GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Modelsby Haibo…
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelsby Zhihong Shao, Peiyi Wang,…
Nevermind: Instruction Override and Moderation in Large Language Modelsby Edward KimFirst submitted to arxiv on:…
Do Diffusion Models Learn Semantically Meaningful and Efficient Representations?by Qiyao Liang, Ziming Liu, Ila FieteFirst…
AONeuS: A Neural Rendering Framework for Acoustic-Optical Sensor Fusionby Mohamad Qadri, Kevin Zhang, Akshay Hinduja,…
Test-Time Adaptation for Depth Completionby Hyoungseob Park, Anjali Gupta, Alex WongFirst submitted to arxiv on:…
HASSOD: Hierarchical Adaptive Self-Supervised Object Detectionby Shengcao Cao, Dhiraj Joshi, Liang-Yan Gui, Yu-Xiong WangFirst submitted…
SpecFormer: Guarding Vision Transformer Robustness via Maximum Singular Value Penalizationby Xixu Hu, Runkai Zheng, Jindong…
Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentationsby Helen Qu, Sang Michael XieFirst submitted…
Slot Structured World Modelsby Jonathan Collu, Riccardo Majellaro, Aske Plaat, Thomas M. MoerlandFirst submitted to…