Accepted Submissions (🎤 = oral)
Beyond PII: Preserving Implicit User Privacy via LLM-Generated Synthetic Data Guided by Reinforcement Learning
Enhancing Trust and Safety with Fine-Tuned LLMs: A Cost-Effective Hybrid Approach at Thumbtack
RaCT: Ranking-aware Chain-of-Thought Optimization for LLMs
🎤 Context, Models and Prompt Optimization for Automated Hallucination Detection in LLM Output
Scalable Function Calling: A Hybrid Retrieval-Augmented Fine-Tuning Pipeline
Large VLM based stylized Sports Captioning
Mentorship for All: Multi-Agent Multilingual Long-Form Video Question Answering for Mentorship Applications
Multi-Agent Multimodal Models for Multicultural Text to Image Generation
🎤 Emerging Aspects in ResNet Quantization with Adaptive Codebook Sizes
DeepChem Equivariant: SE(3)-Equivariant Support in an Open-Source Molecular Machine Learning Library
Agentic Debugging Framework for LLMs
Attention-Guided Task Complexity Prediction for Edge-Cloud LLM Collaboration
Improving GANs through contradictions
MemeTranslate: AI-Powered Cross-Cultural Meme Transcreation with Vision-Language Models
🎤 Knowing You Don’t Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing
MCANN: A Mixture Clustering-Based Attention Neural Network for Multivariate Time Series Forecasting
Efficient Deployment of Very Wide and Very Deep Hypersparse FFNs on FPGA
AUSGAN: Attention-UNet Spectral GAN for Multi-Dataset MRI Reconstruction with Tissue-Specific Bhattacharya Distance Evaluation
Predicting Optimization
Optimizing Vision Transformers for White Shark Re-Identification
Leveraging Large Language Models to Predict MRI Protocols
Trade-offs in Data Memorization via Strong Data Processing Inequalities
Attention-Augmented EfficientNetV2-L for Knee Osteoporosis Classification
Deep Reinforcement Learning for Intelligent Traffic Distribution in IEEE 802.11be Multi-Link Operation
How Does Machine Learning Accelerate Design Optimization of Pedestal Heaters for Semiconductor Manufacturing?
HoneyBee: Efficient Access Control in Multi-tenant Vector Databases
Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
Steady Continuous Monitoring is Just Barely Impossible for Tests of Unbounded Length
Faithful-SAE: Rank-One Parameter Decomposition for Post-Hoc Concept Debiasing
🎤 Dementor: Stealing the Soul of a Language Model
PM1: A Foundation Model Fusing Genotype, Phenotype, and Image for Precision Medicine
The Blessing of Reasoning: LLM-Based Contrastive Explanations in Black-Box Recommender Systems
Yield Curve Forecasting using Machine Learning and Econometrics: A Comparative Analysis
LLMs as Mold Makers and Not 3D Printers
🎤 Empowering Microgrid Autonomy through Intelligent Agents
Information Theoretic Analysis of Generative AI Models
Leveraging Large Language Model Workflows in a Conversational Video Agent: a Live Demo
REOrdering Patches Improves Vision Models
Interpretable Graph Neural Networks for Microbiome-Disease Modeling
Concept-level Explanations for ML System Control
Integrating Domain Knowledge into Large Language Models for Enhanced Fashion Recommendations
A Graph-based Framework for Whole-Genome SNP Representation Learning
Mouse-Guided Gaze: Semi-Supervised Learning of Intention-Aware Representations for Reading Detection
Closing the Loop: Evaluation-Guided Prompt Optimization for High-Quality Synthetic Data Generation
Cooperative Incentives Mitigate Operational Collisions in Multi-Agent Energy Management Systems
How Large Language Models Balance Internal Knowledge with User and Document Assertions
iVISPAR — An Interactive Visual-Spatial Reasoning Benchmark for VLMs
How to Recommend a Dataset for Model Training Team? Rethinking Proxy-Model-based Technique
GRIT: Teaching MLLMs to Think with Images
Learning to Summarize for Search Relevance with Reinforcement Learning
Learning to Drive by Imitating Surrounding Vehicles
From Perception to Understanding: Frame-Based Semantic Compression for Interpretable Autonomous Driving
Effect of Expert Selection on the Performance of Combined RL-IL Approaches
Who’s the F(AI)rest of them all? A Large-Scale Analysis of Racial and Gender Bias in AI-Generated User Personas
Inferring Dynamic Hidden Graph Structure in Heterogeneous Correlated Time Series
Residual Matrix Transformers
GenAI-Powered Knowledge Graph Summarization for Real-Time and Explainable Fraud Ring Detection
Follow My Lead: Logical Fallacy Classification with Knowledge-Augmented LLMs
Inference With Parallel Is All You Need
Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts
Does Reasoning Introduce Bias? A Study of Social Bias Evaluation and Mitigation in LLM Reasoning
MAPO: Minimax Adaptive Prompt Optimization without Data or Rewards
Enough Coin Flips Can Make LLMs Act Bayesian
Direct Alignment with Heterogeneous Preferences
Adaptive Control of Inference-Time Activation Sparsity for On-Device LLMs
Call for Abstracts
BayLearn 2025 will be an in-person event, held on Thursday, October 16th, 2025.
BayLearn 2025 will be hosted at Santa Clara University and co-organized in partnership with the University of California, Santa Cruz.
Note: BayLearn 2025 will not be a hybrid event, and it will not be live-streamed.
The BayLearn 2025 abstract submission site is now open for submissions:
- Submit via Microsoft CMT
The abstract submission deadline has been extended to Tuesday, Aug 5th, 2025, 11:59pm PDT.
Please submit abstracts as a 2-page pdf in NeurIPS 2023 format. An extra page for acknowledgements and references is allowed.
About BayLearn
The BayLearn Symposium is an annual gathering of machine learning researchers and scientists from the San Francisco Bay Area. While BayLearn promotes community building and technical discussions between local researchers from academic and industrial institutions, it also welcomes visitors. This one-day event combines invited talks, contributed talks, and posters, to foster exchange of ideas.
Meet with fellow Bay Area machine learning researchers and scientists during the symposium that will be held on October 16th, at Santa Clara University.
Feel free to circulate this invitation to your colleagues and relevant contacts.
Key Dates
- Abstract submission deadline (Deadline Extended): Tuesday, Aug 5th, 2025 at 11:59pm PDT
- Author notifications (New Date) : Friday, September 19th, 2025
- Registration Lottery opens (New Date) : Friday, September 19th, 2025
- Symposium: Thursday, Oct 16th, 2025
Submissions
We encourage submission of abstracts. Acceptable material includes work which has already been submitted or published, preliminary results, and controversial findings. We do not intend to publish paper proceedings; only abstracts will be shared through an online repository. Our primary goal is to foster discussion! For examples of previously accepted talks, please watch the paper presentations from previous BayLearn Symposiums: https://baylearn.org/previous
Submit your abstracts via CMT:
https://cmt3.research.microsoft.com/BAYLEARN2025
Note: The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.