#zero-shot generalization

try —

4 papers match

cs.AI2026

World Action Planner: Generalizable Decision-Making with Action-Conditioned World Models

Xiangcheng Zhang, Yilun Du

The paper introduces World Action Planner, a robot planning system that combines vision‑language models with a multi‑task, pose‑image conditioned world model to generate and iterat…

#action-conditioned world models#vision-language models#robot planning#zero-shot generalization
cs.CV2026

FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry

Muxin Liu, Xiaoyang Lyu, Tianhe Ren +7

FoundationGeo is a two‑stage framework that first learns an affine‑invariant geometry model from a large multi‑domain dataset, then refines metric depth using lightweight pixel‑wis…

#monocular depth estimation#metric geometry#spatial calibration#zero-shot generalization
cs.IT2026

FM-Receiver: A Foundation Model Enabled Unified Inner and Outer Neural Receiver Towards AI-Native Wireless Communications

Tianyue Zheng, Chao Jiang, Linglong Dai

The paper introduces FM-Receiver, a unified neural receiver that leverages a foundation model to jointly perform outer and inner decoding of wireless signals, enabling end‑to‑end A…

#neural receiver#foundation model#channel decoding#transformer
cs.LG2026

TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale

Zhouchonghao Wu, Akshay Rangesh, Weixin Li +5

TerraZero is a procedural driving simulator that enables large-scale, zero‑demonstration self‑play reinforcement learning for autonomous driving, achieving high simulation speed an…

#procedural simulation#self-play reinforcement learning#zero-demonstration training#traffic rule enforcement