5 citations · 17 across the 23 of their papers we have counts for
24 papers
Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning
Jifan Zhang, Miklos Racz, Suqi Liu
Knowledge graph learning provides a powerful framework for representing and inferring structured knowledge, with broad practical applications. However, the scarcity of relation-spe…
Leum-VL Technical Report
Yuxuan He, Chaiming Huang, Yifan Wu +4
A short video succeeds not simply because of what it shows, but because of how it schedules attention -- yet current multimodal models lack the structural grammar to parse or produ…
Unknown Aware AI-Generated Content Attribution
Ellie Thieu, Jifan Zhang, Haoyue Bai
The rapid advancement of photorealistic generative models has made it increasingly important to attribute the origin of synthetic content, moving beyond binary real or fake detecti…
Stress-Testing Model Specs Reveals Character Differences among Language Models
Jifan Zhang, Henry Sleight, Andi Peng +2
Large language models (LLMs) are increasingly trained from AI constitutions and model specifications that establish behavioral guidelines and ethical principles. However, these spe…
Causal Representation Learning from Network Data
Jifan Zhang, Michelle M. Li, Elena Zheleva
Causal disentanglement from soft interventions is identifiable under the assumptions of linear interventional faithfulness and availability of both observational and interventional…
Improving Task Diversity in Label Efficient Supervised Finetuning of LLMs
Abhinav Arabelly, Jagrut Nemade, Robert D Nowak +1
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, but developing high-performing models for specialized applications often requires sub…
Which LLMs Get the Joke? Probing Non-STEM Reasoning Abilities with HumorBench
Reuben Narad, Siddharth Suresh, Jiayi Chen +5
We present HumorBench, a benchmark designed to evaluate large language models' (LLMs) ability to reason about and explain sophisticated humor in cartoon captions. As reasoning mode…
Topology-Aware Conformal Prediction for Stream Networks
Jifan Zhang, Fangxin Wang, Zihe Song +3
Stream networks, a unique class of spatiotemporal graphs, exhibit complex directional flow constraints and evolving dependencies, making uncertainty quantification a critical yet c…
Bridging the Creativity Understanding Gap: Small-Scale Human Alignment Enables Expert-Level Humor Ranking in LLMs
Kuan Lok Zhou, Jiayi Chen, Siddharth Suresh +6
Large Language Models (LLMs) have shown significant limitations in understanding creative content, as demonstrated by Hessel et al. (2023)'s influential work on the New Yorker Cart…
Harnessing Multiple Correlated Networks for Exact Community Recovery
Miklós Z. Rácz, Jifan Zhang
We study the problem of learning latent community structure from multiple correlated networks, focusing on edge-correlated stochastic block models with two balanced communities. Re…
From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling
Jinhong Lin, Cheng-En Wu, Huanran Li +3
Masked Image Modeling (MIM) has emerged as a powerful self-supervised learning paradigm for visual representation learning, enabling models to acquire rich visual representations b…
Deep Active Learning in the Open World
Tian Xie, Jifan Zhang, Haoyue Bai +1
Machine learning models deployed in open-world scenarios often encounter unfamiliar conditions and perform poorly in unanticipated situations. As AI systems advance and find applic…
AHA: Human-Assisted Out-of-Distribution Generalization and Detection
Haoyue Bai, Jifan Zhang, Robert Nowak
Modern machine learning models deployed often encounter distribution shifts in real-world applications, manifesting as covariate or semantic out-of-distribution (OOD) shifts. These…
GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data
Jifan Zhang, Ziyue Luo, Jia Liu +2
Large language models require vast amounts of high-quality training data, but effective filtering of web-scale datasets remains a significant challenge. This paper demonstrates tha…
Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
Jifan Zhang, Lalit Jain, Yang Guo +9
We present a novel multimodal preference dataset for creative tasks, consisting of over 250 million human ratings on more than 2.2 million captions, collected through crowdsourcing…
Learning from the Best: Active Learning for Wireless Communications
Nasim Soltani, Jifan Zhang, Batool Salehi +3
Collecting an over-the-air wireless communications training dataset for deep learning-based communication tasks is relatively simple. However, labeling the dataset requires expert…
An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models
Gantavya Bhatt, Yifang Chen, Arnav M. Das +9
Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language mo…
Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation
Shyam Nuggehalli, Jifan Zhang, Lalit Jain +1
Class imbalance severely impacts machine learning performance on minority classes in real-world applications. While various solutions exist, active learning offers a fundamental fi…
LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning
Jifan Zhang, Yifang Chen, Gregory Canal +8
Labeled data are critical to modern machine learning applications, but obtaining labels can be expensive. To mitigate this cost, machine learning methods, such as transfer learning…
Algorithm Selection for Deep Active Learning with Imbalanced Datasets
Jifan Zhang, Shuai Shao, Saurabh Verma +1
Label efficiency has become an increasingly important objective in deep learning applications. Active learning aims to reduce the number of labeled examples needed to train deep ne…
PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks
Liu Yang, Jifan Zhang, Joseph Shenouda +3
Weight decay is one of the most widely used forms of regularization in deep learning, and has been shown to improve generalization and robustness. The optimization objective drivin…
GALAXY: Graph-based Active Learning at the Extreme
Jifan Zhang, Julian Katz-Samuels, Robert Nowak
Active learning is a label-efficient approach to train highly effective models while interactively selecting only small subsets of unlabelled data for labelling and training. In "o…
Improved Algorithms for Agnostic Pool-based Active Classification
Julian Katz-Samuels, Jifan Zhang, Lalit Jain +1
We consider active learning for binary classification in the agnostic pool-based setting. The vast majority of works in active learning in the agnostic setting are inspired by the…
Learning to Actively Learn: A Robust Approach
Jifan Zhang, Lalit Jain, Kevin Jamieson
This work proposes a procedure for designing algorithms for specific adaptive data collection tasks like active learning and pure-exploration multi-armed bandits. Unlike the design…