13 papers
Beyond Better Ideas: How Human-AI Collaboration Shapes Scientific Ideas and Human Perceptions
Qian Chen, Saatvik Pradhan, Janice Ahn +7
As AI increasingly becomes a collaborator in scientific research, its impact may extend beyond improving ideas to reshaping how they are evaluated, attributed, and perceived by hum…
CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets
Berke Arda, Ahmetcan Yavuz, Paul Gerry +7
Croissant has emerged as a standard for machine-readable dataset metadata, yet populating its fields remains labor-intensive and requires careful reading of accompanying dataset do…
New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models
Sourajit Saha, Shubhashis Roy Dipta, Nobin Sarwar +4
A model first sees an image from one physical measurement experiment, such as how far a block coasted, and must answer a question about a new trial, such as whether the block will…
BEFORE THE FLIP: Measuring Hidden Score Shifts In Quantized Vision Language Models Before The Answer Changes for Visual Question Answering
Sourajit Saha, Shubhashis Roy Dipta, Shaswati Saha +2
Quantization makes vision language models (VLMs) cheaper to store and run by using fewer bits to represent their weights. While unchanged answers on visual question answering (VQA)…
OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution
Shubhashis Roy Dipta, Sourajit Saha, Shaswati Saha +1
Recursive Super-Resolution (SR) extends fixed-scale SR to extreme magnification by repeatedly feeding predictions back into the same model, analogous to zooming an image repeatedly…
Last Translation Benchmark
Vilém Zouhar, Niyati Bafna, Mukund Choudhary +263
For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, stan…
Pluralis v0.1: Towards a Multicultural, Multimodal, Multilingual Benchmark for AI Risk and Reliability
Alicia Parrish, Rajat Shinde, Sanket Badhe +57
Current AI safety evaluation and benchmarking frameworks predominantly rely on Western-centric culture-agnostic defaults that mask critical regional laws, socio-linguistic nuances,…
Croissant Baker: Metadata Generation for Discoverable, Governable, and Reusable ML Datasets
Rafi Al Attrach, Rajna Fani, Sebastian Lobentanzer +17
Croissant has emerged as the metadata standard for machine learning datasets, providing a structured, JSON-LD-based format that makes dataset discovery, automated ingestion, and re…
FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health
Nobin Sarwar, Shubhashis Roy Dipta
Privacy-preserving adaptation of Large Language Models (LLMs) in sensitive domains (e.g., mental health) requires balancing strict confidentiality with model utility and safety. We…
FedMentalCare: Towards Privacy-Preserving Fine-Tuned LLMs to Analyze Mental Health Status Using Federated Learning Framework
Nobin Sarwar
With the increasing prevalence of mental health conditions worldwide, AI-powered chatbots and conversational agents have emerged as accessible tools to support mental health. Howev…
FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA
Nobin Sarwar
Visual Question Answering requires models to generate accurate answers by integrating visual and textual understanding. However, VQA models still struggle with hallucinations, prod…
Differentially Private Data Publication with Multi-level Data Utility
Honglu Jiang, S M Sarwar, Haotian Yu +1
Conventional private data publication mechanisms aim to retain as much data utility as possible while ensuring sufficient privacy protection on sensitive data. Such data publicatio…
Differential Privacy in Privacy-Preserving Big Data and Learning: Challenge and Opportunity
Honglu Jiang, Yifeng Gao, S M Sarwar +2
Differential privacy (DP) has become the de facto standard of privacy preservation due to its strong protection and sound mathematical foundation, which is widely adopted in differ…