Publications (8)
Calibrated Reasoning: An Explanatory Verifier for Dynamic and Efficient Problem-Solving
Anisha Garg, Engin Tekin, Yash More +3
Advanced test-time computing strategies are essential for scaling reasoning models, but their effectiveness is capped by the models' poor self-evaluation. We propose a pairwise Exp…
CoRPO: Adding a Correctness Bias to GRPO Improves Generalization
Anisha Garg, Claire Zhang, Nishit Neema +3
Group-Relative Policy Optimization (GRPO) has emerged as the standard for training reasoning capabilities in large language models through reinforcement learning. By estimating adv…
Caustics in the spherically symmetric Einstein-dust system
David Bick
Caustics-envelopes formed by the trajectories of fluid particles-arise in proposed dynamical extensions for shell-crossing singularities occurring in the Einstein-dust system. In t…
The Conductor and the Engine: A Path Towards Co-Designed Reasoning
Yuanxin Wang, Pawel Filipczuk, Anisha Garg +4
Modern LLM reasoning relies on extensive test-time computation, driven by internal model training and external agentic orchestration. However, this synergy is often inefficient, as…
TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement
Yunyang Zeng, Joseph Konan, Shuo Han +5
Speech enhancement models have greatly progressed in recent years, but still show limits in perceptual quality of their speech outputs. We propose an objective for perceptual quali…
Timelike bounce hypersurfaces in charged null dust collapse
David Bick
We establish results on the dynamics of interacting charged null fluids in general relativity, specifically in the context of the bouncing continuation proposed in [Ori91]. In this…
Improving Speech Enhancement through Fine-Grained Speech Characteristics
Muqiao Yang, Joseph Konan, David Bick +3
While deep learning based speech enhancement systems have made rapid progress in improving the quality of speech signals, they can still produce outputs that contain artifacts and…
PAAPLoss: A Phonetic-Aligned Acoustic Parameter Loss for Speech Enhancement
Muqiao Yang, Joseph Konan, David Bick +5
Despite rapid advancement in recent years, current speech enhancement models often produce speech that differs in perceptual quality from real clean speech. We propose a learning o…