32 papers
GKDT: General Keypoint Detection Transformer
Changsheng Lu, Yuxin Chen, Haokun Gui +5
With the emergence of various pre-trained vision and language models, computer vision is shifting from narrow-domain to open-domain recognition. The construction of a more powerful…
Enhancing Speckle Metrology with Diffusion Denoising in Photon-Starved Regimes
Admir Bajraktarevic, Alexander C. Trowbridge, Saba N. Khan +3
Laser speckle is a powerful tool for precision metrology that enables highly sensitive measurements of light sources and subtle environmental perturbations. Many applications requi…
LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation
Bo Miao, Weijia Liu, Jun Luo +8
Language-conditioned goal navigation (LGN) requires agents to locate user-specified targets without step-by-step guidance. However, existing benchmarks largely focus on category-le…
Procedural Pretraining: Warming Up Language Models with Abstract Data
Liangze Jiang, Zachary Shinnick, Anton van den Hengel +2
Pretraining language models directly on web-scale corpora is the de facto paradigm. We study an alternative where the model is initially exposed to abstract structured data to ease…
Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers
Zachary Shinnick, Liangze Jiang, Hemanth Saratchandran +2
Transformers are remarkably versatile, suggesting the existence of generic inductive biases beneficial across modalities. In this work, we explore a new way to instil such biases i…
I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?
Yuhang Liu, Dong Gong, Yichao Cai +6
Recent empirical evidence shows that LLM representations encode human-interpretable concepts. Nevertheless, the mechanisms by which these representations emerge remain largely unex…