MultiDiffusion employs multi-path optimization to enable controllable image generation without retraining, supporting diverse constraints like aspect ratio and spatial masks.

Omer Bar-Tal, Lior Yariv, Yaron Lipman et al.

Proposes a numerically stable second-order influence function estimator achieving √n consistency in high-dimensional settings.

Lin Liu, Chang Li

Proposes a performance optimization framework using PIE dataset, achieving 6.86× average speedup with large language models.

Alexander Shypula, Aman Madaan, Yimeng Zeng et al.

PolyFormer introduces sequence-to-sequence polygon generation for referring image segmentation, achieving 5.40% and 4.52% improvements on RefCOCO+ and RefCOCOg.

Jiang Liu, Hui Ding, Zhaowei Cai et al.

ConceptFusion leverages foundation models for open-set, multimodal 3D mapping, enabling zero-shot queries with over 40% improvement in 3D IoU.

Krishna Murthy Jatavallabhula, Alihusein Kuwajerwala, Qiao Gu et al.

STREET benchmark evaluates multi-task reasoning and explanation; GPT-3 and T5 models lag behind human performance.

Danilo Ribeiro, Shen Wang, Xiaofei Ma et al.

Immunizing images with imperceptible adversarial perturbations prevents diffusion models from realistic editing.

Hadi Salman, Alaa Khaddaj, Guillaume Leclerc et al.

DCMT framework improves CVR AUC by 1.07%, addressing selection bias and data sparsity.

Feng Zhu, Mingjie Zhong, Xinxing Yang et al.

Evaluated GPT-3 (text-davinci-003) on the SARA dataset for legal reasoning, using various prompting methods, achieving better results but with notable errors and knowledge gaps.

Andrew Blair-Stanek, Nils Holzenberger, Benjamin Van Durme

This study reveals that instruction-tuned LLMs exhibit programmable behaviors akin to traditional programs, enabling security attacks like code injection and virtualization, raising dual-use risks.

Daniel Kang, Xuechen Li, Ion Stoica et al.

Proposes ViT-22B with parallel layers, QK normalization, and bias removal, achieving stable training at 22B parameters, surpassing prior models.

Mostafa Dehghani, Josip Djolonga, Basil Mustafa et al.

Combining reinforcement learning and sequential optimization, the method achieves up to 150% improvement in intersection management metrics.

Nishchal Hoysal G., Pavankumar Tallapragada

This survey reviews over 300 methods for automatic knowledge graph construction, focusing on knowledge acquisition, refinement, and evolution, emphasizing deep learning and multi-scenario applications.

Lingfeng Zhong, Jia Wu, Qian Li et al.

Toolformer enables self-supervised learning for language models to call external APIs, boosting zero-shot performance with only 6.7B parameters.

Timo Schick, Jane Dwivedi-Yu, Roberto Dessì et al.

Adapting pre-trained Vision Transformers from 2D to 3D using weight inflation improves medical image segmentation, achieving a 1.95% DSC increase.

Yuhui Zhang, Shih-Cheng Huang, Zhengping Zhou et al.

Riemannian Flow Matching (RFM) enables simulation-free, scalable generative modeling on complex manifolds using spectral distances, achieving state-of-the-art results.

Ricky T. Q. Chen, Yaron Lipman

DSIR framework uses hashed n-gram importance resampling to efficiently select 100M documents, boosting downstream performance.

Sang Michael Xie, Shibani Santurkar, Tengyu Ma et al.

pix2pix-zero enables image-to-image translation without manual prompts, preserving original image structure.

Gaurav Parmar, Krishna Kumar Singh, Richard Zhang et al.

FAEP employs ATSP-based path optimization and adaptive yaw planning, reducing exploration time by over 20% and path length by 20% compared to state-of-the-art methods.

Yinghao Zhao, Li Yan, Hong Xie et al.

First non-asymptotic learning bounds for Koopman operator using EDMD and RRR algorithms.

Vladimir Kostic, Karim Lounici, Pietro Novelli et al.