Information & Intelligence Lab
Overview
Information and Intelligence Lab (iil) is a research group in the Department of Electrical Engineering (and affiliated with the Graduate School of Artificial Intelligence) at Pohang University of Science and Technology (POSTECH).
Our research is centered around the quantification and transmission of information and intelligence. We aim to find fundamental limits, optimal designs, and principled practical implementations of information systems, often by pushing mathematical tools from information theory, coding theory, (convex) optimization, and learning theory in new directions.
Recent News
(02/2025) Code release: "Multiple-masks error correction code transformer for short block codes," IEEE Journal on Selected Areas in Communications (JSAC). [code]
(02/2025) TPC: Invited to serve as a TPC member for IEEE VTC 2025 Spring
(02/2025) Invited talk: "CrossMPT: Cross-attention message-passing transformer for error correcting codes," Information Theory and Applications (ITA) Workshop
(01/2025) TPC: Invited to serve as a TPC member for IEEE Globecom 2025
(01/2025) Accepted paper: "CrossMPT: Cross-attention message-passing transformer for error correcting codes," International Conference on Learning Representations (ICLR), Apr. 2025
(01/2025) Invited talk: "Transformer for communications: Semantic encoder and universal decoder," Workshop on Semantic Communication and AI-RAN for 6G (hosted by IEEE South Australia Section)
(01/2025) Accepted paper: "Multiple-masks error correction code transformer for short block codes," IEEE Journal on Selected Areas in Communications (JSAC) (Special Issue on Rethinking the Information Identification, Representation, and Transmission Pipeline: New Approaches to Data Compression and Communication)
(01/2025) Accepted paper: "Vision transformer-aided importance-aware quantization for digital semantic communications," IEEE International Conference on Communications (ICC), May 2025
(01/2025) Accepted posters: "CrossMPT: Cross-attention message-passing transformer for error correcting codes" and "Robust deep joint source channel coding," IEEE Communication Theory Workshop (CTW) [link]
(12/2024) I will serve as an Editor for IEEE Transactions on Communications (Area: Machine Learning and Communications) [link]
(12/2024) Invited talk: "Transformer for communications: Semantic encoder and universal decoder," Coding and Information Theory Workshop, Hong Kong (hosted by IEEE Hong Kong Section Information Theory Chapter and City University of Hong Kong)
(11/2024) Invited tutorial: "Transformer for communications," KICS Fall Conference (한국통신학회 추계종합학술발표회) [link]
(11/2024) Accepted paper: "Boosted neural decoders: Achieving extreme reliability of LDPC codes for 6G networks," IEEE Journal on Selected Areas in Communications (JSAC) (Special Issue on Next Generation Advanced Transceiver Technologies) [link]
(11/2024) TPC: Invited to serve as a TPC member for IEEE ICC 2025
(10/2024) Code release: "Attention-Aware Semantic Communications for Collaborative Inference," IEEE Internet of Things Journal [link] [code]
(10/2024) Invited talk: "Cross-attention message-passing transformer for error correcting codes," Huawei Theory Lab
(10/2024) Funding: LG Electronics, Optimizing homomorphic computations for transformer models (트랜스포머 모델의 동형 연산 최적화 기법)
(09/2024) Invited talk: "Information theoretic limits on high-bandwidth interconnect," Samsung Global Technology Conference