SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference

Kavli Affiliate: Feng Wang | First 5 Authors: Feng Wang, Jieru Mei, Alan Yuille, , | Summary: Recent advances in contrastive language-image pretraining (CLIP) have demonstrated strong capabilities in zero-shot classification by aligning visual representations with target text embeddings in an image level. However, in dense prediction tasks, CLIP often struggles to localize visual features […]


Continue.. SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference

SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference

Kavli Affiliate: Feng Wang | First 5 Authors: Feng Wang, Jieru Mei, Alan Yuille, , | Summary: Recent advances in contrastive language-image pretraining (CLIP) have demonstrated strong capabilities in zero-shot classification by aligning visual representations with target text embeddings in an image level. However, in dense prediction tasks, CLIP often struggles to localize visual features […]


Continue.. SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference

Using Large Language Models to Accelerate Communication for Users with Severe Motor Impairments

Kavli Affiliate: Michael P. Brenner | First 5 Authors: Shanqing Cai, Subhashini Venugopalan, Katie Seaver, Xiang Xiao, Katrin Tomanek | Summary: Finding ways to accelerate text input for individuals with profound motor impairments has been a long-standing area of research. Closing the speed gap for augmentative and alternative communication (AAC) devices such as eye-tracking keyboards […]


Continue.. Using Large Language Models to Accelerate Communication for Users with Severe Motor Impairments

Neutron stars more compact than black holes as a probe of strong-field gravity

Kavli Affiliate: Lijing Shao | Summary:Probing gravity in its strongest regime is a central goal of modern physics, as the nature of the most compact objects reflects fundamental aspects of Einstein’s theory of general relativity (GR). In GR, black holes are regarded as the most compact objects in the Universe. Here, for the first time, […]


Continue.. Neutron stars more compact than black holes as a probe of strong-field gravity

The Operator Product Expansion in Quantum Field Theory

Kavli Affiliate: Robert Wald | Summary:Operator product expansions (OPEs) in quantum field theory (QFT) provide an asymptotic relation between products of local fields defined at points $x_1, dots, x_n$ and local fields at point $y$ in the limit $x_1, dots, x_n to y$. They thereby capture in a precise way the singular behavior of products […]


Continue.. The Operator Product Expansion in Quantum Field Theory

Explore the Nucleon Tomography through Di-hadron Correlation in Opposite Hemisphere in Deep Inelastic Scattering

Kavli Affiliate: Feng Yuan | First 5 Authors: Yuxun Guo, Feng Yuan, , , | Summary: We investigate the correlation of di-hadron productions between the current fragmentation region (CFR) and target fragmentation region (TFR) in deep inelastic scattering as a probe of the nucleon tomography. The QCD factorization and powering counting method are applied to […]


Continue.. Explore the Nucleon Tomography through Di-hadron Correlation in Opposite Hemisphere in Deep Inelastic Scattering

Do Mini-halos Affect Cosmic Reionization?

Kavli Affiliate: Nickolay Y. Gnedin | First 5 Authors: Nickolay Y. Gnedin, , , , | Summary: The role of unresolved structures ("mini-halos") in determining the consumption of ionizing photons during cosmic reionization remains an unsolved problem in modeling cosmic reionization, despite recent extensive studies with small-box high-resolution simulations by Park et al. and Chan […]


Continue.. Do Mini-halos Affect Cosmic Reionization?

Towards a Psychological Generalist AI: A Survey of Current Applications of Large Language Models and Future Prospects

Kavli Affiliate: Dan Luo | First 5 Authors: Tianyu He, Guanghui Fu, Yijing Yu, Fan Wang, Jianqiang Li | Summary: The complexity of psychological principles underscore a significant societal challenge, given the vast social implications of psychological problems. Bridging the gap between understanding these principles and their actual clinical and real-world applications demands rigorous exploration […]


Continue.. Towards a Psychological Generalist AI: A Survey of Current Applications of Large Language Models and Future Prospects

Manipulating the Label Space for In-Context Classification

Kavli Affiliate: Jing Wang | First 5 Authors: Haokun Chen, Xu Yang, Yuhang Huang, Zihan Wu, Jing Wang | Summary: After pre-training by generating the next word conditional on previous words, the Language Model (LM) acquires the ability of In-Context Learning (ICL) that can learn a new task conditional on the context of the given […]


Continue.. Manipulating the Label Space for In-Context Classification