127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

safety

19,755 results

Safety

Alignment-Aware Decoding

DGX agent

arXiv:2509.26169v2 Announce Type: replace Abstract: Alignment of large language models remains a central challenge in natural language processing. Preference optimization has emerged as a popular and

safetyarxiv-cs-lg

3 Jun 2026

Safety

an astonishing statistic, consistent with the claim I made the other day that Elon’s best days may be behind him:

DGX agent

safety

Alignment-Aware Decoding

an astonishing statistic, consistent with the claim I made the other day that Elon’s best days may be behind him:

Are we really tilting? The mechanics of reward guidance in flow and diffusion models

ASAP: Exploiting the Satisficing Generalization Edge in Neural Combinatorial Optimization

Assessing Region-Level EEG Contributions to Cognitive Workload Prediction

ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information

Attention Calibration for Position-Fair Dense Information Retrieval

Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs

Bayesian Tensor Decomposition with Diffusion Model Prior

Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching

Bionic Human-Motion Style Transfer for Physically Executable Whole-Body Control of Humanoid Robots

Black-box, Adaptive, Efficient, Transferable, Harmful, Applicable... Attacks Are All You Need to Break LLMs

Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL

Bridging Predictive Uncertainty and Safe Action: Sample-Conditioned Differentiable Planning for Autonomous Driving

Brief Announcement: Generative Markov Model for Distributed Computing Systems

Building Better Activation Oracles

Coherence Maximization Improves Pluralistic Alignment

Collab-REC: An LLM-based Agentic Framework for Balancing Recommendations in Tourism

Consistency Training Can Entrench Misalignment

Constitutional On-Policy Safe Distillation

ConTrack: Constrained Hand Motion Tracking with Adaptive Trade-off Control

ConTraIRL: Factorized Contrastive Abstractions for Transferable IRL

Contrastive Neural Algorithmic Reasoning for Graph Coloring

Correcting Neural Operator Spectral Bias via Diffusion Posterior Sampling with Sparse Observations

CP-Agent: Context-Aware Multimodal Reasoning for Cellular Morphological Profiling under Chemical Perturbations

Curriculum-Adapted Robust Reinforcement Learning for UAV Deconfliction in Adversarial Environments

D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting

Data- and Variance-dependent Regret Bounds for Online Tabular MDPs

Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering

Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies

Discovering autonomous quantum error correction via deep reinforcement learning

Do Explanations Increase the Risk of Decision Logic Leakage? Explanation-Guided Stealing of Graph Models

Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors

DriftSched: Adaptive QoS-Aware Scheduling under Runtime Token Drift for Multi-Tenant GPU Inference

Dynamic Short Convolutions Improve Transformers

Easy-to-Use Shielding for Reinforcement Learning

Effect of Demographic Bias on Skin Lesion Classification

Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis

Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection

Estimating Bidirectional Causal Effects with Large Scale Online Kernel Learning

Evaluating Transformer and LSTM Frameworks for Prediction in Ungauged Basins

Every action that I partake is animated by two ideals: Truth and freedom. Seeing the endless attacks on both ideals throughout the West is s…

EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation

Explainable Forecasting of Scientific Breakthroughs from Concept Network Dynamics

Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models

Extreme Motion Generation via Hybrid Null-Space Control for Straight-Line Path Following

FAF-CD: Frequency-Aware Fusion for Change Detection under Imperfect Multimodal Remote Sensing

Fairness Definitions and Metrics in Deep Reinforcement Learning for Drug Discovery in Healthcare: A Rapid Evidence Review