Deployable AI (DAI)

Papers Accepted for Oral Presentation

All Papers accepted for Oral presentation will have a 12-minute (10 + 2) talk at the workshop.  

• Title: UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models, Video Presentation

Authors: Sejoon Oh, Yiqiao Jin, Megha Sharma, Donghyun Kim, Yingchen Ma, Gaurav Verma and Srijan Kumar

• Title: Secure Multiparty Generative AI, Video Presentation

Authors: Manil Shrestha, Yashodha Ravichandran and Edward Kim

• Title: Predicting Goal Misgeneralisation Using Policy-Implied Reward Comparsion, Video Presentation

Authors: Matt MacDermott, Titus Buckworth and Francesco Belardinelli

• Title: DREAM-VEP: A Modular and Open-Source Framework for Developing Robust, Efficient, and Adaptive Models in Variant Effect Prediction, Video Presentation

Authors: Huixin Zhan, Zijun Zhang and Jason H. Moore

• Title: Membership Inference Test: Auditing Training Data in Object Classification Models, Video Presentation

Authors: Gonzalo Mancera Fernández, Daniel Dealcala Valcarcel, Aythami Morales Moreno, Ruben Tolosana Moranchel and Julian Fierrez Aguilar

• Title: Large Language Models for Enhanced Interpretability for Sentiment Analysis, Video Presentation

Authors: Thivya Thogesan, Dr. Anupiya Nugaliyadde and Dr.Kok Wai Wong

• Title: Refine: Robust Unsupervised Anomaly Detection for Production HPC Systems  Video Presentation

Authors: Efe Sencan, Yin-Ching Lee, Connor Casey, Benjamin Schwaller, Vitus J. Leung, Jim Brandt, Brian Kulis, Manuel Egele and Ayse Coskun

• Title: Node Classification With Integrated Reject Option For Legal Judgement Prediction Video Presentation

Authors: Uday Bhaskar K, Jayadratha Gayen, Charu Sharma and Naresh Manwani

• Title: Interpreting adversarial attacks and defences using architectures with enhanced interpretability  Video Presentation

Authors: Akshay G Rao, Chandrashekhar Lakshminarayanan and Arun Rajkumar

• Title: The Potential of Causal Modelling in Cloud Microservice Architectures Video Presentation

Authors: Christopher Lohse, Diego Tsutsumi, Amadou Ba, Pavithra Harsha, Chitra Subramanian, Martin Straesser and Marco Ruffini

• Title: Using Comparative Machine Learning Methods to Validate Educational Content  Video Presentation

Authors: John Kos, Kenneth Eaton, Rahul Dass, Sareen Zhang and Ashok Goel

• Title: MultiTutor: Collaborative LLM Agents for Multimodal Student Support  Video Presentation

Authors: Edward Sun and Leann Tai

• Title: A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio Video Presentation

Authors: Ningyuan Xi, Yetao Wu, Kun Fan, Teng Chen, Qingqing Gu and Luo Ji

• Title: TopKElim: A Bandit Approach to Identify Top-k Candidates from Noisy Ratings Video Presentation

Authors: Ishaan Taneja and Arun Rajkumar

• Title: Deploying Privacy Guardrails for LLMs: A Comparative Analysis of Real-World Applications Video Presentation

Authors: Shubhi Asthana, Bing Zhang, Ruchi Mahindru, Chad DeLuca, Anna Lisa Gentile and Sandeep Gopisetty

• Title: Build Your Knowledge Base Using GenAI Powered ScienceSage Video Presentation

Authors: Yong Zhang, Eric Gyamfi, Kelly Anderson, Sasha Roberts and Matt Barker

• Title: Intanify AI Platform: Embedded AI for Automated IP Audit and Due Diligence Video Presentation

Authors: Viktor Dörfler, Dylan Dryden and Viet Lee

• Meta-Learning for Speeding Up Large Model Inference in Decentralized Environments (N)

    Authors: Yuzhe Yang, Yipeng Du, Ahmad Farhan, Claudio Angione, Yue Zhao, Harry Yang, Fielding Johnston, James Buban and Patrick Colangelo

Papers Accepted for Poster Presentation (Lightning Talk)

All Papers accepted for Poster presentation will have a 2-minute lightning talk at the workshop and the poster presentation session.  Posters are 30"x40" and can be portrait or landscape orientation.

