Summary of Sam 2: Segment Anything in Images and Videos, by Nikhila Ravi et al.
SAM 2: Segment Anything in Images and Videosby Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang…
SAM 2: Segment Anything in Images and Videosby Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang…
A Natural Language Processing Framework for Hotel Recommendation Based on Users’ Text Reviewsby Lavrentia Aravani,…
CERT-ED: Certifiably Robust Text Classification for Edit Distanceby Zhuoqun Huang, Neil G Marchant, Olga Ohrimenko,…
Leaf Angle Estimation using Mask R-CNN and LETR Vision Transformerby Venkat Margapuri, Prapti Thapaliya, Trevor…
Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Modelby Benlin Liu, Yuhao Dong, Yiqin Wang,…
Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attentionby Susung HongFirst submitted…
Tamper-Resistant Safeguards for Open-Weight LLMsby Rishub Tamirisa, Bhrugu Bharathi, Long Phan, Andy Zhou, Alice Gatti,…
AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationby…
Dilated convolution neural operator for multiscale partial differential equationsby Bo Xu, Xinliang Liu, Lei ZhangFirst…
Learning Structurally Stabilized Representations for Multi-modal Lossless DNA Storageby Ben Cao, Tiantian He, Xue Li,…