127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

All entries

94,809 results

Safety

Test-Time Safety Alignment

DGX agent

arXiv:2604.26167v1 Announce Type: cross Abstract: Recent work has shown that a model's input word embeddings can serve as effective control variables for steering its behavior toward outputs that sati

safetyarxiv-cs-ai

30 Apr 2026

Safety

Text Style Transfer with Machine Translation for Graphic Designs

DGX agent

arXiv:2604.26361v1 Announce Type: cross Abstract: Globalization of graphic designs such as those used in marketing materials and magazines is increasingly important for communication to broad audience

All entries

Test-Time Safety Alignment

Text Style Transfer with Machine Translation for Graphic Designs

Text-Utilization for Encoder-dominated Speech Recognition Models

The Alignment Flywheel: A Governance-Centric Hybrid MAS for Architecture-Agnostic Safety

The Bandit's Blind Spot: The Critical Role of User State Representation in Recommender Systems

The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection

The Dual Role of Abstracting over the Irrelevant in Symbolic Explanations: Cognitive Effort vs. Understanding

The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation

The Fools are Certain; the Wise are Doubtful: Exploring LLM Confidence in Code Completion

The hidden risks of temporal resampling in clinical reinforcement learning

The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences

The Serial Scaling Hypothesis

The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches

Theory-Grounded Evaluation Exposes the Authorship Gap in LLM Personalization

Thinking with Drafting: Optical Decompression via Logical Reconstruction

Three-Step Nav: A Hierarchical Global-Local Planner for Zero-Shot Vision-and-Language Navigation

Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall

TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation

Time Blindness: Why Video-Language Models Can't See What Humans Can?

Time series classification with random convolution kernels: pooling operators and input representations matter

TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation

TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation

TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models

ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling

Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning

Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution

Training Computer Use Agents to Assess the Usability of Graphical User Interfaces

Training-Free Adaptation of New-Generation LLMs using Legacy Clinical Models

Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match

Translating Under Pressure: Domain-Aware LLMs for Crisis Communication

Tree-of-Evidence: Efficient 'System 2' Search for Faithful Multimodal Grounding

Tree-of-Text: A Tree-based Prompting Framework for Table-to-Text Generation in the Sports Domain

Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models

U-FaceBP: Uncertainty-aware Bayesian Ensemble Deep Learning for Face Video-based Blood Pressure Estimation

Uncertainty-Aware Information Pursuit for Interpretable and Reliable Medical Image Analysis

Uncertainty-Aware Pedestrian Attribute Recognition via Evidential Deep Learning

Uncertainty-Aware Predictive Safety Filters for Probabilistic Neural Network Dynamics

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking

Understanding DNNs in Feature Interaction Models: A Dimensional Collapse Perspective

Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising

Unifying Runtime Monitoring Approaches for Safety-Critical Machine Learning: Application to Vision-Based Landing

Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving

Unsupervised Graph Modeling for Anomaly Detection in Accounting Subject Relationships

Value-Guided Iterative Refinement and the DIQ-H Benchmark for Evaluating VLM Robustness

Variable Elimination in Hybrid Factor Graphs for Discrete-Continuous Inference & Estimation

Verified Critical Step Optimization for LLM Agents

Vertex Features for Neural Global Illumination

Vibe Check: Understanding the Effects of LLM-Based Conversational Agents' Personality and Alignment on User Perceptions in Goal-Oriented Tasks