• Title: Demystifying the Accuracy-Interpretability Trade-Off: A Case Study of Inferring Ratings from Reviews Video Presentation

Authors: Pranjal Atrey, Michael Brundage, Min Wu and Sanghamitra Dutta

• Title: Deep Linearly Gated Network : A Transparent Deep Model Video Presentation

Authors: Shivangi Shreya, Chandrashekar Lakshmi Narayanan, Arun Rajkumar and Amit Vikram Singh

• Title: Seq2Seq Model-Based Chatbot with LSTM and Attention Mechanism for Enhanced User Interaction Video Presentation

Authors: Lamya Benaddi, Charaf Ouaddi, Adnane Souha, Abdeslam Jakimi, Mohamed Rahouti, Mohammed Aledhari, Diogo Oliveira and Brahim Ouchao

• Title: Beyond Bans: Thoughtful Use of AI in the Classroom Video Presentation

Authors: Kendall Brogle and Umang Bhatt

• Title: From Explainability to Interpretability: Interpretable Policies in Reinforcement Learning Via Model Explanation Video Presentation

Authors: Peilang Li, Umer Siddique and Yongcan Cao

• Title: Model Calibration for Audio Driven Disease Diagnosis via Uncertainty Quantification Video Presentation

Authors: Shubham Kulkarni, Hideaki Watanabe and Fuminori Homma

• Title: Accelerating Manufacturing Scale-Up from Material Discovery Using Agentic Web Navigation and Retrieval-Augmented AI for Process Engineering Schematics Design Video Presentation

Authors: Sagar Srinivas Sakhinana, Akash Das, Shivam Gupta and Venkataramana Runkana

• Title: Standardizing Data Parsing Technique for Enhanced LLM Interpretability through RAG Video Presentation

Authors: Ashvinn Kanagar, Anupiya Nugaliyadde and Kok Wai Wong

• Title: AI-Based Teat Shape and Skin Condition Prediction for Dairy Management Video Presentation

Authors: Yuexing Hao, Tiancheng Yuan, Yuting Yang, Aarushi Gupta, Matthias Wieland, Ken Birman and Parminder Basran

• Title: Deploying AI with Factual and Legal Accountability (N)

Authors: Neethu Rajam

• Title: Mining Unstructured Medical Texts With Conformal Active Learning Video Presentation

Authors: Juliano Genari and Guilherme Tegoni Goedert

• Title: Graphbook: An Interactive Visual Framework for Production Ready Interpretable AI Video Presentation

Authors: David Winer

• Title: Robust Pairwise Ranking Under Byzantine Setting Video Presentation

Authors: Abdul Bakey Mir, Arun Rajkumar and John Augustine

• Title: Multilinguality in LLM-Designed Reward Functions for Restless Bandits: Effects on Task Performance and Fairness Video Presentation

Authors: Ambreesh Parthasarathy, Chandrasekar Subramanian, Ganesh, Shreyash Adappanavar, Aparna Taneja, Balaraman Ravindran and Milind Tambe

• Title: TradingAgents: Multi-Agents LLM Trading Framework

Authors: Yijia Xiao, Edward Sun, Di Luo and Wei Wang

• Title: LLM Assisted Anomaly Detection Service for Site Reliability Engineers: Enhancing Cloud Infrastructure Resilience Video Presentation

Authors: Nimesh Jha, Dhaval Patel, Christodoulos Constantinides, Shuxin Lin, Srideepika Jayaraman and Kyle Frohling

• Title: Leveraging Interpretability in the Transformer to Automate the Proactive Scaling of Cloud Resources  Video Presentation

Authors: Amadou Ba, Pavithra Harsha and Chitra Subramanian