Deep Learning
Statistical Knowledge Assessment for Large Language Models
In this paper, we study the problem of quantifying knowledge contained in an LLM regarding a given set of facts.
StressID: a Multimodal Dataset for Stress Identification
Additionally, we provide multimodal predictive models combining video, audio, and physiological inputs.
GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection
We shed light on the current progress of GAD, setting a robust groundwork for subsequent investigations in this domain.
Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models Gen Luo
Instead of using large neural networks to connect the image encoder and LLM, MMA adopts lightweight modules, i.e., adapters, to bridge the gap between LLMs and VL tasks, which also enables the joint optimization of the image and language
AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking Y ang Y u
User modeling, which aims to capture users' characteristics or interests, heavily