activity
20242026
collaborators

9 papers

cs.CL2026

Linguistically Informed Evaluation of Multilingual ASR for African Languages

Fei-Yueh Chen, Lateef Adeleke, C. M. Downey

Word Error Rate (WER) mischaracterizes ASR models' performance for African languages by combining phonological, tone, and other linguistic errors into a single lexical error. By co…

cs.LG2025

Contrastive Difference Predictive Coding

Chongyi Zheng, Ruslan Salakhutdinov, Benjamin Eysenbach

Predicting and reasoning about the future lie at the heart of many time-series questions. For example, goal-conditioned reinforcement learning can be viewed as learning representat…

cs.CL2025

DM-Codec: Distilling Multimodal Representations for Speech Tokenization

Md Mubtasim Ahasan, Md Fahim, Tasnim Mohiuddin +6

Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional…

cs.LG2025

Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data

Chongyi Zheng, Benjamin Eysenbach, Homer Walke +4

Robotic systems that rely primarily on self-supervised learning have the potential to decrease the amount of human annotation and engineering effort required to learn control strat…

cs.CV2025

Effective Data Augmentation With Diffusion Models

Brandon Trabucco, Kyle Doherty, Max Gurinas +1

Data augmentation is one of the most prevalent tools in deep learning, underpinning many recent advances, including those from classification, generative models, and representation…

cs.LG2025

Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference

Benjamin Eysenbach, Vivek Myers, Ruslan Salakhutdinov +1

Given time series data, how can we answer questions like "what will happen in the future?" and "how did we get here?" These sorts of probabilistic inference questions are challengi…