Affinity Event Tue, Jul 7, 2026 • 4:00 PM – 1:00 AM PDT ROOM E1 - E4 (3rd Floor)

WiML Symposium at ICML 2026

Li Zhang ⋅ Belen Martin Urcelay ⋅ Charlotte Gerhaher ⋅ Minseon Kim ⋅ Haneul Yoo ⋅ Irene Ballester Campos

Project Page

Abstract

The Women in Machine Learning (WiML) workshop was founded in 2006 to forge connections within the relatively small community of women working in machine learning, to encourage mentorship and exchange of ideas, and to promote communication. The workshop attracts representatives from academia and industry, whose contributed talks showcase some of the cutting-edge research done by women. In addition to technical presentations and discussions, the workshop aims to incite debate on promising research avenues and career choices for machine learning professionals. Details about WiML’s history and past events can be found at http://womeninml.org/. WiML workshops are overseen by the WiML Board of Directors, who select and oversee the organizing committee for each year’s workshop.

Schedule

Timezone: America/Los_Angeles

6:00 PM

Introduction & Opening Remarks

6:15 PM

Talk1

6:40 PM

Talk2

7:05 PM

Talk3

7:45 PM

Panel Discussion: Career transitions in ML

8:40 PM

Panel Breakout Q&A with the Speakers

8:40 PM

Panel Breakout Q&A with the Speakers

9:30 PM

Mentor & Sponsor Round Tables

10:30 PM

Panel Discussion: What does research look like when AI does research?

→ Semantic Graphs for Jailbreak Detection: Structure, Transferability, and Fairness

Shanu Sushmita

→ Attractor Momentum: Narrative Pattern Completion as a Mechanism for LLM Safety Failures

Carla Troper

→ Adversarial Robustness in Time Series Classification: Curriculum Training, Recurrent Resilience, and a Multi-Architecture Benchmark

Khalida Mir Alam

→ When Graph Reranking Narrows the Retrieved Evidence Space

Min Zhang

→ Scaling E-commerce Dense Retrieval with Unified Semantic and Behavioral Supervision

Isha Shah

→ Deep Learning-Based Mycobacterium Tuberculosis Bacterial Growth Detection for Antimicrobial Susceptibility Testing

Thuy Nguyen

→ Q-Learning-Assisted DE and PSO for Enhanced Dose Planning in Radiotherapy

Devika Gautam

→ A Comparative Study of Molecular Dynamics Approaches for Simulating Ionic Conductivity in Solid Lithium Electrolytes

Dounia Shaaban Kabakibo

→ Deep neural networks divide and conquer dihedral multiplication

Sihui Wei

→ Where the Model Looks: Uncovering Racial and Gender Bias in Vision-Language Models Through Visual Attribution

Tesnim Gulsen

→ ECSEL: Explainable Classification via Signomial Equation Learning

Adia C. Lumadjeng

→ RAIGen: Rare Attribute Identification in Text-to-Image Generative Models

Silpa Vadakkeeveetil Sreelatha

→ Astro-UNETR: Segmenting Superbubbles in a Simulated Multiphase Interstellar Medium

Jing-Wen Chen

→ To Augment or Not to Augment? Diagnosing Distributional Symmetry Breaking

Hannah Lawrence

→ Anatomically-Guided Patches for Joint KL and OARSI Grading of Knee Osteoarthritis

Tzu-Tsen Hsieh

→ Conceptual Routing for Efficient Continual Learning of Pretrained Vision Models

Shruthi Gowda

→ Controllable Concept Interventions for Stress-Testing Video World Models

Nahid Alam

→ $\PSI$DAG: Projected Stochastic Approximation Iteration for Linear DAG Structure Learning

