grounding

Agent S: an open agentic framework that uses computers like a human

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

awesome grounding: A curated list of research papers in visual grounding

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization

CLIPort: What and Where Pathways for Robotic Manipulation

Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"

We perform functional grounding of LLMs' knowledge in BabyAI-Text

PG-Video-LLaVA: Pixel Grounding in Large Multimodal Video Models

[TPAMI 2025] Towards Visual Grounding: A Survey

UI-Venus is a native UI agent based on the Qwen2.5-VL multimodal large language model, designed to perform precise GUI element grounding and effective navigation using only screenshots as input.

[TMM 2023] Self-paced Curriculum Adapting of CLIP for Visual Grounding.

Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding" (COLM 2024)

Hierarchical Universal Language Conditioned Policies

Official implementation of ICCV19 oral paper Zero-Shot grounding of Objects from Natural Language Queries (https://arxiv.org/abs/1908.07129)

[CVPR20] Video Object Grounding using Semantic Roles in Language Description (https://arxiv.org/abs/2003.10606)

[CVPR21] Visual Semantic Role Labeling for Video Understanding (https://arxiv.org/abs/2104.00990)

[ACM MM 2024] Hierarchical Multimodal Fine-grained Modulation for Visual Grounding.

Official implementation of "Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology"

[Paper][AAAI 2023] DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning