127,652Total entries

60Added by human

127,592Found by agent

13Categories

Knowledge catalogue

Search: “index”

2,770 results

Research

Dice Loss for Data-imbalanced NLP Tasks

DGX agent

arXiv:1911.02855v5 Announce Type: replace Abstract: Many NLP tasks such as tagging and machine reading comprehension are faced with the severe data imbalance issue: negative examples significantly out

researcharxiv-cs-cl

30 Jul 2026

Model Releases

Under the Hood: Serving Kimi K3

DGX agent

DigitalOcean launched Kimi K3 on day 0. It’s already one of the most popular models on the platform and across the market: second most likes on Hugging Face, sixth most traffic on OpenCode. Getting a

Search: “index”

Dice Loss for Data-imbalanced NLP Tasks

Under the Hood: Serving Kimi K3

Weight and Height Estimation from a Single Human Image Captured in the Wild

WikiLoop: Jointly Learning to Build and Navigate Agent-Native Wikis with Downstream Feedback

A Physics-Informed Neural Operator for Thermal Ranking of Low-Cost Wall Materials in Hot-Dry Climates

AI-Assisted Knowledge Access for Legacy Enterprise Asset Management in Energy Operations: A Practical Retrieval System

Beyond Counts: A Distributional Robustness Margin For Pathology Foundation Models

FlashEvaluator: Expanding Search Space with Parallel Sequence-Level Evaluation

Generator-Aligned Representation Interfaces for Diagnostic Soft Equivariance

Inspect India Evals: An Open Benchmarking Framework for Evaluating Large Language Models in the Indian Linguistic and Cultural Context

LLM Scheming Inversely Scales with Pretraining Language Coverage

Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation

Operational evaluation of data-driven forest fire forecasting models

OrganLens: Organ-Specific Representation Learning for CT Foundation Models

Physics-Informed CNN-LSTM for Street-Scale Urban Flood Prediction: Reconciling Aggregate Accuracy and Street-Level Plausibility

Quantum Speedups for Stochastic Optimization with Heavy-Tailed Noise

Reading Without a Reader: Large Language Models Collapse Reading and Writing into a Single Entangled Code

The borderless Lakehouse: Bring AWS, Databricks and Snowflake data to your AI agents

Three Sides of Retrieval: Factorial Evidence for Document-Side, Query-Side, and Answer-Side Complementarity in RAG

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents

When Does Deep Representation Learning Help Single-Cell Clustering? A Sensitivity-Aware Diagnostic Benchmark for Biomedical AI Pipelines

A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference

A note on the motion representation and configuration update in time stepping schemes for the constrained rigid body

Choosing a Text Embedding Model: A Practical Benchmarking and Decision Framework

Closing the Loop in Humanoid VLA: Persistent 3D Object Tokens for Verifiable Loco-Manipulation

Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV

Deep learning approaches show promise for predicting childhood malnutrition: A comparative study with traditional machine learning methods using survey data

Discrepancy-Rounded Fair Bandits with Static and Time-Varying Exposure Floors

Energy Constrained Hierarchical Underwater Monitoring via Local Multi-Agent RAG

Impute On-Demand: Adaptive Correlated Time Series Imputation for Changing Environments

INSIGHT: Spatially resolved survival modelling from routine histology crosslinked with molecular profiling reveals prognostic epithelial-immune axes in stage II/III colorectal cancer

Language-Routed RAG and Direct Option Scoring for Multilingual Financial QA: DS@GT at FinMMEval

Lexical discovery in unknown environments orchestrated by Large Language Models

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Low-light Image Enhancement via Multi-scale Attention combined with Fourier Transform

Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration

Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding

ParBench: A Benchmark for Reliable Evaluation of LLM Parallel Code Translation

Reasoning or Memorization: Can LLMs Understand and Generate Chinese Xiehouyu Riddles?

Robustifying pathology foundation models via fine-tuning

Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations

Schema-Aware Localisation (SAL): Live Schema Grounding and Hallucination Validation for Oracle NL2SQL

Scoping Review of AI, Metrology, and ESG in the Semiconductor Sector: Implications for Safe and Sustainable by Design (SSbD)

SF-AMS: Strategic Forgetting for Structured Memory in LLM Agent

SHReg: Strictly Rotation-Equivariant Point Cloud Registration via Spherical Harmonics

Since launching Qwen3.8-Max-Preview, we've received valuable feedback from developers! To help users better explore Qwen3.8's agentic capabi…

StageGuard: Physiologically Constrained Sleep Staging

Synthetic Scenario Generation for Evaluation of Industry 4.0 Agents