Klea Ziu

→ Consumption Diversity in Combinatorial Semi-Bandits

Ruo-Chun Tzeng

→ Selective Critique for Cost-Aware LLM Agent Reasoning

Heewon Park

→ Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub

Eunsu Kim

→ Bargaining Over Bias: Cooperative Contracts for AI Fairness

Aishika Manu ⋅ Pratishtha Batra

→ When Reasoning Collapses: A Depth-Aware Probe into LLM Reasoning

Azka Ikramullah

→ Effective Distillation to Hybrid xLSTM Architectures

Anamaria-Roberta Hartl

→ On the Selectivty of Generative Models in Structure-Based Drug Design

Jungyoon Lee

→ Cost-Asymmetric Graph Attention Networks for VAT Fraud Detection in Imbalanced Transaction Networks

AMAL AARAB

→ What Do Chart Question Answering Benchmarks Measure? Task-Specific Visual Evidence Dependence in Vision-Language Models

Mary Le

→ From Accuracy to Visual Dependence: Auditing and Filtering Modality Collapse in Traffic VideoQA

Sena Korkut

→ Towards Predictive Models of Strategic Behaviour in Large Language Model Agents

Jennifer Za Nzambi

→ Between Rule Induction and Retrieval: In-Context Arithmetic in Llama-3.1-8B

Bianca-Mihaela Ganescu

→ Evaluating Large Language Models and Neural Machine Translation Models on Yoruba Idiomatic Expressions

Joy Olusanya

→ Diffusion Forcing for Multi-Agent Interaction Sequence Modeling

Vongani Maluleke

→ An Empirical Study of Architectural Trade-offs in Vision-Based Traffic Sign Interpretation Systems

Su Myat Noe

→ Q-SOAP: Quantized Second-Order Optimization for Memory-Efficient LLM Training

Beheshteh Toloueirakhshan

→ TemporalSAEBench: Evaluating Sparse Autoencoders on Temporal Data

Angela van Sprang ⋅ Ege Erdogan

→ Transferable Lesion-Supervised Speech Representations for Post-Stroke Modelling

Giulia Sanguedolce

→ Using Deep Learning for Earthquake Detection

Grace Gong

→ Simplifying Kalman Filter Tuning via Online Noise Adaptation for Quadruped State Estimation

Mihaela Popescu

→ LLM Self-play in Diplomacy

Sujin Yun

→ Probably Reduced Sample Complexity in Hyperparameter Optimization

Leona Hennig

→ Quantifying Symmetries: How Optimisers Impact the Functional Dimension

Johanna Marie Gegenfurtner

→ Active Reinforcement Learning for Efficient Calibration of Digital Twins

Vladyslava Spitkovska

→ Drift-Aware Coordination for Long-Horizon LLM-Based Multi-Agent Systems

Sangeun Park

→ Unmasking the Hidden Fairness, Bias, and Safety Costs of Compression with Mixture-of-Expert Models

Elizabeth Szentmiklossy

→ CB-SLICE: Concept-Based Interpretable Error Slice Discovery

Yael Konforti

→ Compact Merging of Vision-Language-Action Models: Shared Cores and Spectral Residuals

Kyungjin Im

Link

→ Block Redundancy in Tabular Foundation Models for Clinical Applications

Irene Cannistraci

→ Multimodal Brain Tumor Detection via CT–MRI Fusion Using EfficientNetB4

Racheal S. Akinbo

→ Task-specific Subnetwork Discovery in Reinforcement Learning for Autonomous Underwater Navigation

Yi-Ling Liu

→ Are Explanations Faithful Across Skin Tones? \\Assessing Foundation-Model Dermatology Classifiers

Rosa Y. G. Paccotacya-Yanque

→ Formalizing and Falsifying Causal Pathways of Rare Events

Anahita Haghighat

→ A Two-Dimensional Attention-Weighted Offline Evaluation Framework for Carousel Based Recommender Systems

Ashwaq Salim

→ ShiftBench: A Benchmark for Per-Cohort Certify-or-Abstain Decisions on Positive Predictive Value Under Covariate Shift

