Search Results for author:
Found 38 papers, 10 papers with code
Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMs
To solve this problem, we propose Private Benchmarking, a solution where test datasets are kept private and models are evaluated without revealing the test data to the model.
Evaluating Atypical Gaze Patterns through Vision Models: The Case of Cortical Visual Impairment
A wide range of neurological and cognitive disorders exhibit distinct behavioral markers aside from their clinical manifestations.
X Hacking: The Threat of Misguided AutoML
Explainable AI (XAI) and interpretable machine learning methods help to build trust in model predictions and derived insights, yet also present a perverse incentive for analysts to manipulate XAI metrics to support pre-specified conclusions.
Development and Validation of a Dynamic Operating Envelopes-enabled Demand Response Scheme in Low-voltage Distribution Networks
In the second stage, the demand response aggregator (DRA) utilises DOEs assigned by the DNSP to develop a hierarchical control scheme for tracking a load set-point signal without jeopardising network statutory limits.
Finding Inductive Loop Invariants using Large Language Models
Finally, we explore the effectiveness of using an efficient combination of a symbolic tool and an LLM on our dataset and compare it against a purely symbolic baseline.
Discretizing Numerical Attributes: An Analysis of Human Perceptions
We conduct an extensive analysis of human perceptions of partitioning a numerical attribute and compare these perceptions with the results obtained from our two proposed measures.
Ranking LLM-Generated Loop Invariants for Program Verification
In this work, we observe that Large Language Models (such as gpt-3. 5 or gpt-4) are capable of synthesizing loop invariants for a class of programs in a 0-shot setting, yet require several samples to generate the correct invariants.
Numerical Association Rule Mining: A Systematic Literature Review
Numerical association rule mining is a widely used variant of the association rule mining technique, and it has been extensively used in discovering patterns and relationships in numerical data.
Training with Mixed-Precision Floating-Point Assignments
Hence, it is important to use a precision assignment -- a mapping from all tensors (arising in training) to precision levels (high or low) -- that keeps most of the tensors in low precision and leads to sufficiently accurate models.
Machine learning techniques for the Schizophrenia diagnosis: A comprehensive review and future research directions
Moreover, for accurate diagnosis of SCZ, researchers have used machine learning (ML) algorithms for the past decade to distinguish the brain patterns of healthy and SCZ brains using MRI and fMRI images.
Audio-Visual Activity Guided Cross-Modal Identity Association for Active Speaker Detection
Active speaker detection in videos addresses associating a source face, visible in the video frames, with the underlying speech in the audio modality.
Ranked #1 on
Audio-Visual Active Speaker Detection
on VPCD
MinUn: Accurate ML Inference on Microcontrollers
Running machine learning inference on tiny devices, known as TinyML, is an emerging research area.
Machine Learning for Optical Motion Capture-driven Musculoskeletal Modelling from Inertial Motion Capture Data
Marker-based Optical Motion Capture (OMC) systems and associated musculoskeletal (MSK) modelling predictions offer non-invasively obtainable insights into in vivo joint and muscle loading, aiding clinical decision-making.
Unsupervised active speaker detection in media content using cross-modal information
We leverage speaker identity information from speech and faces, and formulate active speaker detection as a speech-face assignment task such that the active speaker's face and the underlying speech identify the same person (character).
Efficient ML Models for Practical Secure Inference
For instance, the model provider could be a diagnostics company that has trained a state-of-the-art DenseNet-121 model for interpreting a chest X-ray and the user could be a patient at a hospital.
Federated Learning with Noisy User Feedback
Federated learning (FL) has recently emerged as a method for training ML models on edge devices using sensitive user data and is seen as a way to mitigate concerns over data privacy.
Using Active Speaker Faces for Diarization in TV shows
Speaker diarization is one of the critical components of computational media intelligence as it enables a character-level analysis of story portrayals and media content understanding.
Audio visual character profiles for detecting background characters in entertainment media
We curate a background character dataset which provides annotations for background character for a set of TV shows, and use it to evaluate the performance of the background character detection framework.
Phonetic Word Embeddings
This work presents a novel methodology for calculating the phonetic similarity between words taking motivation from the human perception of sounds.
MAFIA: Machine Learning Acceleration on FPGAs for IoT Applications
Recent breakthroughs in ML have produced new classes of models that allow ML inference to run directly on milliwatt-powered IoT devices.
SIRNN: A Math Library for Secure RNN Inference
Although prior work on secure 2-party inference provides specialized protocols for convolutional neural networks (CNNs), existing secure implementations of these math operators rely on generic 2-party computation (2PC) protocols that suffer from high communication.
Variational Rejection Particle Filtering
We present a variational inference (VI) framework that unifies and leverages sequential Monte-Carlo (particle filtering) with \emph{approximate} rejection sampling to construct a flexible family of variational distributions.
Partial Rejection Control for Robust Variational Inference in Sequential Latent Variable Models
Effective variational inference crucially depends on a flexible variational family of distributions.
Secure Medical Image Analysis with CrypTFlow
Our first component is an end-to-end compiler from TensorFlow to a variety of MPC protocols.
Cryptography and Security
Oasis: ILP-Guided Synthesis of Loop Invariants
Automated synthesis of inductive invariants is an important problem in software verification.
CrypTFlow2: Practical 2-Party Secure Inference
We present CrypTFlow2, a cryptographic framework for secure inference over realistic Deep Neural Networks (DNNs) using secure 2-party computation.
Cross modal video representations for weakly supervised active speaker localization
Avoiding the need for manual annotations for active speakers in visual frames, acquiring of which is very expensive, we present a weakly supervised system for the task of localizing active speakers in movie content.
On Scaling Data-Driven Loop Invariant Inference
Automated synthesis of inductive invariants is an important problem in software verification.
Refined $α$-Divergence Variational Inference via Rejection Sampling
Our inference method is based on a crucial observation that $D_\infty(p||q)$ equals $\log M(\theta)$ where $M(\theta)$ is the optimal value of the RS constant for a given proposal $q_\theta(x)$.
CrypTFlow: Secure TensorFlow Inference
Finally, to provide malicious secure MPC protocols, our third component, Aramis, is a novel technique that uses hardware with integrity guarantees to convert any semi-honest MPC protocol into an MPC protocol that provides malicious security.
Overfitting in Synthesis: Theory and Practice (Extended Version)
A standard approach to mitigate overfitting in machine learning is to run multiple learners with varying expressiveness in parallel.
Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time
Furthermore, we develop a graph pruning strategy at that leads to an additional 58% improvement in recommendations.
LoopInvGen: A Loop Invariant Generator based on Precondition Inference
We describe the LoopInvGen tool for generating loop invariants that can provably guarantee correctness of a program with respect to a given specification.
Synthesizing Program Input Grammars
We present an algorithm for synthesizing a context-free grammar encoding the language of valid program inputs from a set of input examples and blackbox access to the program.
Programming Languages
