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “safety”

22,392 results

Safety

WorldSonus: Bringing Sound to Worlds

DGX agent

arXiv:2610.08760v1 Announce Type: cross Abstract: Recent advances in world models have enabled increasingly realistic visual synthesis. However, these generated environments remain largely silent. Bri

safetyarxiv-cs-ai

7 Oct 2026

Safety

Search: “safety”

WorldSonus: Bringing Sound to Worlds

yep, this, too, like a bunch of other similar tweets, is typical of the cluelessness of people who literarily don’t understand the differenc…

A Statistical Inference Framework for PMI Estimation and SGNS Word Embeddings

A Unified Dynamics Framework for Reinforcement Learning and Classical Control of a Six-DOF Pipeline-Tracking ROV in NVIDIA Isaac Sim

Adaptive Bregman Alternating Projections for Feasible Gromov-Wasserstein Learning

Agentic Resource Allocation for Batch Multi-Objective Bayesian Optimization in Autonomous Materials Discovery

AID: A Framework for AI Infrastructure Dynamics

Aligning Multimodal Patient Evidence with Biomedical Knowledge Graphs for Clinical LLMs

Amortized Score-Hamiltonian Policy Iteration: A Grid-Free Scheme for Relaxed Stochastic Control Problems

An evolutionary origin of collective decision making in humans and machines

An LLM-in-the-loop RL Framework for Bioinformatics Feature Selection

Anatomy-aware Fine-grained Multimodal Fusion for Laryngopharyngeal Cancer T-Staging Prediction Using CT and Radiology Report

Articulatory Entrainment and Coordination Complexity in Spontaneous Autistic and Non-autistic Dialogue

ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience

Asking the Crowd the Right Question: Bias-Cancelling Weights for Federated Learning

Benchmarking CLIP for Zero-Shot Face and Periocular Gender Estimation

Best-of-N Guidance for Test-time Diffusion Alignment

Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models

Beyond Token Accuracy: Prioritizing What Matters for Visual Reconstruction

Bilinear Flow Policy: Distributional Extrapolation for Goal-Conditioned Visuomotor Imitation

Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning

Build a voice travel concierge with Amazon Bedrock AgentCore, Managed Knowledge Base and Nova Sonic

CACFG: Curvature-Aware Classifier-Free Guidance and Optimal Control

Causally Fair Generation with Large Language Models

CEENs: Causality-enforced evolutional networks for solving time-dependent partial differential equations

ClasSAE: Class-Aligned Sparse Autoencoders via Differentiable Feature-Class Affinity

Climate Surrogates for Scalable Multi-Agent Reinforcement Learning: A Case Study with CICERO-SCM

Collaborative Personalized Preference Alignment for LLMs under Data Deficiency

Conditional Trajectory Peaks: Single-Pass Multimodal Policies over Action Chunks

ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution

Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification

Considering Context: When World Models Need Context Encoders

Continual Humanoid Motion Learning

Contrastive Time Series Forecasting with Anomalies

Cross-Time Directional Selection in Diffusion Sampling

CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery

Dataset-Free Compliant Humanoid Loco-Manipulation with Dynamic Online Posture

Decouple, Purify and Unite: Semantic-Structural Prototype Learning for Federated Medical Segmentation

Deep Fair Learning: Task-Aware Fair Representations via Joint Distance-Covariance Regularization

DeepStock: Reinforcement Learning with Policy Regularizations for Inventory Management

Demonstration-Calibrated Port-Hamiltonian Retuning for Manipulation Policies

DeNoise: Learning Robust Graph Representations for Unsupervised Graph-Level Anomaly Detection

Direction-Conditioned Policies for Online Goal-Conditioned Reinforcement Learning

Disambiguate Gripper State in Grasp-Based Tasks: Pseudo-Tactile as Feedback Enables Pure Simulation Learning

Dissecting Quantization Error: A Concentration-Alignment Perspective

Distributionally Robust Deep Q-Learning

Do VLAs Understand and Adapt to the Objects They Handle, or Simply Replay Learned Behaviors?

Dual Variational Autoencoders for Efficient Sim-to-Real Transfer in Low-Cost Robotic Navigation