Ananya Salian

→ One Backbone, Two Flood Hazards: Cross-Basin CNN Forecasting of Tropical Cyclone Rainfall and Storm Surge

Jeni Mei

→ Accelerated and Stable Convergence with Anchored Optimistic Methods

Motahareh Sohrabi

→ From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives

Chloe Ho ⋅ Arjun Bahuguna

→ Minibinder Lab: The Reliability Gap Of Agents For Designing High Quality Protein Binders

Anda-Raluca Epure

→ Beyond Degree: Fair Link Recommendation via Coreness

Elif Ece Erdem

→ Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres

Muskan Dosi

→ Text-Guided ROI Refinement for Semantic Brain Tumor Segmentation in MRI

Somayeh Davar

→ Cache Coherent Resampling for Efficient Test Time Scaling in LLM Reasoning via Adaptive Sequential Monte Carlo

Ke Wang

→ Asymmetric Semantic Recoverability in Sparse Autoencoder Features

Prerna Luthra

→ RM-Quest: Quantile-Guided Coreset Selection via Sparse Adversarial Representation Margins

Manasa Madabhushi

→ Fine-Tuning YOLO26 for Outer and Inner Cochlear Hair Cell Detection

Yukiko Hughes

→ Activation Editing for Low-Resource Cross-Lingual Machine Translation: Does JoLA Transfer?

Erika Germinario

→ Don’t Explore What You Already Know: Pattern-Seeking Exploration via Temporal Invariance

Jin Schofield

→ Human Causal Reasoning as Finite-State Dynamics: Implications for Neurosymbolic AI

Rachel Papirmeister

→ Early Detection of Paroxysmal Nocturnal Hemoglobinuria from Routine Laboratory Data Using Machine Learning

Chi-en Amy Tai

→ CAVEWOMAN: Two-Channel Evaluation of Linguistic Compression in Large Language Model Inference

Morayo Danielle Adeyemi

→ Diagnosing How Scientific Reasoning Fails: A Benchmark for Qualifier and Rebuttal Errors

Helen Jin

→ Trajectory-Based Confidence for Efficient Hint Retrieval in Agentic SLMs

Yimeng (Yoyo) Liu

→ Conditional Diffusion-Based EEG Channel Reconstruction for Motor Imagery Decoding

Sharon C Quispe

→ A Unified Shapley-Based Framework for Adaptive Privacy and Fair Rewarding in Federated Learning

Zahra Batool

→ A Mechanistic View of Authority Hierarchy in LLM Sycophancy

Srujananjali Medicherla

→ GOODPOINT: Learning Constructive Scientific Paper Feedback from Author Responses

Chani Jung

→ A Framework for Quantifying Metacognitive Skills in LLM Reasoning Traces

Sandani S. Fernando

→ Reference-Free Detection of Novel Pathogens in Wastewater Using Genomic Foundation Model Embeddings

Divya Sitani

→ On the Failure of Synthetic Mixing for Real-World SceneFake Detection

Jiya Sinha

→ JuICE: A Benchmark for Evaluating LLM-Judge in Identifying Cultural Errors

Jiho Jin ⋅ Junyeong Park

→ Quantifying Temperature Scaling in Discrete Sequence (Language) Models

Hannah Scheufele

→ Fair Learning with Biased Labels: When Observed Accuracy Is the Wrong Target

Heng-Chien Liou

→ Who Counts as Evidence-Based? Knowledge Practices in British and Swiss Parliamentary Speech

Afagh Mulazadeh

→ Stabilizing In-Context Multi-Source Domain Adaptation for Biomedical Images Through Controls

Ana Sanchez Fernandez

→ Interventionist Metacognition: Implementing Nelson–Narens Monitoring–Control Theory in an LLM Agent

Poli Nemkova

→ Fairness-Aware Representation Learning for ECG-Based Disease Prediction in Wearable Systems

Farjana Yesmin

→ Physics-Guided Evolving Neuro-Fuzzy Systems for Interpretable Battery State-of-Health Estimation

