6 papers
LiNC: Lightweight Noise Correction via Per-Sample Trust and Gaussian Mixture Modeling
Abhishek Moturu, Babak Taati, Anna Goldenberg
Label noise is common in medical imaging datasets due to factors such as inter-rater variability, annotation errors, and ambiguous cases. This can severely undermine the reliabilit…
LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training
Abhishek Moturu, Muhammad Muzammil, Anna Goldenberg +1
Training deep neural networks with noise and data heterogeneity is a major challenge. We introduce Lightweight Learnable Adaptive Weighting (LiLAW), a method that dynamically adjus…
SynPAIN: A Synthetic Dataset of Pain and Non-Pain Facial Expressions
Babak Taati, Muhammad Muzammil, Yasamin Zarghami +5
Accurate pain assessment in patients with limited ability to communicate, such as older adults with severe dementia, represents a critical healthcare challenge. Robust automated sy…
When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains
Ahmadreza Jeddi, Kimia Shaban, Negin Baghbanzadeh +4
Reinforcement learning (RL) is increasingly used to post-train medical Vision-Language Models (VLMs), yet it remains unclear whether RL improves medical visual reasoning or mainly…
LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation
Ahmadreza Jeddi, Marco Ciccone, Babak Taati
Looped Transformers have emerged as an efficient and powerful class of models for reasoning in the language domain. Recent studies show that these models achieve strong performance…
Similarity-Aware Token Pruning: Your VLM but Faster
Ahmadreza Jeddi, Negin Baghbanzadeh, Elham Dolatabadi +1
The computational demands of Vision Transformers (ViTs) and Vision-Language Models (VLMs) remain a significant challenge due to the quadratic complexity of self-attention. While to…