Publications

This section contains publications published by ISI over the past several decades.

2026

FlashMap: Flow Map Speculative Decoding

Jeff Shen, Zhejian Zhou, Ryan Lee, Jonathan May, Shirley Ho
arXiv preprint arXiv:2610.24365,  2026

Edit, Don't Imitate: Minimal-Edit On-Policy Distillation for Multimodal Reasoning

Wen Ye, Ailin Deng, Zirui Wang, Shixing Yu, Han Zhang, Tian Yun, Nikhil Mehta, Tarun Kalluri, Xuefei Cao, Xuezhe Ma, Hengduo Li
arXiv preprint arXiv:2610.30231,  2026

Towards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State Design

Benhao Huang, Chufan Shi, Junlin Chen, Shicheng Wen, Zhengzhong Liu, Eric Xing, Xuezhe Ma
arXiv preprint arXiv:2610.23036,  2026

From Relevant Memories to Sufficient Evidence: Rethinking Memory Utilization in LLM Agents

Shixuan Li, Wei Yang, Peiyu Zhang, Anzhe Cheng, Heng Ping, Xiaole Zhang, Jesse Thomason, Xuezhe Ma, Yue Zhao, Paul Bogdan
arXiv preprint arXiv:2610.22668,  2026

SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning

Wei Yang, Shawn Li, Yuehan Qin, Yawei Wang, Mingxi Wang, Shixuan Li, Tiankai Yang, Jiate Li, Jesse Thomason, Xuezhe Ma, Yue Zhao
arXiv preprint arXiv:2610.11345,  2026

UReason: Benchmarking Reasoning-to-Generation Alignment in Unified Multimodal Models

Cheng Yang, Chufan Shi, Bo Shui, Yaokang Wu, Muzi Tao, Huijuan Wang, Ivan Lee, Yong Liu, Xuezhe Ma, Taylor Berg-Kirkpatrick
Proceedings of the 2026 Conference on Empirical Methods in Natural Language …,  2026

MIRROR: Learning from the Other View for Multi-Modal Reasoning

Wen Ye, Yuxiao Qu, Aviral Kumar, Xuezhe Ma
arXiv preprint arXiv:2607.21552,  2026

An Exam for Active Observers

Jiarui Zhang, Muzi Tao, Shangshang Wang, Ollie Liu, Xuezhe Ma, Willie Neiswanger
arXiv preprint arXiv:2607.16165,  2026

Photonic Static Random Access Memory

A Jaiswal, MAAI Kaiser, S Sunder, A Jacob
US Patent App. 18/989,456,  2026

Embedded ROM-based multi-bit, multi-kernel, multi-channel weights in individual pixels for in-pixel computing

A Jaiswal, AP Jacob, Z Yin
US Patent 12,659,630,  2026

Semantics for Science: Toward a Massive Scale Evidence-Centric Scientific Knowledge Graph

Mayank Kejriwal

Bounding Mobile Latency from Network Interconnections

Shefali Tushar Kulkarni, John Heidemann
arXiv preprint arXiv:2610.19156,  2026

ChunkAct: Action Chunking for Agentic Robotics

Bingxin Xu, Wenrui Bao, Xinxin Liu, Jiawei Zhou, Yuzhang Shang, Emilio Ferrara
arXiv preprint arXiv:2610.18874,  2026

Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga

Emilio Ferrara
arXiv preprint arXiv:2610.13840,  2026

A null model to detect coordinated online behavior integrating evidence from multiple indicators

Filipi Nascimento Silva, Manita Pote, Lake Yin, Luca Luceri, Filippo Menczer, Alessandro Flammini
arXiv preprint arXiv:2610.17533,  2026

PEDBench: Can Speech Models Detect Phonetic Errors?

Zhonghao Shi, Zackary Rackauckas, Jasmine Yip, Savannah Halpern, Simon Campos, Lauren Brace, Emma Yang, Tiantian Feng, Xuan Shi, Shrikanth Narayanan, Teresa Satterfield, Ying Xu
arXiv preprint arXiv:2610.20830,  2026

Probing Neural Audio Codecs with Speaker Traits and Speech Characteristics

Jihwan Lee, Tiantian Feng, Minu Kim, Junhyeok Lee, Sean Foley, Thanathai Lertpetchpun, Najim Dehak, Dani Byrd, Shrikanth Narayanan
arXiv preprint arXiv:2610.20955,  2026

Assessments of Credibility in the Social and Behavioral Sciences

Anna Lou Abatayo, Titipat Achakulvisut, Daniel Acuna, Balazs Aczel, Laxmaan Balaji, Anita Bandrowski, DM Benjamin, MM Bishop, GL Brase, AW Brown, M Bush, J Caverlee, T Chakravorti, Y Chen, M Daley, M Dehghani, M Dirzo, A Dreber, P Eckmann, TM Errington, Q Feng, F Fidler, S Field, NW Fox, RD Fraleigh, A Frank, H Fraser, J Gentile, CL Giles, B Goldfedder, P Gooch, M Gordon, E Gould, C Griffin, T Gulden, N Haber, K Hahn, F Holzmeister, XB Hu, Y Huang, M Johannesson, B Kennedy, M Kline Struhl, A Kwasnica, D Lee, K Lerman, Y Liu, A Pearce, I Mandema, A Marcoci, B Mawhinney, S McIntosh, M Mclaughlin, A Menon, O Miske, F Mody, F Morstatter, NS Nakshatri, BA Nosek, MB Nuijten, D Pennock, T Pfeiffer, D Pipkin, J Pujara, S Rajtmajer, M Roelandse, A Russell, P Silverstein, V Singh, CK Soderberg, AM Squicciarini, T Stankov, JW Suchow, B Szaszi, L Tran, PA Vesk, T Vines, CJ Vorland, J Wang, Z Wang, DP Wilkinson, B Wintle, J Wu

Reliability of LLM Judges for Evaluating Entity Alignment

Vaibhava Lakshmi Ravideshik, Mayank Kejriwal
arXiv preprint arXiv:2610.09554,  2026

Efficient Integer-Only Implementation ofĀ Tanh andĀ Sigmoid forĀ Embedded AI onĀ RISC-V

Kamil Kaczmarski, Pawel Gepner, Ewa Deelman, Pawel Poczekajlo, Leonid Moroz, Nataliia Gavkalova
Springer Nature Switzerland,  2026