Monday

NikolaPigeonMariePierre
Coding and Sensing (INV)


Mario Diaz Memorial 1 (INV)


Machine Learning


Wireless Communications



10:40 AMSubspace Coding for Spatial Sensing

Robin Rajamäki

Remembering Mario

Universality of kernel random matrices and kernel regression in the quadratic regime

Zhichao Wang

Active Beam Learning for Full-Duplex Wireless Systems

Ian Roberts

11:00 AMFrom Quantum Sensing to Classical Weight Enumerators

Narayanan Rengaswamy

Can we catch two birds of privacy and fairness?

Haewon Jeong

Shallow diffusion networks provably learn hidden low-dimensional structure

Stephen Tu

Quantization for optimal UAV Network Deployment

Hamid Jafarkhani

11:20 AMJoint Communication and Sensing beyond i.i.d. and Static Models

Matthieu Bloch

Towards Optimal Privacy Mechanisms Under Estimated Sensitivity

James Melbourne

Sparse recovery of binary vectors

Neha Sangwan

On pulse shaping filters and I/O relation estimation & equalization in Zak-OTFS

Ananthanarayanan Chockalingam

11:40 AMEquivalence Principles for Nonlinear Random Matrices in High-Dimensional Estimation and Learning

Yue Lu

Auditing Privacy of Additive Noise Mechanisms Using Linear Predictive Models

Lalitha Sankar

Perceptual adjustment queries:Learning from slider data

Jingyan Wang

AI for Autonomous Robot Systems (INV)


Coding Theory


Mario Diaz Memorial 2 (INV)


Online Algorithms and Security



2:00 PMBuilding Robust Intelligence: A Continuous Domain Adaptation Strategy

Salimeh Sekeh

Undetected Error Probability in the Short Blocklength Regime: Codes and (New) Bounds

Gianluigi Liva

Peter Kairouz

Linear Elastic Caching via Ski Rental

Manish Purohit

2:20 PMModel-Free, Position-Free Acoustic Signal Source Seeking in Cluttered Environments

Zahra Nili Ahmadabadi

Fair-Density Parity-Check Codes

Hessam Mahdavifar

Shahab Asoodeh

Online bookmaking

Oron Sabag

2:40 PMFoundation Model to Intelligence Embodiment

Xueyan Zou

Using Linearity to Lower List Decoder Complexity

Rick Wesel

Anand Sarwate

Realizable Mis-specified Universal Learning

Meir Feder

3:00 PMActive initialization for Gaussian splatting

Konstantinos Polyzos

Uncorrelated optimal ZCZ sequences always come from Popovic construction

Hong-Yeop Song

Reveal-or-Obscure: A Differentially Private Sampling Algorithm for Discrete Distributions

Oliver Kosut

Queueing the Threats: A New Lens on Attack Surface Dynamics

Emre Koksal

LLMs


Error Correcting Codes


Privacy and Secret Sharing




3:40 PMTransformers Learn Causal structure

Jason Lee

Error correction in interference-limited wireless systems

Charles Wiame

Optimal Computational Secret Sharing

Rafael D'Oliveira

4:00 PMAI-Written or Human-Edited? Detecting Text Edits with Higher Criticism and Information Theory

Alon Kipnis

High-Rate Spatially Coupled LDPC Codes Derived From Convolutional Self-Orthogonal Codes

Daniel Costello

Differentially Private Distributed Inference

Amin Rahimian

4:20 PMTheoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach

Haiyun He

Laplacian-ORBGRAND: Decoding for Impulsive Noise

Jiewei Feng

An Extension of the Adversarial Threat Model in Quantitative Information Flow

Parastoo Sadeghi

4:40 PMSufficient Context: A New Lens on Retrieval Augmented Generation Systems

Cyrus Rashtchian

Mixed-Integer ADMM Decoding for LDPC codes

Stark Draper

Compression of Differentially Private Mechanisms via Channel Simulation

Cheuk Ting Li

Tuesday

NikolaPigeonMariePierre
Sequential and Reinforcement Learning


Quantum Computing and IT


Quantum Error Correction (INV)




