Towards Practical Single-shot Motion Synthesisby Konstantinos Roditakis, Spyridon Thermos, Nikolaos ZioulisFirst submitted to arxiv on:…
InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretationby Jacob Si, Wendy Yusi…
DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detectionby Zhi Zhou, Ming Yang, Jiang-Xin Shi, Lan-Zhe Guo,…
Exploring Vulnerabilities and Protections in Large Language Models: A Surveyby Frank Weizhen Liu, Chenhui HuFirst…
Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modelingby Sili Huang, Jifeng Hu, Zhejian Yang,…
Quriosity: Analyzing Human Questioning Behavior and Causal Inquiry through Curiosity-Driven Queriesby Roberto Ceraolo, Dmitrii Kharlapenko,…
XPrompt:Explaining Large Language Model’s Generation via Joint Prompt Attributionby Yurui Chang, Bochuan Cao, Yujia Wang,…
SysCaps: Language Interfaces for Simulation Surrogates of Complex Systemsby Patrick Emami, Zhaonan Li, Saumya Sinha,…
LLM as a Complementary Optimizer to Gradient Descent: A Case Study in Prompt Tuningby Zixian…
Stress-Testing Capability Elicitation With Password-Locked Modelsby Ryan Greenblatt, Fabien Roger, Dmitrii Krasheninnikov, David KruegerFirst submitted…