You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
| 11:30-11:45 | Introduction | Opening remarks | Prof. Dr. Rafet Sifa & Dr. Linsey Pang |
46
+
| 11:45-12:30 | Keynote |[The Operating System for AI-Native Enterprises](#keynote-mouli)| Avinash Karn |
47
+
| 12:30-13:30 | Lunch break |||
48
+
| 13:30-14:45 | Keynote |[Towards Trustworthy and Scalable Graph Foundation Models](#keynote-sandeep)| Dr. Sandeep Kumar |
49
+
| 14:45-15:00 | Paper | ChatGIT: Intent-Aware Routing for Multi-Turn Conversational Code Retrieval | TBA |
50
+
| 15:00-15:15 | Paper | Towards Empathetic AI: MITI-Guided Evaluation of Large Language Models for Motivational Interviewing | TBA |
51
+
| 15:15-15:30 | Paper | ZoneGate: Per-Zone Deployment Readiness for Vision-Language Models in Industrial CCTV | TBA |
41
52
42
-
| Time | Paper / Speaker | Presenter |
43
-
|------|-----------------|-----------|
44
-
| TBA | TBA | TBA |
45
53
46
54
## Keynotes
47
55
48
-
### The Operating System for AI-Native Enterprises: From Experimentation to Agentic Transformation
56
+
### The Operating System for AI-Native Enterprises: From Experimentation to Agentic Transformation {#keynote-mouli}
49
57
50
58
**Avinash Karn**, Senior Director, AI Strategy, PayPal
51
59
52
60
Avinash Karn is Senior Director of AI Strategy at PayPal, where he leads AI strategy and engineering within PayPal's central AI group and builds AI products, both customer-facing and internal, that shape how the company operates in the age of Agentic AI. His portfolio spans Business AI Transformation programs that tie AI investment to measurable business outcomes; Agentic Commerce, positioning PayPal as the economic operating system for the agent economy; an AI Fluency Index measuring enterprise adoption maturity; and foundational AI Research advancing PayPal's frontier AI capabilities. Avinash built the measurement science that gives leadership confidence in AI ROI. A first-principles, frameworks-driven leader, Avinash sits at PayPal's leadership table on AI positioning and competitive strategy, and shapes academic and industry dialogue across India on the future of AI-native enterprises.
53
61
54
62
**Abstract**: Large language models have lowered the barrier to enterprise AI experimentation, but for most organizations, the real challenge is now transformation, not experimentation. Moving from isolated pilots to AI-native operating models demands new ways of working, new organizational capabilities, and new architectural foundations. Drawing on practical experience at PayPal, this keynote explores scaling AI adoption through workforce fluency, platform democratization, internal AI champions, and measurable organizational enablement, and how initiatives were prioritized around business outcomes across finance operations, conversational platforms, workflow automation, and emerging agentic systems. The talk also covers the technical and operational realities of deploying enterprise-scale AI in regulated environments: orchestration frameworks, semantic caching, memory architectures, evaluation systems, governance, and production deployment, before outlining emerging patterns for AI-native enterprises, where reusable AI capabilities become foundational primitives that move organizations from AI-assisted work toward increasingly autonomous, adaptive operating models.
55
63
56
-
### Towards Trustworthy and Scalable Graph Foundation Models
64
+
### Towards Trustworthy and Scalable Graph Foundation Models {#keynote-sandeep}
57
65
58
66
**Dr. Sandeep Kumar**, Associate Professor, IIT Delhi (Electrical Engineering and Yardi School of AI)
59
67
60
68
Dr. Sandeep Kumar is an Associate Professor in the Department of Electrical Engineering and the Yardi School of Artificial Intelligence at the Indian Institute of Technology Delhi, where he leads the Machine Intelligence Signals and Networks (MISN) Lab. He holds the Pankaj Gupta Chair Professorship in Privacy and Decentralization. His research spans graph machine learning, trustworthy and scalable AI, optimization, and foundation models, with applications in public health, finance, neuroscience, communication systems, and national security. He is Lead Investigator of Adi Vaani, a flagship initiative of the Ministry of Tribal Affairs developing multilingual AI for low-resource tribal and regional languages to advance digital inclusion and linguistic preservation. Through government and industry collaborations, his work combines rigorous algorithmic foundations with socially impactful AI systems.
