Related papers: UniER: A Unified Benchmark for Item-level and Path…

We consider the problem of teaching via demonstrations in sequential decision-making settings. In particular, we study how to design a personalized curriculum over demonstrations to speed up the learner's convergence. We provide a unified…

The goal of recommender systems is to provide ordered item lists to users that best match their interests. As a critical task in the recommendation pipeline, re-ranking has received increasing attention in recent years. In contrast to…

Scaling reinforcement learning to tens of thousands of parallel environments requires overcoming the limited exploration capacity of a single policy. Ensemble-based policy gradient methods, which employ multiple policies to collect diverse…

To promote precision medicine, individualized treatment regimes (ITRs) are crucial for optimizing the expected clinical outcome based on patient-specific characteristics. However, existing ITR research has primarily focused on scenarios…

Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like Reinforcement Learning with Human Feedback (RLHF) face notable challenges. These approaches require high-quality datasets of positive…

In recent years, neural networks and other complex models have dominated recommender systems, often setting new benchmarks for state-of-the-art performance. Yet, despite these advancements, award-winning research has demonstrated that…

The "pre-training $\rightarrow$ downstream adaptation" presents both new opportunities and challenges for Continual Learning (CL). Although the recent state-of-the-art in CL is achieved through Parameter-Efficient-Tuning (PET) adaptation…

Analyzing student behavior in educational scenarios is crucial for enhancing teaching quality and student engagement. Existing AI-based models often rely on classroom video footage to identify and analyze student behavior. While these…

Generative Recommendation has emerged as a transformative paradigm, reformulating recommendation as an end-to-end autoregressive sequence generation task. Despite its promise, existing preference optimization methods typically rely on…

The scaling of Large Language Models (LLMs) is increasingly limited by data quality. Most methods handle data mixing and sample selection separately, which can break the structure in code corpora. We introduce \textbf{UniGeM}, a framework…

This Work in Progress Research paper departs from the recent, turbulent changes in global societies, forcing many citizens to re-skill themselves to (re)gain employment. Learners therefore need to be equipped with skills to be autonomous…

Peer grading has emerged as a scalable solution for assessment in large and online classrooms, offering both logistical efficiency and pedagogical value. However, designing effective peer-grading systems remains challenging due to…

This paper addresses the challenge of jointly modeling user intent diversity and behavioral uncertainty in recommender systems. A unified representation learning framework is proposed. The framework builds a multi-intent representation…

Handwritten Mathematical Expression Recognition (HMER) remains a persistent challenge in Optical Character Recognition (OCR) due to the inherent freedom of symbol layouts and variability in handwriting styles. Prior methods have faced…

Inventory-policy comparisons are often difficult to interpret because performance depends on the evaluation contract as much as on the policy itself. Differences in topology, demand regime, information access, feasibility constraints,…

Model ensemble is an effective strategy in continual learning, which alleviates catastrophic forgetting by interpolating model parameters, achieving knowledge fusion learned from different tasks. However, existing model ensemble methods…

Unhealthy behaviors, e.g., physical inactivity and unhealthful food choice, are the primary healthcare cost drivers in developed countries. Pervasive computational, sensing, and communication technology provided by smartphones and…

Continual Instruction Tuning (CIT) is adopted to continually instruct Large Models to follow human intent data by data. It is observed that existing gradient update would heavily destroy the performance on previous datasets during CIT…

Given multiple videos of the same task, procedure learning addresses identifying the key-steps and determining their order to perform the task. For this purpose, existing approaches use the signal generated from a pair of videos. This makes…

Video reasoning has advanced with large multimodal models (LMMs), yet their inference is often a single pass that returns an answer without verifying whether the reasoning is evidence-aligned. We introduce Reinforce to Learn, Elect to…