activity
20242026
collaborators

5 papers

cs.IR2026

A Brief Comparison of Training-Free Multi-Vector Sequence Compression Methods

Rohan Jha, Chunsheng Zuo, Reno Kriz +1

While multi-vector retrieval models outperform single-vector models of comparable size in retrieval quality, their practicality is limited by substantially larger index sizes, driv…

cs.IR2026

Multi-Vector Index Compression in Any Modality

Hanxiang Qin, Alexander Martin, Rohan Jha +3

We study efficient multi-vector retrieval for late interaction in any modality. Late interaction has emerged as a dominant paradigm for information retrieval in text, images, visua…

cs.CL2025

GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models

Jixiao Zhang, Chunsheng Zuo

Group Relative Policy Optimization (GRPO), which is widely adopted by R1-like reasoning models, has advanced mathematical reasoning. Nevertheless, GRPO faces challenges in reward s…

cs.LG2025

TAU: Modeling Temporal Consistency Through Temporal Attentive U-Net for PPG Peak Detection

Chunsheng Zuo, Yu Zhao, Juntao Ye

Photoplethysmography (PPG) sensors have been widely used in consumer wearable devices to monitor heart rates (HR) and heart rate variability (HRV). Despite the prevalence, PPG sign…

cs.CL2024

Position Information Emerges in Causal Transformers Without Positional Encodings via Similarity of Nearby Embeddings

Chunsheng Zuo, Pavel Guerzhoy, Michael Guerzhoy

Transformers with causal attention can solve tasks that require positional information without using positional encodings. In this work, we propose and investigate a new hypothesis…