paper-with-me

Papers

Falcon Perception

2026-03-28 · Aviraj Bevli, Sofian Chaybouti, Yasser Dahou, Hakim Hacid, Ngoc Dung Huynh, Phuc H. Le Khac, Sanath Narayan, Wamiq Reyaz Para, Ankit Singh arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.27365

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

FalconApp: Rapid iPhone Deployment of End-to-End Perception via Automatically Labeled Synthetic Data

2026-04-21 · Yan Miao, Will Shen, Sayan Mitra arxiv

Reliable perception for robotics depends on large-scale labeled data, yet real-world datasets rely on heavy manual annotation and are time-consuming to produce. We present FalconApp, an iPhone app with an end-to-end fron…

Pose Estimation

Falcon Perception-HD: High Density Perception via Reinforcement Learning

2026-08-19 · Sofian Chaybouti, Yasser Dahou, Ngoc Dung Huynh, Reda Alami 외 arxiv

Autoregressive perception models trained to localize visual entities under the open-vocabulary setting are mostly trained using Supervised fine-tuning (SFT) with maximum likelihood, yet it optimizes a proxy objective (pe…

Referring Expression SegmentationReinforcement Learning

FalconTrack: Photorealistic Auto-Labeled Perception and Physics-Aware Vision-Based Aerial Tracking

2026-06-29 · Yan Miao, Karteek Gandiboyina, Noah Giles, Hideki Okamoto 외 arxiv

Vision-based aerial tracking is critical in GPS-denied environments. Reliable perception for tracking depends on large-scale labeled data, yet most photorealistic datasets rely on heavy manual annotation and are time-con…

Visual Tracking

Falcon: A Cross-Modal Evaluation Dataset for Comprehensive Safety Perception

2025-09-28 · Qi Xue, Minrui Jiang, Runjia Zhang, Xiurui Xie 외 arxiv

Existing methods for evaluating the harmfulness of content generated by large language models (LLMs) have been well studied. However, approaches tailored to multimodal large language models (MLLMs) remain underdeveloped …

Visual Question Answering

FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers

2025-01-27 · Renshan Zhang, Rui Shao, Gongwei Chen, Kaiwen Zhou 외

The incorporation of high-resolution visual input equips multimodal large language models (MLLMs) with enhanced visual perception capabilities for real-world tasks. However, most existing high-resolution MLLMs rely on a …