Hafsaa Ouifak ⋅ Ahmed BEN DAOUIA

→ Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind

Vaidehi Patil

→ VChain: Chain-of-Visual-Thought for Reasoning in Video Generation

Ziqi Huang

→ Singular Bayesian Neural Network

Mame Diarra Toure

Link

→ Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity

Aneri Muni

→ Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations

Narges Babadi

→ CoCo: Collaborate via Coarsening for Personalized Federated Graph Learning

Nikita Malik

→ HINT: Task Demonstrations for Hierarchical Inference in Abstract Reasoning

→ Benchmarking privacy leakage in multi-agent systems

Soumya Sharma

→ SCoPE: Sampling with Confidence via Predictive Information for Local Explanations

Sumedha Chugh

→ Can Large Language Models Generalize Procedures Across Representations?

Fangru Lin

→ VideoSense AI: Agentic Comment-Based Quality Assessment of Online Videos Using Tree-of-Thought Reasoning and Semantic Retrieval

Mopock Talla Ceverine Thaliitha

→ Behavioral Determinants of Deployed AI Agents in Social Networks: A Multi-Factor Study of Personality, Model, and Guardrail Specification

Sarah Wilson

Link

→ Synthetic Personalities: Probing Behavioral Identity Stability Across Long-Context Dialogue Models

Meriem Mehri

→ Individually Fair Correlation Clustering

Binita Maity

→ Healing in One's Own Tongue: A Fine-tuned LLM-Powered Speech-to-Speech Translation System for Ethiopian Healthcare

Rahel Mekonen Tamiru

→ A Theoretical and Empirical Taxonomy of Imbalance in Binary Classification

Rose Yvette Bandolo Essomba

→ Hierarchial Benchmark for Vision-Language Understanding of 3D scenes

Roshani Poudel

→ Optimality-Based Vision-Language-Action Fine-Tuned Model for Whole-Body Humanoid Robots

Melya Boukheddimi

→ Compute-Aware Mixture-of-Agents: Verifier-Gated Adaptive Aggregation under a Fixed Token Budget

Shine Gupta

→ MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs

Huiyi Chen

→ AfriVTON-Bench: Evaluating the Robustness of Virtual Try-On Models to African Textile Patterns and Garment Structures

Shiloh Oni

→ BreastXNet: A Bio-Inspired Lightweight Explainable Ensemble Framework for Breast Cancer Histopathology Classification in Resource-Constrained Clinical Environments

Roseline Oluwaseun Ogundokun

→ MANGO: Meta-Adaptive Network Gradient Optimization for Online Continual Learning

Ankita Awasthi

→ Comparing Classical and Deep Learning Approaches for Early Sepsis Prediction with Model-Specific Explainability

Anna Rechkalova ⋅ Dmytro Kuzmenko

→ SCRUB: Feature Collapse and Partial Signal Recovery in Gloved-Hand Pose Estimation

Waverly Rose Brim

→ FUSE-AD: Foundation-Model Unified Semantic Embeddings for Binary Alzheimer’s Disease Classification from MRI and FDG-PET.

Modupe Odusami

→ Multi-view Multi-label Canonical Correlation Analysis with Dual Correlations for Cross-modal Multimedia Retrieval

Asha Rani

→ Benchmarking Machine Learning Algorithms for Groundwater Contamination Vulnerability Prediction Using Hydrogeophysical Indicators in Ibadan, Nigeria

OLUWAKEMI OLUKAYODE

→ SicklePrenatal: Biometric-Guided Deep Learning for Early Sickle Cell Risk Detection

Maqsudhat Bisiriyu

→ TO KEEP OR TO FORGET: TOWARD CONTEXTSENSITIVE MEMORY IN LARGE LANGUAGE MODELS

→ Continual learning with world model-based interactions for embodied learning

Sharmita Dey

→ When Questions Override Images: Diagnosing and Mitigating Language Reliance in Medical Visual QA

