127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “evaluation”

39,611 results

Research

surprisal is Not a Theory

DGX agent

arXiv:2607.20208v1 Announce Type: new Abstract: Surprisal Theory is often characterized as a computational-level explanation per (Marr, 1982). We argue in this work that, even though a computational l

researcharxiv-cs-cl

23 Jul 2026

Research

Surprise Forcing: What to Remember, When to Skip in Long Video Generation

DGX agent

arXiv:2607.18436v1 Announce Type: new Abstract: Streaming autoregressive diffusion makes minute-scale video synthesis practical, but its bounded context and fixed denoising schedule allocate resources

Search: “evaluation”

surprisal is Not a Theory

Surprise Forcing: What to Remember, When to Skip in Long Video Generation

SynPre-FL: Synthetic data-driven pretraining integrated Federated Learning training framework

Test-Time Training for Modality Order Consistency in Vision-Language Models

Text-conditioned Segmentation for Tomato Phenotyping via Procedural Synthetic Data

The Maskability Index: Predicting Task-Objective Alignment in Pretrained Language Models

The PAR dataset: Prostate biopsy whole slide images from an underrepresented Middle Eastern population

Think Sparse, Predict Dense: Continuous Thought Machines for Image Super-Resolution

Time Series Network Utilization KPI Forecasting Using Advanced AI/ML Models

Total Variation Distance Estimation in Autoregressive Models

Toward Seasonal Guidelines for Robust Deep-Learning Sentinel-2 Building Detection in Different Area Types

Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations

TRUST-ESD: A Risk-Calibrated and Governance-Aware AI Framework for Enterprise Strategic Decision Support Under Uncertainty

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI

Trustworthy Privacy-Preserving Multimodal Federated Learning for Personalised Breast Cancer Prediction

Twin Agent: Context Residual Compression for Privilege Separated Agents

Two-Step Occupation Coding

Understanding Developer Pain Points in Federated Learning: Insights from Stack Overflow and GitHub

Unified Prediction and Planning via Conflict-Aware Disjoint Parameter Training

VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers

When Does Consensus Beat Voting? A Critical Analysis of Statistical Label Fusion in Medical Image Segmentation

When Does Knowledge Distillation Hurt? Reliability-Aware Distillation for Low-Resource Language Summarization

When Reasoning Narrows the Move: Diversity Collapse in LLM Game Play

When Visual Evidence is Ambiguous: Pareidolia as a Diagnostic Probe for Vision Models

WHU-PCPR: A cross-platform heterogeneous point cloud dataset for place recognition in complex urban scenes

Zero-Observation User Reactivation with Gap-Driven Dimensional Gating

Zero-Shot Heart Rate Variability Forecasting from Consumer Wearables Using Time Series Foundation Models

ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting

A 3DGS-Driven Dynamic Viewpoint and Vibrotactile Framework for Subsea Teleoperation Validated via fNIRS

A Generalised Exponentiated Gradient Approach to Enhance Fairness in Binary and Multi-class Classification Tasks

A Hybrid Sampling-Based Trajectory Planner with Game-Theoretic Guidance for Autonomous Racing

A Masked Autoencoder Approach to Unsupervised Steel Surface Defect Recognition

Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains

Adaptive Conformal Inference through the Lens of Blackwell Approachability

Adversarial Prompting Framework for AI Safety Assessment

An Explainable Agentic System for Detection of Conversational Scams with Summary-Based Memory

Anatomically Faithful but Temporally Blind: Auditing Attribution for Left-Ventricular Ejection-Fraction Estimation from Echocardiography

Anatomy of Uncertainty: Expressive Descriptors of Robotic Manipulator Motion for Non-verbal Communication in Human-Robot Collaboration

Beyond Backbone Backpropagation: A Decoupled Strategy for Efficient Transfer Learning

BiLoG-Net: A Bi-Context Location-Guided Network for Breast Mass Segmentation and Malignancy Classification in Mammography

Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation

CDS: Counterfactual Directionality Score for Structured Interventions in Spatial Graphs

CLIP-Guided Label-Free Discriminative Region Scoring for Fine-Grained Classification

CoDiffGRN: Rethinking Gene Regulatory Network Inference via the BEELINE-KGC Benchmark and Co-evolutionary Discrete Diffusion

COLMAR: Cooperative View Policy Learning for Multi-Agent Active 3D Reconstruction

Compaction as Epistemic Failure: How Agentic LLM Tools Fabricate Confirmed Results from Killed Processes

Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes

Deformable State Estimation for Autonomous Surgical Tissue Retraction Under Partial Observability