5 papers
Do Audio Language Models Use Paralinguistic Evidence? Counterfactual Audits for Response Evaluation
Kevin Miller, Arjun Chandra, Venkatesh Saligrama
Audio-language models (ALMs) are increasingly used as judges for speech-to-speech systems, but a judge that receives audio may not actually use paralinguistic evidence. We introduc…
Symmetry Reveals Layerwise Dynamics: How Transformers Perform In-Context Classification
Patrick Lutz, Themistoklis Haris, Arjun Chandra +2
Transformers can perform in-context classification from a few labeled examples, yet the inference-time algorithm remains opaque. We study multi-class linear classification in the h…
BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models
Shengao Wang, Wenqi Wang, Zecheng Wang +20
Early children's developmental trajectories set up a natural goal for sample-efficient pretraining of vision foundation models. We introduce BabyVLM-V2, a developmentally grounded…
Hearing Between the Lines: Unlocking the Reasoning Power of LLMs for Speech Evaluation
Arjun Chandra, Kevin Miller, Venkatesh Ravichandran +2
Large Language Model (LLM) judges exhibit strong reasoning capabilities but are limited to textual content. This leaves current automatic Speech-to-Speech (S2S) evaluation methods…
BabyVLM: Data-Efficient Pretraining of VLMs Inspired by Infant Learning
Shengao Wang, Arjun Chandra, Aoming Liu +2
Human infants rapidly develop visual reasoning skills from minimal input, suggesting that developmentally inspired pretraining could significantly enhance the efficiency of vision-…