Mansi Dhamne

→ Individualized and Subtype-Aware Representation Learning in Biomedical Data

Sai Spandana Chintapalli

→ Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attacks on Breast Ultrasound Images

Yasamin Medghalchi

→ Closing the Lineage Gap: Machine Learning for MDR-TB Drug Resistance Prediction in Nigerian Clinical Isolates

Abioye Delight

→ FedGreenTopics: Federated and Energy-Aware Topic Modelling for Distributed Nigerian Music Archives

→ When Should Pre-Sleep Monitoring Begin? An Explainable Evaluation of Temporal Windows for Sleep Fragmentation Prediction

Adaora Obayi

→ Active query synthesis for preference learning

Namrata Nadagouda

→ Geographic Imbalance and Spatial Generalisation in Machine Learning for Global Water-Quality Prediction

Sushma Kumari

→ Persistent Recourse: Topology-Constrained Counterfactual Explanations with Stability Guarantees

Sita Bissu ⋅ Navnit Kumar Yadav

→ AdaCRAD: Adaptive Compression via Representation-Aware Drift for Ranking Preservation in AIGC-IQA

Sreejita Roy

→ Spatio-Temporal Paradox of 2D Priors: Evidential Feature Gating for Robust 3D Occupancy Prediction

Umme Rubaiyat Chowdhury

→ Ray-Conditioned Attention for Geometry-Aware 360° Panoramic Depth Estimation

Kimberly Grace Sevillano Colina

→ Benchmarking LLMs for Predictive Applications in the Intensive Care Units

Chehak Malhotra

→ Fairness-Aware Demand Estimation for Paratransit Networks: Lessons from Inclusive Mobility Planning in Ibadan, Nigeria

Daniella Ojekere

→ Learning to Detect Hardcoded Secrets

Farnaz Soltaniani

→ Human AI Cooperation for Stigma Sensitive Health Education Content Generation for Women in Situations of Sex Work

Tia Dwi Setiani

→ SENTIMENT ANALYSIS WITH CONTRASTING WORDS: COMPARISON OF DEEP LEARNING ALGORITHMS

Adenike T Odegbile

→ CREST: Covariate-Regularized Emission Forecasting with Seasonal-Temporal Decomposition for Carbon Prediction

Anushka Chaubey ⋅ Tushar Shinde

→ OFMU: OPTIMIZATION-DRIVEN FRAMEWORK FOR MACHINE UNLEARNING

Sadia Asif

→ Mechanistic Interpretability of Attention Heads in Long-Context Transformers

Sri Vidya M

→ Riemannian Cooperation Dynamics for Stable Multi-Agent Adaptation

Jagannatham Jahnavi ⋅ Suprith S

→ MF-GCN: A Multi-Frequency Graph Convolutional Network for Multimodal Depression Detection from Eye-Tracking, Facial, and Acoustic Signals

Sejuti Rahman

→ Why Large Language Models Fail for Hausa Educational Content: Cascading Errors from Translation to Speech to Comprehension

Honour-Jesus Bezaleel ⋅ Pearse Jim

→ Culturally‑Grounded Prompt Engineering for Indonesian Heritage Illustrations: Expert Evaluation and a Multi-Tier Critic Loop

Argya Hanisi

→ Bridging the Terminology Gap: Glossary-Augmented Machine Translation for Nigerian Pidgin

Flora Oladipupo

→ A Stone Against Goliath: Addressing Occlusion Without LiDAR on Resource-Constrained Robots

Toyibat Adele

→ Project Paradox: Studying Memory, Emotion, and Trust in LLM Social Agents

Erina Karati

→ Improving Diversity in Prompt Adaptation via Density Based Scaling in RL

Ria Shekhawat

→ SHARP-VAE: Steerable High-frequency Aware Reconstruction Preservation for VAEs

V MANUSHREE

→ Wasserstein-Regularized Subspace Alignment for Continual Object Detection

AASHU Kathairiya

→ CVarGD: Coreset-Variance-Aware Gradient Descent for Data-Scarce Image Classification

