Search Results for author:
Found 15 papers, 5 papers with code
A Geometric Analysis-Based Safety Assessment Framework for MASS Route Decision-Making in Restricted Waters
To enhance the safety of Maritime Autonomous Surface Ships (MASS) navigating in restricted waters, this paper aims to develop a geometric analysis-based route safety assessment (GARSA) framework, specifically designed for their route decision-making in irregularly shaped waterways.
Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
We seek strategies for training on the SIMPLE version of the tasks that improve performance on the corresponding HARD task, i. e., S2H generalization.
Phi-4 Technical Report
We present phi-4, a 14-billion parameter language model developed with a training recipe that is centrally focused on data quality.
Can Models Learn Skill Composition from Examples?
(2) When skill categories are split into training and held-out groups, models significantly improve at composing texts with held-out skills during testing despite having only seen training skills during fine-tuning, illustrating the efficacy of the training approach even with previously unseen skills.
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty
Compositionality is a critical capability in Text-to-Image (T2I) models, as it reflects their ability to understand and combine multiple concepts from text descriptions.
AI-Assisted Generation of Difficult Math Questions
We present a design framework that combines the strengths of LLMs with a human-in-the-loop approach to generate a diverse array of challenging math questions.
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
Public LLMs such as the Llama 2-Chat underwent alignment training and were considered safe.
Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models
The paper develops a methodology for (a) designing and administering such an evaluation, and (b) automatic grading (plus spot-checking by humans) of the results using GPT-4 as well as the open LLaMA-2 70B model.
Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks
By classifying infinite-width neural networks and identifying the *optimal* limit, Tensor Programs IV and V demonstrated a universal way, called $\mu$P, for *widthwise hyperparameter transfer*, i. e., predicting optimal hyperparameters of wide neural networks from narrow ones.
New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound
Saliency methods compute heat maps that highlight portions of an input that were most {\em important} for the label assigned to it by a deep net.
A Kernel-Based View of Language Model Fine-Tuning
It has become standard to solve NLP tasks by fine-tuning pre-trained language models (LMs), especially in low-data settings.
New Definitions and Evaluations for Saliency Methods: Staying Intrinsic and Sound
Saliency methods seek to provide human-interpretable explanations for the output of machine learning model on a given input.
Enhanced Convolutional Neural Tangent Kernels
An exact algorithm to compute CNTK (Arora et al., 2019) yielded the finding that classification accuracy of CNTK on CIFAR-10 is within 6-7% of that of that of the corresponding CNN architecture (best figure being around 78%) which is interesting performance for a fixed kernel.
Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks
On VOC07 testbed for few-shot image classification tasks on ImageNet with transfer learning (Goyal et al., 2019), replacing the linear SVM currently used with a Convolutional NTK SVM consistently improves performance.
Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee
Over-parameterized deep neural networks trained by simple first-order methods are known to be able to fit any labeling of data.