10:40 AMSequential Hypothesis Testing via No-Regret Learning

Jun-Kun Wang

Information-theoretic adversarial communication: preventing disinformation from becoming misinformation

Jody O'Sullivan

Design of Finite-Length Lifted Product Quantum LDPC Codes

Bane Vasic

11:00 AMOptimal Multi-Objective Best Arm Identification with Fixed Confidence

Vincent Tan

Information Velocity of Cascaded Gaussian Channels with Feedback

Yuval Kochman

Reed-Muller Codes on Classical-Quantum Channels and the Holevo Capacity

Henry Pfister

11:20 AMDOPL: Direct Online Preference Learning for Restless Multi-Armed Bandits with Preference Feedback

Jian Li

On the Capacity of Linear Computations over Quantum Many to One Networks

Syed Jafar

Cluster Decomposition for Improved Erasure Decoding of Quantum LDPC Codes

Hanwen Yao

11:40 AMAchieving Safe and Robust Policy Improvement in Offline safe Reinforcement Learning

Honghao Wei

Pauli measurements are not optimal for single-copy tomography

Yuhan Liu

Low Latency Decoding for Quantum LDPC Codes

Nithin Raveendran

Statistics


Wireless Communications 1


Polar Codes




2:00 PMOn Estimation of ROC curves from Likelihood Ratio Observations

Bruce Hajek

Advanced Receivers for 5G and 6G

Dongwoon Bai

In Search Of the Best Dimension 128 Lattice: Construction A

Brian Kurkoski

2:20 PMSharp trajectory predictions for iterative nonconvex optimization with random data

Kabir Verchand

User Scheduling Optimization with Enhanced Time Division Duplex Slot Allocation in Non-Terrestrial Networks

Michele Zorzi

Data-driven approach for capacity estimation and polar codes

Haim Permuter

2:40 PMNon-convex matrix sensing: Breaking the quadratic rank barrier in the sample complexity

Yizhe Zhu

CrossMPT: Cross-Attention Message-Passing Transformer for Error Correcting Codes

Yongjune Kim

Neural Polar Decoders for Deletion Channels

Ziv Aharoni

3:00 PMA sliced Wasserstein and diffusion approach to random coefficient models

Fang Han

DEFINED: A Transformer-based Signal Detector over Fading Channels

Cong Shen

Statistical Learning


Wireless Communications 2


Coding Applications




3:40 PMBayesian Estimation of a Probability Mass Function Tensor with Automatic Rank Detection

Martin Haardt

Integrated Communication and Sensing Systems in High Mobility Environments

Athina Petropulu

Capacity Approximations for Insertion Channels with Small Insertion Probabilities

Busra Tegin

4:00 PMStatistical curriculum learning: An elimination algorithm achieving an oracle risk

Nir Weinberger

Uberize Wireless Multiple Access Control

Wei Wang

Short Blocklength Codes for Correcting Random Edit Errors in DNA Storage

Serge Kas Hanna

4:20 PMSimple binary hypothesis testing: One-shot Bayes error bounds and reverse data-processing inequalities

Varun Jog

The Pulse-Shaping Trojan: A New Security Threat in Wireless Communication

Aria Nosratinia

Analog Error-Correcting Codes for AI Computing

Anxiao Jiang

4:40 PMA Theoretical Framework for Transfer Learning via High-Dimensional Statistical Analysis

Shao-Lun Huang

Realizing Full-Duplex Wireless Systems through Beamforming

Ian Roberts

Learning to Decode GLDPC Codes: Policy Evaluation and Q-learning

David Mitchell

Wednesday

NikolaPigeonMariePierre
Privacy


ML Theory


ML Applications




9:00 AMCorrelated Privacy Mechanisms for Differentially Private Distributed Mean Estimation

Sajani Vithana

Exploration-exploitation trade-off in sequential lossy compression

Ram Zamir

ML on high-dimensional data for personalized clinician-in-loop care

David Scheinker

9:20 AMTradeoffs in data memorization: Learn more to remember less

Vitaly Feldman

Re-examing double descent and scaling law under norm-based capacity

Fanghui Liu

How do neural networks learn features from data?

