Bounded knowledge map

Recent connections

Explicit wiki links among recent Safety entries.

90 nodes · 2 links. The server bounds this neighbourhood, so the browser never downloads or simulates the complete wiki graph.

Search nodesMinimum links 0Zoom 100%

90 nodes · 2 links shown. Hover or focus to isolate neighbours; select a node to open its source entry.

Linked entries

2 shown

Learning to Report Unsafe Tasks in a Multi-Agent Game→SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning

MORAD: Reinforcement Learning with Multi-Objective Rewards for RNA Inverse Design→DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models

Safety

90 shown

DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models1 SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning1 Learning to Report Unsafe Tasks in a Multi-Agent Game1 MORAD: Reinforcement Learning with Multi-Objective Rewards for RNA Inverse Design1 Evo-World: A Lightweight Vision-Language-Action Model with Future Motion Prediction via Optical-Flow Supervision Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems Tracing and Taming Hallucinated Terms via Subsequence-Association Filtering and Breadth-Aware Selection for LLM Query Expansion Personalized Federated Direct Preference Optimization via LoRA Adapters Sure does look like @GavinSBaker is “suggesting that public companies are materially inflating their remaining performance obligations”. yet…Non-Prehensile Multi-Object Placement with Mobile Robots via Diffusion-Based Trajectory Planning HorizonNav: Geometry-Guided Video Diffusion for Anticipatory 3D Robot Navigation Rethinking Relative Policy Differences Transfer of On-Policy Distillation Evidence-Guided Counterfactual Learning for Long-Tailed Robotic Policies Matched-Context Group Policy Optimization for LLM Agent Training ReAT: Residual Action Tokenization for Autoregressive Robot Policies SharP: Soft and Hard Prompt-Guided Augmentation with LLM for Low Resource Fake News Detection Evidential Multimodal Transformers with Dempster-Shafer Fusion for Emotion Recognition Variance-Reduced Policy Gradient is Nearly Minimax-Optimal RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits Collaborative Theory of Mind: Learning to Self-Revise by Anticipating User Responses Vision Transformers Learn Word Meaning from Images Alone Opening the Black Box of Classifier-Free Guidance via Information Bottleneck EndoRSI: Physical-Evidence-Driven Recursive Improvement of Endoscopic Robot Policies Reflex: Visually Grounded Reactive Humanoid Control Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation Universal Bounds for Self-Normalized Kullback-Leibler Estimation Branching On-Policy Distillation When MLLMs miss what humans read: diagnosing and learning to read squint text RESCUE: Is This Alarm Worth Acting On? Counterfactual Evaluation of VLA Runtime Monitors SOAR: Source-Aware Reinforcement Learning with Precise Credit Assignment for Search Agents Can Language Models Learn When to Abstain? Policy Learning and Calibrated Answer Selection Why Linear Models Can Still Work in a Complex and Changing World What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training Reflect-VLA: Internalizing Reflective Guidance via Dual-Path On-Policy Self-Distillation for Autonomous Driving TAME-Nav: Temporal Asymmetric Mixture-of-Experts Distillation for Agile and Versatile Robot Navigation Noise Space Learning for VLA Adaptation LAPT-Scale: Scaling Embodied Policies with Latent Action Pre-Training on Human Videos CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual-Textual Alignment for QA-Style Radiology Report Generation The Predictability Bias of Joint-Embedding Predictive Learning in Medical Imaging CopRoute: Dependence-Aware Conformal Routing for Language Models Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation A Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPO Proactive Agentic Orchestration L_0 Feature Selection via Monte Carlo Tree Search in High-Dimensional Financial Regression Learning to accelerate Krasnosel'skii-Mann fixed-point iterations with guarantees Towards Understanding the Training of GFlowNets: A Theoretical Perspective Beyond Successful Robot Demonstrations: Learning from Human Interactions and Modeling Failure Dynamics ATHLETE: Learning Reactive Humanoid Tennis via Trajectory-Guided Motion Matching UniConFlow: A Unified Constrained Flow-Matching Framework for Certified Motion Planning SAP-CoPE: Social-Aware Planning using Cooperative Pose Estimation with Infrastructure Sensor Nodes Equality, Equity, and Causality in Fairness Research: A Commentary on Cheng (2026)Goal-Oriented Bundle Management and Flow Control for Deep-Space Communications via Reinforcement Learning DeFiRank: Federated Pairwise Ranking for Governance in Decentralized Financial Networks Hyper Algorithm Design Agent: Evolving Learnable Optimizer from Zero Learning Schwarzschild Geodesic Motion with Lagrangian Neural Networks The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs Mind the Temporal Gap: Evaluating Video Models for Temporal Understanding in Driving Dual-Stream Memory for Vision-Language-Action Policies Representation Alignment from a Few Paired Data via Distilled Optimal Transport CV-OPD: Contrastive Vision On-policy Distillation ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios StereoEngine: Scaling Stereo Bimanual Robot Data without Stereo Cameras State-OPD: State-Grounded On-Policy Distillation for Multi-Turn Agents Splat2Act: From Captured Scenes to Personalized VLA Manipulation Agreement Without Alignment: Label-Free Rubric Clarification Increases LLM-Judge Consensus but Not Agreement with Humans VLMs are Native Action Models: Unleashing the Manipulation Capabilities of VLMs with Explicit Action-Space Grounding Randomized Momentum Transport with Cheap Predictors KITE: A Knowledge-Injected Temporal Encoder for Time-Series Event Forecasting Recover, Discover, Plan: Learning Skills and Concepts from Robot Failures Visual-Wi-Fi Navigation to Signal-Emitting Devices OpenPA: Forced-alignment-free Multi-granular Pronunciation Assessment with Mixed-transcript Adaptation REMM: Revisable Embodied Memory for Manipulation CLEAT: Learning Value-Guided Clarification for Interactive Agents Introducing RSI-Anything: Unlocking Recursive Self-Improvement with World Models 🚀 Can AI learn to improve itself by predicting the consequ…Hidden Data Challenges in Clinical Machine Learning LeWAM: End-to-End World and Action Modeling with JEPAs AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation PanTact: Teaching Whole-Body Dexterity with a Wearable Contact Interface MotionCoach: Constructing Multimodal Guidance for Video Professional Motion Editing DistressBench: Evaluating Multi-Dimensional Crisis Support in Large Language Models Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence X-AVDD: Cross-Attentive Audio-Visual Dataset Distillation VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails Grounded-Dreamer: Robot Learning from World Model Synthetic Data with Physical Grounding Tracking the Invisible: Self-Supervised Wheel Track Detection with Thermal-RGB Fusion JoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied Agents Playing the network backward: A Game Theoretic Attribution Framework Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization