Workshops

Organizers: Jun Chen, Elza Erkip, Yong Fang, Ezgi Ozyilkan

Recent advances in machine learning and artificial intelligence have brought compression back to the forefront of information science. Once regarded primarily as a tool for efficient data storage and transmission, compression has now emerged as a unifying principle linking representation learning, generalization, and efficient communication. This workshop explores how classical information-theoretic concepts—such as rate- distortion tradeoff, minimum description length, and universal compression—are being reimagined and extended in modern contexts like neural source coding, model compression, semantic communication, and generative AI. It aims to foster dialogue between information theorists and machine learning researchers to examine how compression not only enables efficient inference and transmission but also offers a powerful lens for explaining and designing intelligent systems. The program will feature invited talks, contributed presentations, and panel discussions that bridge theory and practice, laying the groundwork for the next generation of compression-inspired learning and communication paradigms.

Organizers: Venkata Gandikota, Ling Liu, Shanxiang Lyu

This workshop focuses on coding theory as a unifying foundation for post-quantum cryptography (PQC) and quantum reliability, highlighting how classical codes, lattices, and decoding algorithms underpin both quantum-safe security and fault-tolerant quantum information processing. The workshop aims to bring together researchers from information theory, coding theory, post-quantum cryptography, and quantum error correction to explore shared mathematical structures and algorithmic principles.

Organizers: Yingbin Liang, Jiantao Jiao, Yuheng Bu, Haiyun He, Ziqiao Wang, Peng Wang

Topics (including but not limited to): IT for GenAI (Generalization, Representation, and Reasoning; Compression, Rate-Distortion, and Efficiency; Trustworthiness, Robustness and Security), GenAI for IT (AI Agents for Research; Learning for Classical IT Problems; Modeling, Simulation and Algorithm Design)

Organizers: Rishabh Dudeja, Zhenyu Liao, Junjie Ma, Arian Maleki

High-dimensional learning and inference have recently seen major theoretical advances showing that both learning performance and algorithmic dynamics obey universal mean-field laws. Dynamical mean-field theory provides exact asymptotic descriptions for algorithms such as (stochastic) gradient descent and Langevin dynamics, while Gaussian equivalence and random matrix techniques simplify complex nonlinear random-feature and kernel models into
tractable Gaussian surrogates. At the same time, universality and state-evolution analyses for approximate message passing (AMP) and related iterative algorithms, together with new insights into prediction risk and data influence, demonstrate that many seemingly different procedures are governed by the same low-dimensional order parameters. We invite participation in the Universality and Dynamics in High-Dimensional Learning and Inference Workshop at ISIT 2026. This workshop aims to bring together researchers from information theory, machine learning (ML), high-dimensional statistics, random matrix theory, and statistical physics, to develop a unified view of these advances.

Organizers: Khaled B. Letaif, Xinping Yi, Hong Xing, Yunchuan Zhang

Advanced machine learning (ML) models are increasingly deployed in task-critical industrial scenarios, e.g., smart factory, autonomous vehicle/drone/robot networks, with embodied intelligence through wireless interface that integrate computer vision, pattern recognition, sensing, communications and mobile computing. Wireless environment is non-stationary with spatial-temporal varying channels, information feedback distortion, and hardware impairments. These factors make embodied intelligence more challenging, bringing risks such as unpredictable outage during mobility events, unsafe robots navigation due to misspecified models, and corrupted multi-agent coordination due to misaligned scheduling policy. This workshop invites researchers and industry practitioners to present novel theory, performance analysis, and architectural insights that advance deployment- time reliability guarantees of embodied intelligence in wireless networks.

Organizers: Lei Liu, Yuhao Chi, Yao Ge

With the rapid expansion of high-mobility applications, ensuring reliable communication in rapidly time-varying environments has become a critical challenge. Conventional Orthogonal Frequency Division Multiplexing (OFDM) suffers pronounced degradation in such dynamic scenarios, underscoring the urgent necessity for next-generation modulation waveforms. Consequently, emerging multicarrier schemes—including orthogonal time frequency space (OTFS), orthogonal delay division multiplexing (ODDM), orthogonal chirp division multiplexing (OCDM), affine frequency division multiplexing (AFDM), interleave frequency division multiplexing (IFDM), and random multiplexing (RM)—have provided new perspectives for robust system design. This workshop highlights core waveform design challenges at the intersection of information theory and wireless communication, aiming to bridge theory and practice to spur innovation.

Organizers: Xiao Ma, Richard Wesel, Linqi Song

Since Shannon’s seminal work, coding theory has been a central pillar of information theory and has powered generations of communication systems. Looking ahead, infor- mation processing and communication is moving beyond the classical AWGN-centric paradigm and is increasingly shaped by application-driven requirements. Emerging sce- narios call for advances in coding theory and coded modulation across: i) advanced waveforms such as OTFS, FTN, ODDM, and AFDM exploit delay–Doppler or time– frequency diversity but require waveform-aware code design and decoding; ii) inte- grated sensing and communication (ISAC) systems call for coding strategies that jointly guarantee reliable data delivery and accurate sensing/localization, motivating new trade-off analyses and unified frameworks; iii) coded computing underpins dis- tributed learning, large-scale data processing, and storage by providing straggler re- silience, fault tolerance, and low-latency operation; iv) multi-user access, including NOMA, RSMA, and massive random access, requires both new multi-user code con- structions and the adaptation of classical single-user codes to joint detection/decoding; v) AI-native systems demand information-theoretic and coding tools for compression, efficient/robust training, and interpretability.

Organizers: Xueyan Niu, Jun Chen, Bo Bai

The IT4LLM workshop explores the intersection of infor- mation theory and large language models (LLMs), unit- ing researchers to advance both theoretical understand- ing and practical applications. Contemporary AI sys- tems, particularly LLMs, have demonstrated remarkable capabilities, yet they often function as “black boxes,” un- dermining trust, fairness, and efficiency. This workshop will explore information theory as a principled frame- work to advance both the capabilities and interpretability of LLMs, addressing fundamental questions about how information-theoretic principles can guide the develop- ment, optimization, and interpretation of these models.

By integrating core information-theoretic concepts into the design and analysis of LLMs, we aim to deepen our understanding of their behavior, efficiency, and inherent limitations. The interdisciplinary gathering fosters col- laboration between information theorists and machine learning researchers, seeking to uncover how informa- tion theory can provide fundamental insights into the ca- pabilities and limitations of LLMs while simultaneously enhancing their transparency and performance.