61
69
62
70
**Abstract**: As AI moves into the foundation-model era, a central question remains: how can we reason over complex relational structure while keeping systems trustworthy, scalable, and efficient? While large models excel in language and vision, many real-world domains, from biology and finance to social networks and scientific discovery, are inherently graph-structured. This talk positions Graph Neural Networks (GNNs) and graph representation learning as a foundation for the next generation of reliable AI. The talk first examines the trust gap in graph machine learning, covering robustness, fairness, privacy, and uncertainty in large-scale relational systems, including recent advances in fairness-aware models, privacy-preserving learning, and robust representations for high-impact deployment. It then discusses Self-Supervised Learning (SSL) as a scalable path to graph foundation models, showing how SSL objectives learn transferable relational representations and support graph-language models that combine semantic understanding with structural reasoning. Finally, the talk addresses scalability through optimization-based graph coarsening, compression, and hashing-driven dimensionality reduction, along with graph-to-MLP distillation for efficient deployment. The talk outlines a roadmap toward graph foundation models that are powerful, trustworthy, scalable, and practical for real-world AI systems.
63
71
72
+
## Organizers
73
+
74
+
**Prof. Dr. Rafet Sifa***(Contact Person)*
75
+
University of Bonn, Germany · `rafet.sifa@bit.uni-bonn.de`
76
+
Prof. Dr. Rafet Sifa is a leading researcher in AI and machine learning, with over 15 years of experience and a
77
+
regular contributor to top-tier machine learning conferences. His research focuses on hybrid deep learning and large-scale
78
+
analytics, with extensive publications on both theoretical and applied machine learning topics with a deep focus on
79
+
representation learning. He co-organized the special session on Informed and Explainable Methods for Machine Learning
80
+
at ICANN 2019, the three workshops on foundational and large language models at IEEE BigData (2023, 2024, 2025), a
81
+
special session on Large Language and Foundation Models at IEEE DSAA 2025, and workshops on Bridging Neurons and
82
+
Symbols for NLP and Knowledge Graphs Reasoning at COLING 2024 and 2025.
83
+
84
+
**Prof. Dr. Wei Liu**
85
+
University of Technology Sydney, Australia · `wei.liu@uts.edu.au`
86
+
Wei Liu is an Associate Professor of Machine Learning and Director of the Future Intelligence Research Lab at UTS. He
87
+
holds a PhD in Machine Learning from the University of Sydney. His research spans generative AI, adversarial machine
88
+
learning, cybersecurity, game theory, multimodal learning, NLP, and intrusion detection. He has earned 3 Best Paper
89
+
Awards and a Most Influential Paper Award at PAKDD, and serves as senior PC member and area chair at KDD, AAAI, and
90
+
ICDM.
91
+
92
+
**Dr. Dhaval Patel**
93
+
IBM Research, USA · `dhaval.patel@ibm.com`
94
+
Dr. Dhaval Patel is a research scientist specializing in AI model optimization and industrial applications. His work
95
+
bridges fundamental research and real-world deployment, focusing on scalable machine learning solutions. He
96
+
co-organized the previous workshops on foundational and large language models at IEEE BigData as well as the special
97
+
session at DSAA 2025.
98
+
99
+
**Dr. Linsey Pang**
100
+
PayPal Inc., USA · `panglinsey@gmail.com`
101
+
Linsey Pang is a Distinguished Scientist at PayPal. Previously she was a Principal Machine Learning Scientist at Salesforce.
102
+
Prior to this, she was a Principal Data Scientist at Walmart Lab. Prior to joining Walmart Lab, she worked as an applied
103
+
scientist at eBay Inc. She finished her PhD degree in machine learning research at the University of Sydney. She
104
+
co-organizes multiple workshops and tutorials at CIKM, KDD, and WSDM in top data mining conferences.
105
+
106
+
**Dr. Lorenz Sparrenberg**
107
+
University of Bonn, Germany · `lsparren@uni-bonn.de`
108
+
Dr. Lorenz Sparrenberg's research focuses on large language models and their evaluation, robustness, and limitations.
109
+
His recent work includes research on efficient inference of LLMs and empirical studies on their behavior in real-world
110
+
settings, as well as publications on representative learning for clinical and decision support applications including
111
+
dementia detection and diabetic retinopathy.
112
+
113
+
**Priya Tomar**
114
+
University of Bonn, Germany · `ppriya@uni-bonn.de`
115
+
Priya is a data scientist at Fraunhofer IAIS and a PhD candidate at the University of Bonn focusing on deep
116
+
learning-based medical image analysis, in particular Surgical AI. Her work addresses domain-specific challenges in the
117
+
surgical domain by developing data-driven and application-oriented methods to enhance clinical applicability. Her
118
+
recent publications focus on semantic segmentation for robot-assisted abdominal surgery.
119
+
64
120
## Submission
65
121
66
122
To submit a paper to SSLLFM2026, go to [OpenReview (IEEE DSAA 2026 Conference)](https://openreview.net/group?id=IEEE.org/DSAA/2026/Special_Sessions),
@@ -133,87 +189,12 @@ The topics of interest are, but not limited to:
133
189
All accepted full-length special session papers will be published by IEEE in the DSAA main conference proceedings under
134
190
its Special Session scheme. All papers will be submitted for inclusion in the IEEEXplore Digital Library.
0 commit comments