Adityanarayanan Radhakrishnan

9:40 AMOn the Dichotomy Between Privacy and Traceability in Stochastic Convex Optimization

Mahdi Haghifam

Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes

Yu-Xiang Wang

10:00 AMDifferentially private estimation via first- and second-order optimization

Po-Ling Loh

Graduation Day Talks 1


Graduation Day Talks 2


Graduation Day Talks 3




10:40 AMOptimized Couplings for Watermarking Large Language Models

Dor Tsur

Data-Driven Causal Discovery with Asymmetric Error Control

Joni Shaska

Learning the Structure of Networked Systems that Obey Conservation Laws

Anirudh Rayas

11:00 AMUnderstanding Language Models: Optimization, Architecture and Emergent Abilities

Yingcong Li

Active sampling for Markov hypothesis testing

Greg Fields

Non-rational infinite-horizon control: a unified framework for (distributionally) robust control and beyond

Taylan Kargin

11:20 AMEarly Directional Convergence in Homogeneous Neural Networks

Akshay Kumar

Identifying Causal Effects Under Functional Dependencies

Yizuo Chen

Intelligent Communication Planning for Constrained Environmental IoT Sensing with Reinforcement Learning

Yi Hu

11:40 AMModel-Free Robust ϕ-Divergence Reinforcement Learning Using Both Offline and Online Data

Kishan Panaganti

Optimal Transport and Robust Statistics

Sloan Nietert

Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration

Mahdi Morafah






Thursday

NikolaPigeonMariePierre
AI Institutes 1 (INV)


Interpretability and Safety


Reinforcement and Distributed Learning


Control



10:40 AMDistributed Constrained Combinatorial Optimization leveraging Hypergraph Neural Networks

Farinaz Koushanfar

Enhancing Hallucination Detection through Noise Injection

Litian Liu

Constrained Multi-objective Bayesian Optimization through Optimistic Constraints Estimation

Chong Liu

Minimum Data-Rate for Emulating a Linear System

Girish Nair

11:00 AMToward optimal neural compressors for the rate distortion perception tradeoff

Shirin Saeedi Bidokhti

Scaling Explainability: Fast Algorithms to Decode Ever-Growing ML Models

Amirali Aghazadeh

The Sample-Communication Complexity Trade-off in Federated Q-Learning

Sudeep Salgia

Identification of Analytic Nonlinear Dynamical Systems with Non-asymptotic Guarantees

Yingying Li

11:20 AMFederated Optimization for Multi-task Learning

Gauri Joshi

Model reconstruction using counterfactual explanations: A perspective from polytope theory

Sanghamitra Dutta

Communication Compression for Distributed Learning without Control Variates

Tomas Ortega

Protect or prevent: Optimal vaccine priorities for infectious diseases

Saswati Sarkar

11:40 AMFinite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning

Jia (Kevin) Liu

Implicit Geometry of Semantics in Next-Token Prediction Models

Christos Thrampoulidis

AI Institutes 2 (INV)


Learning and Statistics


Reinforcement Learning


Game Theory



2:00 PMTheory on Vision Transformers in Self-Supervised Learning

Yingbin Liang

Expectations in Expectation Propagation

Dirk Slock

Generative Multi-Agent Q-Learning for Policy Optimization: Decentralized Wireless Networks

Urbashi Mitra

Beyond worst-case equilibria in games

Philip Brown

2:20 PMIncentive Mechanisms with Sequential Voluntary Participation

Mingyan Liu

Frequentist Guarantees of Distributed (Non)-Bayesian Inference

Bohan Wu

Lifelong Linear Bandits via Representation Transfer: Is Task Diversity Essential?