Amina S Omar ⋅ Yussuf Hassan Hamad ⋅ Saleh H Othman

→ Spot the Splice: Wavelet-Driven Segmentation of Tampered Regions

Siddhi Lipare

→ Looks Can Deceive: An Underexplored Dimension of Deepfakes

Poulomi Bhattacharya ⋅ Akshay Agarwal

→ Sparse Autoencoders for LoRA-Adapted CLIP Under Domain Shift

Sunayana Samavedam

→ PR-Level Risk Prediction with Contextual Graph Learning

Hanaanee Hana ⋅ Sandareka Wickramanayake

→ MMDiff: Multimodal Model Diffing for Feature Discovery and Control

Hunar Batra

→ Drift-Adaptive Quantum Forests for Non-Stationary Data Streams

Spandana Chereddy

→ Shifting the Breaking Point of Flow Matching for Multi-Instance Editing

Silvia Cascianelli

→ DP-CARE: a differentially private classifier for mental health analysis in social media posts

Efstathia Soufleri

→ Private Prediction Can Be Practical Too: Revisiting Inference-Time Mechanisms for Differentially Private Learning

Rachel Redberg

→ OASIS: Online Activation Subspace Learning for Memory-Efficient Training

Sakshi Choudhary

→ Adaptive Privacy-Preserving Hierarchical Coordination for Multi-Robot Systems

Maryam Fatima

→ What is AI Reasoning?

Jacqueline Maasch

Link

→ Do Evil Numbers Amplify Emergent Misalignment? Investigating Negatively Associated Numerical Signals in Narrowly Misaligned Finetuning Data

Yashashree Chandak

→ Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs

Afsaneh Hasanebrahimi

→ “Newspaper Eat” Means “Not Tasty”: A Taxonomy and Benchmark for Coded Language in Real-World Chinese Online Reviews

Ruyuan Wan

→ Information-Theoretic Robust Explanations for Graph Neural Networks

Sandareka Wickramanayake

→ Learning to learn with reward-gated local plasticity

Dimitra Maoutsa

→ MMPD-Bench: Bridging Multimodal Fission with Multi-Polarimetric Modalities Decomposition

Yi He ⋅ Yiming Yang

→ Brain–Model Alignment as a Probe for Subliminal Learning

Angela Lopez Cardona

→ Intrinsic Credit Assignment for Long Horizon Interaction

Ilze Amanda Auzina

→ Bulk-Calibrated Credal Ambiguity Sets: Fast, Tractable Decision Making under Out-of-Sample Contamination

Mengqi Chen

→ Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting

Andrea Wynn

→ Selective Safety Steering via Value-Filtered Decoding

Bat-Sheva Einbinder

→ NSF-SciFy: Mining the NSF Awards Database for Scientific Claims

Weiqiu You

→ T-FIX: Text-Based Explanations with Features Interpretable to eXperts

Shreya Havaldar

→ Improving Coverage in Combined Prediction Sets with Weighted p-values

Gina Wong

→ A Localized, Traceable, and Vendor-Agnostic Retrieval-Augmented Generation Architecture for Low-Connectivity Edge Deployment

Seohyeon Lee

→ An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration

Maja Pavlovic

→ CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM

Xinyuan Liu

→ Hyperbolic Identity Geometry for Cross-View Aerial-Ground Person Re-Identification

Shubhi Gehlot

→ Boundary Matters: Adaptive Mixture-of-Experts Learning for Glioma Segmentation

⋅ Akshay Agarwal

→ AdAPT: Advertisement detector adaptation under newspaper domain shift with null-based pseudo-labeling

Faeze Zakaryapour Sayyad

→ CARES: A Causal-Aware Reasoning Benchmark for Evaluating LLM Interpretation of Complex Omics Networks

Sakhaa Alsaedi

3:00 AM

Poster Session (Different Room)