activity
20242026
collaborators

6 papers

cs.AI2026

Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1

Kabir Moghe, Peter Chin

Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy test-time compute over frontier models (evolutionary search, exhaustive sampling,…

cs.CL2026

Probing LLMs for Syntactic Structure Beyond Universal Dependencies: A Minimalist Phase Account in English

Yuanhao Chen, Peter Chin

We show that LLMs encode syntactic distinctions not present in the Universal Dependencies (UD) tree distances that structural probes are trained to recover. On English wh-movement…

q-bio.NC2026

MoDAl: Self-Supervised Neural Modality Discovery via Decorrelation for Speech Neuroprosthesis

Yuanhao Chen, Peter Chin

Speech neuroprosthesis systems decode intended speech from neural activity in the absence of audible output, offering a path to restoring communication for individuals with speech-…

cs.SD2026

TADA: A Generative Framework for Speech Modeling via Text-Acoustic Dual Alignment

Trung Dang, Sharath Rao, Ananya Gupta +6

Modern Text-to-Speech (TTS) systems increasingly leverage Large Language Model (LLM) architectures to achieve scalable, high-fidelity, zero-shot generation. However, these systems…

cs.CL2025

MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning

Thang Nguyen, Peter Chin, Yu-Wing Tai

We present MA-RAG, a Multi-Agent framework for Retrieval-Augmented Generation (RAG) that addresses the inherent ambiguities and reasoning challenges in complex information-seeking…

cs.CL2024

Reward-RAG: Enhancing RAG with Reward Driven Supervision

Thang Nguyen, Peter Chin, Yu-Wing Tai

In this paper, we introduce Reward-RAG, a novel approach designed to enhance the Retrieval-Augmented Generation (RAG) model through Reward-Driven Supervision. Unlike previous RAG m…