Model Detail
ABot-OCR
—ABot-OCR is an AI model with 1.1B parameters released by acvlab. It has accumulated 65 downloads on Hugging Face since publication.
ABot-OCR ships with 1.1B parameters. Total weight footprint is approximately 2.1 GB, which is the relevant figure when planning local-inference VRAM.
ABot-OCR is best fit for general-purpose AI workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution
arXiv:2610.18355v2 Announce Type: new Abstract: We introduce ABot Embodied Reasoning (ABot-ER), a unified embodied reasoning foundation model that breaks the tension between breadth and depth in embodied reasoning. Embodied intelligence demands the joint mastery of perception, planning, and executio
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
arXiv:2607.19191v1 Announce Type: cross Abstract: We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction, supported by a multi-source data infrastructure spanning AAA games, simulation engines, and internet videos to learn controllable wo
ABot-N1: Toward a General Visual Language Navigation Foundation Model
arXiv:2607.10383v3 Announce Type: replace-cross Abstract: Visual Language Navigation foundation models aim to unify deep reasoning for grounded spatial decisions with broad versatility for diverse embodied tasks. Current approaches typically achieve this integration via monolithic policies that map
ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory
arXiv:2607.10350v3 Announce Type: replace Abstract: Recent VLM and VLA systems have improved robotic perception and action prediction, yet long-horizon embodied agents still require a general runtime layer for reasoning, memory, tool use, verification, and cross-embodiment execution. We present ABot
