Education
Aligner: Efficient Alignment by Learning to Correct
Aligner can be applied to any powerful, large-scale upstream models. Moreover, it can even iteratively bootstrap the upstream models using corrected responses as synthetic human preference data, breaking through the model's performance ceiling.
Advancing Video Anomaly Detection: A Concise Review and a New Dataset
Video Anomaly Detection (V AD) finds widespread applications in security surveillance, traffic monitoring, industrial monitoring, and healthcare.
ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
Temporal action segmentation and long-term action anticipation are two popular vision tasks for the temporal analysis of actions in videos.
IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation Fan Lin
Item Discrimination (ID) theory, which is widely used in educational assessment, measures the ability of individual test items to differentiate between high and low performers. Inspired by this theory, we propose an ID-induced prompt synthesis framework for evaluating LLMs to ensure the evaluation set can continually update and refine according to model abilities.
MedJourney: Benchmark and Evaluation of Large Language Models over Patient Clinical Journey Xian Wu
In this paper, we address this gap by dividing a typical patient's clinical journey
AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers
LLMs' flexibility is largely due to an "in-context learning" effect that emerges when