127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

safety

19,755 results

Safety

congrats @yudapearl!

DGX agent

congrats @yudapearl! Judea Pearl Named AI Pioneer by Boston Global Forum in Honor of America’s 250th Anniversary https://samueli.ucla.edu/judea-pearl-named-ai-pioneer-by-boston-global-forum-in-honor-o

safetygary-marcus--x

2 Jul 2026

Safety

'consensus' can't just built by big tech! let's all be careful of regulatory capture and extreme concentration of power!

DGX agent

safety

congrats @yudapearl!

'consensus' can't just built by big tech! let's all be careful of regulatory capture and extreme concentration of power!

Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction

Continuous Speculative Decoding for Autoregressive Image Generation

Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection

Decentralized Geometric Control for Cable-Suspended Payload Transport with Adaptive Mass Estimation

Diffusion-GR2: Diffusion Generative Reasoning Re-ranker

Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation

Distributed Multi Robot Lunar Cargo Transportation via Phase Decomposed Reinforcement Learning

Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts

Dual-Informed Vertical Expansion for Multi-Objective Node Selection in Anytime Conflict-Based Search

ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation

ELMP: Efficient Learning for Motion Planning via Analytical Policy Gradients

Emails disclosed in a court filing detail the uneasy back-and-forth between Dario Amodei and DOD's Emil Michael and how Anthropic's relationship with DOD soured (Wall Street Journal)

Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms

EPO: Boosting 3D Foundation Models with Edge-based Pose Optimization

EquiSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation

Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles

Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflows

FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement

FastBridge: Closing the Model-Based Realization Gap in Safety Filters on 3D Gaussian Splatting for Fast Quadrotor Flight

ForAug: Mitigating Biases in Image Classification via Controlled Image Compositions

FrameONE: Hierarchical Motion Modeling for Universal Multi-View Echocardiographic Keyframe Detection

From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape

From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training

From Prediction Uncertainty to Conformalized Distance Fields for Safe Motion Planning

From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning

From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems

From World Models to World Action Models: A Concise Tutorial for Robotics

Gauging, Measuring, and Controlling Critic Complexity in Actor-Critic Reinforcement Learning

GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception

Google’s Continued Disruption of Malicious Residential Proxy Networks

Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination

GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity

HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment

How Environment and Urbanization Shape Bird Diversity in Sri Lanka

HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding

Identifying Latent Concepts and Structures for Generalized Category Discovery

in case you needed more evidence that tokenmaxxing was a stupid idea

KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills

Learning Category-level Last-meter Navigation from RGB Demonstrations of a Single-instance

Learning Expert Strategy for Autonomous Robotic Endovascular Intervention via Decoupled Procedural Execution

Learning from Demonstration via Spatiotemporal Tubes for Unknown Euler-Lagrange Systems

Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications

Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL

Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory

LIST3R: Long-sequence Instance-aware 3D Reconstruction

Managed Autonomy at Runtime: Gear-Based Safety and Governance for Single- and Multi-Agent Cyber-Physical Systems