activity
20242026
collaborators

7 papers

cs.CL2026

Test-time Recursive Thinking: Self-Improvement without External Feedback

Yufan Zhuang, Chandan Singh, Liyuan Liu +5

Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable rewards. Here, we ask whe…

q-bio.NC2025

Interpretable Embeddings of Speech Enhance and Explain Brain Encoding Performance of Audio Models

Riki Shimizu, Richard J. Antonello, Chandan Singh +1

Speech foundation models (SFMs) are increasingly hailed as powerful computational models of human speech perception. However, since their representations are inherently black-box,…

cs.CL2025

Text Generation Beyond Discrete Token Sampling

Yufan Zhuang, Liyuan Liu, Chandan Singh +2

In standard autoregressive generation, an LLM predicts the next-token distribution, samples a discrete token, and then discards the distribution, passing only the sampled token as…

cs.GR2025

Towards Understanding Graphical Perception in Large Multimodal Models

Kai Zhang, Jianwei Yang, Jeevana Priya Inala +4

Despite the promising results of large multimodal models (LMMs) in complex vision-language tasks that require knowledge, reasoning, and perception abilities together, we surprising…

cs.CV2025

Simplifying DINO via Coding Rate Regularization

Ziyang Wu, Jingyuan Zhang, Druv Pai +5

DINO and DINOv2 are two model families being widely used to learn representations from unlabeled imagery data at large scales. Their learned representations often enable state-of-t…

cs.CL2024

Interpretable Next-token Prediction via the Generalized Induction Head

Eunji Kim, Sriya Mantena, Weiwei Yang +3

While large transformer models excel in predictive performance, their lack of interpretability restricts their usefulness in high-stakes domains. To remedy this, we propose the Gen…