AI Research Papers
Explore the latest research papers from arXiv in artificial intelligence, machine learning, and related fields. Discover cutting-edge research from top institutions and researchers worldwide. Total: 27748 papers
OceanCoder: A Verification-Guided Large Language Model for Automated Simulation Modelling in Ocean Engineering
Nov 19, 2026
6 authors
cs.LGcs.SE
Online Temporal Rotations for 2 Bit KV-Cache Quantization in Video Diffusion Transformers
Nov 19, 2026
3 authors
cs.CVcs.AI
One Framework to Diagnose Them All: A Stratified Benchmark for Bengali LLM Hallucination
Nov 19, 2026
19 authors
cs.CLcs.AI
Sirius-Tiamat: How Small Can a One-Pass Decision Encoder Get Before Its Decisions Change?
Nov 19, 2026
2 authors
cs.AI
DeepQuest: From Knowledge Gaps to Scientific Discovery in Alzheimer's Disease
Nov 19, 2026
9 authors
cs.AI
OffBeat: Multicoset Sampling for 4D Capture Beyond the Camera Frame Rate
Nov 19, 2026
5 authors
cs.CVeess.IV
Perfumer: A Large Language Model-based Agentic Framework Accelerating Structural Relaxation and Electronic Band Prediction for First-Principle Calculation
Nov 19, 2026
7 authors
cond-mat.mtrl-scics.LG
TRCF: Temporal-Reference Complementary Forecasting for Irregular Multivariate Time Series
Nov 19, 2026
5 authors
cs.LG
Mamba Flow Matching Neural Processes: Linear-Time Inference for Irregularly Observed Spatial Fields
Nov 19, 2026
5 authors
cs.LG
How Much Should an Agent Remember? Deployment Lessons from Self-Distilled Memory for LLM Agents
Nov 19, 2026
9 authors
cs.AI
Contactless Estimation of Respiratory Frequency Using 3D-CNN on Thermal Images
Nov 19, 2026
6 authors
cs.CV
From Benchmarks to the Bench: Preference, Correspondence and Selectivity in Bidirectional Drug-Target Screening
Nov 19, 2026
3 authors
cs.LG
EgoCaptioner: Towards Comprehensive and Fine-Grained Egocentric Video Captioning
Nov 19, 2026
17 authors
cs.CV
Evidence from a Multi-Regime Causal Discovery Benchmark: UCMT Algorithms, Comparative Performance, and Controlled Ablation Studies
Nov 19, 2026
1 authors
cs.LG
SEEC: A Large-Scale Dataset and Benchmark for Self-Supervised External-Eye Representation Learning
Nov 19, 2026
9 authors
cs.CV
Simulation-pretrained autoencoders versus PCA for compressing multimode fibre transmission matrices
Nov 19, 2026
6 authors
physics.opticscs.LG
Democratizing Cross-Project Knowledge for Transforming Water Governance and Climate Resilience: an Agentic AI Ecosystem
Nov 19, 2026
4 authors
cs.IRcs.AIcs.CL
TacInno: Teaching Vision-Language-Action Models the Contact Dynamics Beyond Vision and Action
Nov 19, 2026
8 authors
cs.ROcs.CV
Flow Matching from Non-Gaussian Sources: A Theory of Efficient Sampling
Nov 19, 2026
4 authors
stat.MLcs.AIcs.IT+1
WeMM-Video: Pushing the Frontiers of Open-Source Omni-Modal Video Understanding
Nov 19, 2026
12 authors
cs.CVeess.AS
Statistical Inference with Ill-Conditioned Random Weight Neural Network Sieves
Nov 19, 2026
3 authors
stat.MEcs.LGecon.EM+1
How to Effectively Manage the Energy in Residential Systems: Development and Comparison of Methods
Nov 19, 2026
1 authors
eess.SYcs.LGcs.NE
ZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM Brain
Nov 19, 2026
11 authors
cs.AI
FEA solver integration of a composite World Model with a Spiking Neural Network memory Block for computationally efficient modelling of defects and variabilities
Nov 19, 2026
2 authors
cs.LG
Awaken-HI: Scaling Humanoid Intelligence with Whole-Body Human Experience
Nov 19, 2026
1 authors
cs.ROcs.AIcs.CV
Reasoning-Trace Analysis Using Large Language Models for Interpretable Q-Matrix Construction
Nov 19, 2026
3 authors
cs.AI
MemFolder: Structure-Guided Memory Folding for Efficient Agent Memory Management
Nov 19, 2026
9 authors
cs.CLcs.CV
FFGaussType: Feed-Forward Conversion of Glyph and SVG Geometry into Compact Gaussian Assets
Nov 19, 2026
5 authors
cs.CVcs.GR
AdaPixFlow: Learning Continuous-Time 3D Dynamics Across Scenes from Sparse Multi-view Observations
Nov 19, 2026
2 authors
cs.CV
HumanCOIN: A 12,500-Hour Dataset for Human Intent in Egocentric Manipulation
Nov 19, 2026
51 authors
cs.CVcs.RO
Asuka-FM: A System-Architectural Co-Design Framework for Efficient Text-to-Image Pretraining on Consumer Hardware
Nov 19, 2026
4 authors
cs.CVcs.AI