paper-with-me

Papers Continuous Control

“Continuous Control” 태그가 달린 논문 1,431편 · 필터 해제

Event-Adaptive Motion Planning with Distilled Vision-Language Model in Safety-Critical Situations

2026-06-24 · Zhenwei Huang, Changsheng You, Shuai Wang, Chao Zhou 외 arxiv

Robot navigation in safety-critical scenarios faces significant challenges from unforeseen semantic events, where collisions arise primarily from the unpredictable behaviors of dynamic agents rather than unseen objects. …

Continuous ControlRobot NavigationMotion Planning

Bridging Spherical Black-Box Optimizers

2026-06-24 · Johannes Ackermann, Stefano Peluchetti arxiv

When gradient information is unavailable, black-box optimization (BBO) methods provide a practical alternative. While Evolution Strategies (ES), Consensus-Based Optimization (CBO), Optimization via Integration (OVI), and…

Continuous Control

Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning

2026-06-23 · Chenhao Dang, Jing Ma, Mingjie Liao arxiv

The composition of training data, governed by the diversity of sources and their mixing strategy, is a cornerstone of Large Language Model (LLM) pre-training. Online Data Mixing (ODM), the technique of adaptively adjusti…

Reinforcement LearningContinuous Control

Causal Reward World Models: Zero-shot Reward Design for Automated Skill Generation

2026-06-22 · Yang Yang, Yuchuang Tong, Zhengtao Zhang, Xu Ding 외 arxiv

Automated Reward Design (ARD) aims to replace manual reward engineering in reinforcement learning with language-driven reward function synthesis. However, existing approaches based on large language models (LLMs) remain …

Reinforcement LearningContinuous Control

Token-to-Token Alignment of Text Embeddings for Semantic Blending

2026-06-22 · Saar Huberman, Ron Mokady, Or Patashnik, Daniel Cohen-Or arxiv

In modern generative models, images are specified and controlled through text prompts. In practice, images are generated from sequences of tokens derived from these prompts. However, the space of token sequences lacks a …

Semantic correspondenceSemantic SimilarityContinuous Control

Low-power analogue neural networks with trainable nonlinear connections for continuous control

2026-06-21 · Ian T. Vidamour, Fernando Aguirre, Thomas J. Hayward, Matthew O. A. Ellis 외 arxiv

Physical neural networks promise low-power machine learning by computing directly with analogue device physics, but most architectures force nonlinear device responses to act as scalar weights. Inspired by Kolmogorov-Arn…

Continuous ControlPoint Tracking

Objective-Behavior Alignment: Diagnostics for MORL Policy Selection

2026-06-19 · Antonio Mone, Zuzanna Osika, Florian Felten, Pradeep K. Murukannaiah 외 arxiv

Real-world decision-making often requires optimizing multiple competing objectives simultaneously. In reinforcement learning (RL), this is typically addressed by combining reward signals into a single scalar objective vi…

Reinforcement LearningContinuous Control

Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Efficient Differentiable Continuous Control

2026-06-19 · Yueci Deng arxiv

Model-free reinforcement learning algorithms such as Proximal Policy Optimization (PPO) treat the environment as a black box, estimating policy gradients from sampled rewards; this process demands millions of interaction…

Reinforcement LearningContinuous Control

ADaPT: Token-Level Decoupling for Efficient Large Reasoning Models

2026-06-18 · Tingyun Li, Zishang Jiang, Jinyi Han, Xinyi Wang 외 arxiv

Large reasoning models rely on long chain-of-thought to achieve strong performance, but applying such reasoning uniformly incurs high computational cost. Existing efficiency-oriented methods attempt to shorten or mix rea…

Continuous Control

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

2026-06-18 · Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha, Khoa Vo 외 arxiv

Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose prohibitive computational burdens during do…

Continuous Control

Provably Sub-Linear Two-Timescale NeuroEvolution with Online Plasticity

2026-06-18 · Shishen Lin, Yixin Chen arxiv

NeuroEvolution of Augmenting Topologies (NEAT) is a widely used neuroevolution algorithm for learning neural network architectures and weights for control tasks. However, standard offline optimisation searches for connec…

Reinforcement LearningContinuous Control

Evolutionary Bilevel Reward Shaping for Generalization in Reinforcement Learning

2026-06-15 · Ekasit Usaratniwart, Xilin Gao, Marc Ong, Youhei Akimoto arxiv

Reinforcement learning (RL) often suffers from performance degradation when deployed in environments that differ from those encountered during training. Existing techniques such as domain randomization (DR) mitigate this…

Reinforcement LearningBilevel OptimizationContinuous Control

BRICKS-WM: Building Reusability via Interface Composition Kinetics for Structured World Models

2026-06-15 · Shaowei Zhang, Jiahan Cao, Xunlan Zhou, Shenghua Wan 외 arxiv

Model-based Reinforcement Learning (MBRL) has achieved remarkable success in continuous control by leveraging latent world models. However, prevailing approaches typically rely on monolithic latent dynamics, entangling e…

Reinforcement LearningContinuous Control

ARB4WM: An Adversarial Robustness Benchmark for World Models in Continuous Control

2026-06-15 · Junjian Zhang, Hao Tan, Ruonan Li, Dong Zhu 외 arxiv

World models are widely used in robotic and agentic engineering control systems due to their ability to learn latent dynamics for planning and decision-making. As these systems are increasingly deployed in safety-critica…

Adversarial RobustnessContinuous Control

Gaze Heads: How VLMs Look at What They Describe

2026-06-12 · Rohit Gandikota, David Bau arxiv

How a vision-language model internally solves the task of describing an image is far from obvious. We find that the model develops a specific mechanism for this: a small set of attention heads in its language-model backb…

Continuous Control

LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories

2026-06-11 · Baochang Ren, Xinjie Liu, Xi Chen, Yanshuo Liu 외 arxiv

Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach. AI can help read literature, generate hypotheses, and plan p…

Continuous Control

ScoutVLA: UAV-Centric Active Perception via a Dual-Expert VLA Model for Open-World Embodied Question Answering

2026-06-09 · Wenhao Lu, Zhengqiu Zhu, Xiaofeng Wang, Xiaoran Zhang 외 arxiv

Aerial Embodied Question Answering (EQA) requires Unmanned Aerial Vehicles (UAVs) to actively perceive the environment and answer natural language questions. Existing outdoor EQA systems usually stop once the target ente…

Multimodal ReasoningContinuous ControlQuestion Answering

Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning

2026-06-09 · Zhiyuan Zhou, Andy Peng, Charles Xu, Qiyang Li 외 arxiv

Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control. While they are known to scale stably in …

Reinforcement LearningContinuous ControlOffline RL

Difference-Aware Retrieval Policies for Imitation Learning

2026-06-08 · Quinn Pfeifer, Ethan Pronovost, Paarth Shah, Khimya Khetarpal 외 arxiv

Parametric imitation learning via behavior cloning can suffer from poor generalization to out-of-distribution states due to compounding errors during deployment. We show that reusing the training data during inference vi…

Continuous Control

PRISM: PRior-guided Imagination Sampling in world Models

2026-06-06 · Yuhai Wang, Jiawei Xia, Rongxuan Zhou, Xiao Hu 외 arxiv

A learned world model provides a powerful physical intuition for evaluating future states. But its effectiveness in continuous control also depends critically on how candidate actions are generated for model-based planni…

Continuous ControlPhysical Intuition
← 이전 21–40 / 1,431 다음 →