Related papers: Variational Temporal IRT: Fast, Accurate, and Expl…

Computerized adaptive tests (CATs) play a crucial role in educational assessment and diagnostic screening in behavioral health. Unlike traditional linear tests that administer a fixed set of pre-assembled items, CATs adaptively tailor the…

Educational assessment relies heavily on knowing question difficulty, traditionally determined through resource-intensive pre-testing with students. This creates significant barriers for both classroom teachers and assessment developers. We…

Causal representation learning is the task of identifying the underlying causal variables and their relations from high-dimensional observations, such as images. Recent work has shown that one can reconstruct the causal variables from…

Large language models (LLMs) have shown remarkable reasoning capabilities, yet aligning such abilities to small language models (SLMs) remains a challenge due to distributional mismatches and limited model capacity. Existing reasoning…

We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorithmic question: How could a teacher provide an informative…

In this paper, we present a complete framework for quickly calibrating and administering a robust large-scale computerized adaptive test (CAT) with a small number of responses. Calibration - learning item parameters in a test - is done…

In Intelligent Tutoring System (ITS), tracing the student's knowledge state during learning has been studied for several decades in order to provide more supportive learning instructions. In this paper, we propose a novel model for…

This paper presents the first item response theory (IRT) analysis of the national data set on introductory, general education, college-level astronomy teaching using the Light and Spectroscopy Concept Inventory (LSCI). We used the…

Training large language models with reinforcement learning (RL) against verifiable rewards significantly enhances their reasoning abilities, yet remains computationally expensive due to inefficient uniform prompt sampling. We introduce…

Large language models (LLMs) have demonstrated exceptional performance across a wide range of natural language tasks. However, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance…

In this work, we propose Visual-Predictive Instruction Tuning (VPiT) - a simple and effective extension to visual instruction tuning that enables a pretrained LLM to quickly morph into an unified autoregressive model capable of generating…

We propose a class of Item Response Theory models for items with ordinal polytomous responses, which extends an existing class of multidimensional models for dichotomously-scored items measuring more than one latent trait. In the proposed…

Item response theory (IRT) models for categorical response data are widely used in the analysis of educational data, computerized adaptive testing, and psychological surveys. However, most IRT models rely on both the assumption that…

Large Language Model (LLM) agents often run for many steps while re-ingesting long system instructions and large tool catalogs each turn. This increases cost, agent derailment probability, latency, and tool-selection errors. We propose…

We introduce Temporal Variational Implicit Neural Representations (TV-INRs), a probabilistic framework for modeling irregular multivariate time series that enables efficient individualized imputation and forecasting. By integrating implicit…

Discovery and learning of an underlying spatiotemporal hierarchy in sequential data is an important topic for machine learning. Despite this, little work has been done to explore hierarchical generative models that can flexibly adapt their…

Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities…

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

Vision Transformers (ViTs) have attracted a lot of popularity in recent years, due to their exceptional capabilities in modeling long-range spatial dependencies and scalability for large scale training. Although the training parallelism of…

We propose a dynamic computational time model to accelerate the average processing time for recurrent visual attention (RAM). Rather than attention with a fixed number of steps for each input image, the model learns to decide when to stop…