# Falcon Perception Source: [Falcon Perception]() Collection index: [llms.txt]() Data updated: 2026-04-04T06:00:01.688Z Authors: Aviraj Bevli, Sofian Chaybouti, Yasser Dahou, Hakim Hacid, Ngoc Dung Huynh, Phuc H. Le Khac, Sanath Narayan, Wamiq Reyaz Para, Ankit Singh Published: 2026-03-28T18:23:20.000Z ## Abstract Perception-centric systems are typically implemented with a modular encoder-decoder pipeline: a vision backbone for feature extraction and a separate decoder (or late-fusion module) for task prediction. This raises a central question: is this architectural separation essential or can a single early-fusion stack do both perception and task modeling at scale? We introduce Falcon Perception, a unified dense Transformer that processes image patches and text tokens in a shared parameter space from the first layer, using a hybrid attention pattern (bidirectional among image tokens, causal for prediction tokens) to combine global visual context with autoregressive, variable-length instance generation. To keep dense outputs practical, Falcon Perception retains a lightweight token interface and decodes continuous spatial outputs with specialized heads, enabling parallel high-resolution mask prediction. Our design promotes simplicity: we keep a single scalable backbone and shift complexity toward data and training signals, adding only small heads where outputs are continuous and dense. On SA-Co, Falcon Perception improves mask quality to 68.0 Macro-F$\_1$ compared to 62.3 of SAM3. We also introduce PBench, a benchmark targeting compositional prompts (OCR, spatial constraints, relations) and dense long-context regimes, where the model shows better gains. Finally, we extend the same early-fusion recipe to Falcon OCR: a compact 300M-parameter model which attains 80.3% on olmOCR and 88.64 on OmniDocBench. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Referring Expression Segmentation on RefCOCOm (val)](): Referring Expression Segmentation; RefCOCOm (val); Macro F1: 77.3. - [Optical Character Recognition on olmOCR multiple category 1.5](): Optical Character Recognition; olmOCR multiple category 1.5; Average Accuracy: 80.3. - [Full-page Document Parsing on OmniDocBench](): Full-page Document Parsing; OmniDocBench; Overall Score: 88.64. - [Referring Expression Segmentation on PBench](): Referring Expression Segmentation; PBench; L0: Simple Objects Accuracy: 65.1. ## Original sources and implementation [Original paper]() [PDF]()