2024/12/09~2024/12/13 面白そうな論文リスト
A Temporally Correlated Latent Exploration for Reinforcement Learning
https://arxiv.org/abs/2412.04775
時間の相関をなんらか考えた内的報酬
Measuring Goal-Directedness
https://arxiv.org/abs/2412.04758
ゴール志向のなにか
Bounded Exploration with World Model Uncertainty in Soft Actor-Critic Reinforcement Learning Algorithm
https://arxiv.org/abs/2412.06139
Nested Diffusion Models Using Hierarchical Latent Priors
https://arxiv.org/abs/2412.05984
Normalizing Flows are Capable Generative Models
https://arxiv.org/abs/2412.06329
正規化フローの逆襲？
Flow Matching Guide and Code
https://arxiv.org/abs/2412.06264
Flow Matchingの学習にはこれを読んでおけば良さそう
TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft
https://arxiv.org/abs/2412.05255
マルチエージェントでのマルチモーダルなタスクをたくさん用意したみたい
FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation
https://arxiv.org/abs/2412.04987
シンプルにFlow MatchingでのPolicy
Generative Modeling with Explicit Memory
https://arxiv.org/abs/2412.08781
GenEx: Generating an Explorable World
https://arxiv.org/abs/2412.09624
Owl-1: Omni World Model for Consistent Long Video Generation
https://arxiv.org/abs/2412.09600
自動運転関連
Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model
https://arxiv.org/abs/2412.05280
運転シーンでの4D生成。4Dポイントクラウドを中心にキーフレームベースで考えていく？
Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving
https://arxiv.org/abs/2412.06777
Street Gaussians without 3D Object Tracker
https://arxiv.org/abs/2412.05548
UniScene: Unified Occupancy-centric Driving Scene Generation
https://arxiv.org/abs/2412.05435
DriveMM: All-in-One Large Multimodal Model for Autonomous Driving
https://arxiv.org/abs/2412.07689
Pysical Informed Driving World Model
https://arxiv.org/abs/2412.08410
GPD-1: Generative Pre-training for Driving
https://arxiv.org/abs/2412.08643
DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving
https://arxiv.org/abs/2412.09043
Doe-1: Closed-Loop Autonomous Driving with Large World Model
https://arxiv.org/abs/2412.09627
Hidden Biases of End-to-End Driving Datasets
https://arxiv.org/abs/2412.09602