Topic Clusters

Human-level control through deep reinforcement learning

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

Playing Atari with Deep Reinforcement Learning

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

The Condensate Theorem: Transformers are O(n), Not $O(n^2)$

NEXUS: Bit-Exact ANN-to-SNN Equivalence via Neuromorphic Gate Circuits with Surrogate-Free Training

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

MobileFetalCLIP: Selective Repulsive Knowledge Distillation for Mobile Fetal Ultrasound Analysis

Natural Language-Driven Global Mapping of Martian Landforms

TFFM: Topology-Aware Feature Fusion Module via Latent Graph Reasoning for Retinal Vessel Segmentation

PIMPC-GNN: Physics-Informed Multi-Phase Consensus Learning for Enhancing Imbalanced Node Classification in Graph Neural Networks

FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding

WarpRec: Unifying Academic Rigor and Industrial Scale for Responsible, Reproducible, and Efficient Recommendation

FMPose3D: monocular 3D pose estimation via flow matching

LTX-2: Efficient Joint Audio-Visual Foundation Model

F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World

Learning from Yesterday's Error: An Efficient Online Learning Method for Traffic Demand Prediction

Meeting SLOs, Slashing Hours: Automated Enterprise LLM Optimization with OptiKIT

SynthRender and IRIS: Open-Source Framework and Dataset for Bidirectional Sim-Real Transfer in Industrial Object Perception

A Pragmatic VLA Foundation Model

Efficient Hierarchical Any-Angle Path Planning on Multi-Resolution 3D Grids

XMorph: Explainable Brain Tumor Analysis Via LLM-Assisted Hybrid Deep Intelligence

3DLAND: 3D Lesion Abdominal Anomaly Localization Dataset

PMPBench: A Paired Multi-Modal Pan-Cancer Benchmark for Medical Image Synthesis

From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems

The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety

UniSAFE: A Comprehensive Benchmark for Safety Evaluation of Unified Multimodal Models

StructXLIP: Enhancing Vision-language Models with Multimodal Structural Cues

DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset

VILLAIN at AVerImaTeC: Verifying Image-Text Claims via Multi-Agent Collaboration