Microsoft

Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement

A residual RL policy learns purely in simulation from object-centric state. Then, we add it to a frozen base VLA, and it transfers zero-shot to the real robot. Vision-Language-Action (VLA) models ...
GitHub

SPECS.md

This document captures the full requirements for a Raspberry Pi script that, on a physical push-button press, triggers 3 relays and plays a song; when the song ends the relays turn off. Pressing again ...
IEEE

Uncertainty-Aware Transformer for Referring Camouflaged Object Detection

Abstract: Referring camouflaged object detection (Ref-COD) is a recently proposed task, aiming to segment specified camouflaged objects by leveraging visual reference, i.e., a small set of referring ...
IEEE

A Benchmark Review of YOLO Algorithm Developments for Object Detection

Abstract: You Only Look Once (YOLO) has established itself as a prominent object detection framework due to its excellent balance between speed and accuracy. This article provides a thorough review of ...
GitHub

agentdet_a_shared-blackboard_multi-agent_framework_for_zero-few-shot_object_dete.md

description [CVPR 2026][多智能体][零/少样本检测] AgentDet 把零/少样本目标检测拆成 Scout / Pinner / Curator / Judge 四个 LLM 智能体 ...