Zhi Wang

Virtual Democracy: Automating Ethical Decision-Making

Anson Kahng

2:40 PMEstimation via Stochastic Mirror Descent

Tara Javidi

PAC Learning is just Bipartite Matching (sort of)

Shaddin Dughmi

Structured Reinforcement Learning for Wireless Networks

Archana Bura

Some emerging issues in spectrum sharing

Randall Berry

3:00 PMTrans-Glasso: A Transfer Learning Approach for Precision Matrix Estimation

Mladen Kolar

Information Theory and ML


Efficient LLMs and Alignment



Graphs



3:40 PMGeneralized Fenchel-Young Divergence

Lav Varshney

DeepCrossAttention: Supercharging transformer residual connections

Adel Javanmard

Structure Learning in Gaussian Graphical Models from Glauber Dynamics

Gautam Dasarathy

4:00 PMInformation-theoretic quantification of inherent discrimination bias in training data for supervised learning

Mohamed Nafea

Speeding up Speculative Decoding for LLMs via Approximate Verification

Ravi Tandon

Competitive networked bivirus SIS spread over hypergraphs

Sebin Jose Gracy

4:20 PMInference Time Alignment of Large Language Models

Amrit Singh Bedi

Characterization of Planted Tree Problems via Local Weak Convergence

Mehrdad Moharrami

4:40 PMInfAlign: Inference-aware language model alignment

Ahmad Beirami

On the Lovasz Function and Shannon Capacity of Regular Graphs

Igal Sason

Friday

NikolaPigeonMariePierre
Machine Learning and Efficiency


Neural Networks


Privacy


Wireless and Age of Information



10:40 AMStairway to Specialization: The Path of Scalable Experts

Grigorios Chrysos

Weak to Strong Generalization in Random Feature Models

Nathan Srebro

Denoising of Differentially Private Optimizers

Meisam Razaviyayn

Enhancing mm-Wave and THz Indoor Links with Passive Reflectors and LiDAR-Assisted Adaptive Beamforming

Mohammed E Eltayeb

11:00 AMInduced Model Matching: Restricted Models Help Train Full-Featured Models

Mesrob Ohannessian

Hard-Constrained Neural Networks with Universal Approximation Guarantees

Navid Azizan

Privacy for Free in the Over-Parameterized Regime

Marco Mondelli

Optimizing Age of Information without Knowing the Age of Information

Igor Kadota

11:20 AMWeak-to-Strong Generalization Through the Data-Centric Lens

Fred Sala

Dependence Induced Representation Learning

Xiangxiang Xu

Dimension-free Private Mean Estimation

Lydia Zakynthinou

Timely Communications based on Data Significance

Yin Sun

11:40 AMPAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment

Ramya Korlakai Vinayak

AttnMod: Attention-based New Art Style

Jessy Su

Machine Learning


Estimation and Clustering


Random Processes and Coding


Startup Stories (INV)



2:00 PMTraining Dynamics of Softmax Self-Attention: Global Convergence and Neural Scaling Laws

Gautam Goel

Lq Lower Bounds on Distributed Estimation via Fisher Information

Ayfer Ozgur

Mixing Time of the Proximal Sampler in Relative Fisher Information via Strong Data Processing Inequality

Andre Wibisono

From Bits to Billions: Startups Architecting the Next Wave of AI Infrastructure

Cyril Gorlla

2:20 PMRecent Advances in Drone Vision

Sedat Ozer

1+o(1) Optimal Mean Estimation Beyond One Dimension

Paul Valiant

Entropy Quantification in True Random Number Generators via Gaussian Process Phase Noise Models

Maciej Skorski

Startup stories, part 2

Arun Kumar

2:40 PMModular Duality in Deep Learning

Jeremy Bernstein

Tight Clusters Make Specialized Experts

Tan Nguyen

Can coding reduce fragmentation in deduplicated storage systems?

Ilan Shomorony

Startup stories, part 3

Brad Chisum

3:00 PMDiscovering Data Structures: Nearest Neighbor Search and Beyond

Vatsal Sharan

Game of Coding: Sybil Resistant Decentralized Machine Learning with Minimal Trust Assumption

Viveck Cadambe