Falcon Perception-HD: High Density Perception via Reinforcement Learning
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 (per-token cross-entropy) that is fundamentally misaligned with perception metrics such as precision and recall. In this paper, we explore post-training reinforcement learning (RL), specifically GRPO, to directly align these models with their evaluation metrics. Building up on the recently introduced Falcon Perception, we design an RL framework that addresses perception-specific challenges: reward design for set-structured outputs and multi-head sampling control. We discover ...
| Authors | Sofian Chaybouti, Yasser Dahou, Ngoc Dung Huynh et al. |
|---|---|
| Primary category | cs.CV |
| Published | 19 August 2026 |
| Last updated at source | 19 August 2026 |
Connected in the knowledge graph
- tiiuae/Falcon-PerceptionModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.