Falcon Perception
Falcon Perception is an early-fusion transformer by the Technology Innovation Institute (TII) that reads an image and a natural-language query and returns every matching instance. LibreYOLO vendors its inference network for open-vocabulary detection on both sizes and instance segmentation on 600m.
- Tareas
- detection, instance segmentation
- Tamaños
- 300m, 600m at 1024 px
- Instalación
pip install "libreyolo[vlm]"- Nivel de compatibilidad
- Nivel hermano, desde v1.8.0. Una superficie de producto independiente con su propia factoría y su propio contrato.
- Proyecto original
- Falcon Perception de Technology Innovation Institute (TII), Apache-2.0. Artículo, fuente
- Licencias
- Código Apache-2.0, pesos Apache-2.0. Uso comercial
Install
Falcon Perception belongs to LibreYOLO's VLM tier and needs the vlm extra.
pip install "libreyolo[vlm]"Predict
Weights download on first use from TII's own repositories,
tiiuae/Falcon-Perception (600m) and tiiuae/Falcon-Perception-300M, pinned
to a revision. The network is vendored in LibreYOLO; no remote code runs.
from libreyolo import LibreVLM, SAMPLE_IMAGE # Each vocabulary entry is one query; instances get that entry's class id.model = LibreVLM("falcon-perception", names=["building", "person"])result = model.predict(SAMPLE_IMAGE, save=True) for box in result.boxes: print(box.cls, box.xyxy)from libreyolo import LibreVLM, SAMPLE_IMAGE model = LibreVLM("falcon-perception", names=["the titanium building"])result = model.set_task("segment").predict(SAMPLE_IMAGE) print(result.boxes.xyxy)print(result.masks.data.shape) # one mask per instancefrom libreyolo import LibreVLM, SAMPLE_IMAGE # The smaller size has no mask head: detect only.model = LibreVLM("falcon-perception-300m", names=["building"])result = model.predict(SAMPLE_IMAGE)The family loads through LibreVLM(), or the LibreFalconPerception class.
names= (or set_classes()) is required. Each vocabulary entry is one text
query and one generation, so cost grows with the number of entries, and every
instance found for an entry gets that entry's class id. A query can be a class
name or a phrase such as "the dog on the left".
For each instance the model emits a box centre, a box extent and a mask query.
detect returns Results.boxes; segment (600m only) also returns
Results.masks, made by dotting the mask query with AnyUp-upsampled image
features. Confidence is a constant 1.0 and there is no NMS: upstream's
coordinate de-duplication runs inside decoding (coord_dedup_threshold,
default 0.01). The generation budget is 2048 new tokens per query
(max_new_tokens).
Variants
| Name | Size | Tasks |
|---|---|---|
falcon-perception, falcon-perception-600m | 600m (default) | detect, segment |
falcon-perception-300m | 300m | detect |
Both run at 1024 px. When only MPS is available the family runs on CPU, because its RoPE tables are complex64, which MPS does not implement. On CPU in fp32 the port matches the upstream engine bit for bit: logits and hidden states on every forward pass, and the generated tokens, box floats and mask bytes.
Export
Inference only: train(), val(), export() and chat() raise.
Licensing
Comprueba la licencia en el repositorio de Hugging Face de los pesos concretos que descargues. Cada checkpoint de la organización de LibreYOLO incluye una, y no siempre es la misma en toda una familia. Ese repositorio es la fuente autorizada; el resumen siguiente describe qué se aplicaba cuando se verificó esta página por última vez.
Esta es una descripción de las licencias implicadas, no asesoramiento legal. Si la respuesta es importante a nivel comercial, lee las licencias y busca tu propio asesoramiento.
- Trabajo original
- Falcon Perception, Technology Innovation Institute (TII)
- Licencia del proyecto original
- Apache-2.0
- Fuente del proyecto original
- github.com/tiiuae/Falcon-Perception
- Código de LibreYOLO
- MIT
- Pesos
- Apache-2.0, distribuidos por sus autores. LibreYOLO no los aloja ni los replica.
- Interpretación
- Apache-2.0 is a permissive license, so the Falcon Perception code and weights can be used in commercial and closed-source products. Redistributing them means keeping the license text and TII's NOTICE, which asks public-facing work to retain it and cite the project, and the license grants a patent license. LibreYOLO vendors the inference network, preprocessing and generation loop from tiiuae/Falcon-Perception at commit c457916c9974efbacfa91f0f6ecc2c49c6543e56 under Apache-2.0 (libreyolo/models/falcon_perception/NOTICE); the adapter around it is MIT. One exception: the AnyUp feature upsampler that upstream flattened into its code, used only by the 600m segment task, is by the AnyUp authors under CC BY 4.0, which permits commercial use but requires attribution. Weights are not redistributed: they download at runtime from tiiuae/Falcon-Perception (600m, revision a3e21ada0abd533393776ffab8908a728f775509) and tiiuae/Falcon-Perception-300M (300m, detect only, revision 36993684b3ba5945b22d01e705f8ff2e048bf0b0), both declared Apache-2.0 and not gated.
Falcon Perception is Apache-2.0, code and weights, by the Technology Innovation Institute. Commercial use is allowed; TII's NOTICE asks public-facing work to retain it and cite the project. The AnyUp feature upsampler, used only by the 600m segment task, is by the AnyUp authors under CC BY 4.0, which permits commercial use with attribution. LibreYOLO does not redistribute the weights.
Citation
@article{bevli2026falcon,
title = {Falcon Perception},
author = {Bevli, Aviraj and Chaybouti, Sofian and Dahou, Yasser and Hacid, Hakim and Huynh, Ngoc Dung and Le Khac, Phuc H. and Narayan, Sanath and Para, Wamiq Reyaz and Singh, Ankit},
journal = {arXiv preprint arXiv:2603.27365},
year = {2026},
url = {https://arxiv.org/abs/2603.27365}
}Copiado del bloque de cita de los autores en github.com/tiiuae/Falcon-Perception#citation.