arXiv Machine Learning August 7, 2026 By Fahim Shahriar, Cheryl Wang, Alireza Azimi, Gautham Vasan, Hany Hamed, Abhishek Naik, A. Rupam Mahmood, Colin Bellinger

Dynamic Object Masks as Goal Representations for Visual Goal-Conditioned Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2510. 06277v2 Announce Type: replace-cross Abstract: Goal-conditioned reinforcement learning (GCRL) offers a unified way to pursue diverse tasks, yet most existing methods rely on state- or position-based goal representations that are unavailable in real-world robotics.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 18

EffiNav: Fusing Depth and Vision-Language for Efficient Object Goal Navigation

arXiv:2606. 18634v1 Announce Type: cross Abstract: To locate a target object while exploring the unknown environment is a fundamental capability for autonomous agents, with applications ranging from search-and-rescue to field robots.

By Zecheng Yin, Benedict Jun Ma

agents robotics multimodal benchmarks

arXiv Machine Learning

Jun 17

Can Vision Foundation Models Navigate? Zero-Shot Real-World Evaluation and Lessons Learned

arXiv:2603. 25937v2 Announce Type: replace-cross Abstract: Visual Navigation Models (VNMs) promise generalizable, robot navigation by learning from large-scale visual demonstrations.

By Maeva Guerrier, Karthik Soma, Jana Pavlasek, Giovanni Beltrame

llms diffusion robotics benchmarks

arXiv Machine Learning

Jul 8

Learning to Throw Objects Safely in Multi-Obstacle Environments

arXiv:2607. 06388v1 Announce Type: cross Abstract: Robotic throwing enables fast and efficient object placement beyond the robot's immediate workspace, but reliable throwing in cluttered environments remains underexplored.

By Mohammadreza Kasaei, Klemen Voncina, Hamidreza Kasaei

reinforcement-learning robotics benchmarks

arXiv AI

Jul 1

Stage-Transition Dense Reward Modeling for Reinforcement Learning

arXiv:2606. 31377v1 Announce Type: cross Abstract: Reinforcement learning for long-horizon robotic manipulation is often limited by sparse and delayed rewards, while manually designing dense shaping signals is costly and brittle to changes in environments and object configurations.

By Yang Yang, Bingjie Chen, Zihan Wang, Yizhe Li, Guoping Pan, Yi Cheng, Houde Liu

agents reinforcement-learning robotics

arXiv AI

Jun 24

G$^3$VLA: Geometric inductive bias for Vision-Language-Action Models

arXiv:2606. 24472v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have made rapid progress in generalist robot manipulation by harnessing semantic knowledge from pretrained vision-language backbones, but their visual tokens remain grounded in 2D image coordinates rather than the calibrated geometry of the robot's cameras -- a mismatch especially pronounced in multi-camera setups, where views are coupled by known intrinsics and extrinsics yet processed as independent images.

By Yue Peng, Yongzhe Zhao, Artur Habuda, Khuyen Pham, Yanheng Zhu, Tran Nguyen Le, Fares Abu-Dakka, Li Guo

rag robotics multimodal safety

arXiv Machine Learning

Jun 10

GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation

arXiv:2606. 10025v1 Announce Type: cross Abstract: We present GHOST, a framework for learning visuomotor manipulation policies that generalize beyond the training distribution.

By Sriram Krishna, Ben Eisner, Haotian Zhan, Ying Yuan, Haoyu Zhen, Chuang Gan, Shubham Tulsiani, David Held

diffusion robotics

Related stories

EffiNav: Fusing Depth and Vision-Language for Efficient Object Goal Navigation

Can Vision Foundation Models Navigate? Zero-Shot Real-World Evaluation and Lessons Learned

Learning to Throw Objects Safely in Multi-Obstacle Environments

Stage-Transition Dense Reward Modeling for Reinforcement Learning

G$^3$VLA: Geometric inductive bias for Vision-Language-Action Models

GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation