Explore · 每周精选
发现最受关注的研究论文,追踪研究趋势,订阅感兴趣的期刊与关键词。
403 篇论文 · 按点赞排序
Shunyu Yao, Dian Yu, Jeffrey Zhao +4 authors
The Tree of Thoughts framework enhances language models' problem-solving capabilities by enabling the exploration and evaluation of multiple reasoning paths and thoughts.
Shanchuan Lin, Bingchen Liu, Jiashi Li +1 authors
Proposed solutions address flaws in diffusion noise schedules and samplers to ensure consistency between training and inference, enabling more accurate image generation.
Gabriela Ben Melech Stan, Diana Wofk, Scottie Fox +8 authors
Latent Diffusion Model for 3D (LDM3D) generates RGBD images from text prompts and is used to create immersive 360-degree-view experiences.
Guanzhi Wang, Yuqi Xie, Yunfan Jiang +5 authors
Voyager is an LLM-powered agent in Minecraft that autonomously explores, learns, and discovers skills through a curriculum, skill library, and prompting mechanism, demonstrating superior lifelong learning and task-solving capabilities.
Jinyang Li, Binyuan Hui, Ge Qu +13 authors
Bird, a large-scale text-to-SQL benchmark, addresses challenges posed by big databases, emphasizing database values, external knowledge, and SQL efficiency.
Vipul Raheja, Dhruv Kumar, Ryan Koo +1 authors
CoEdIT, a fine-tuned large language model, enhances text editing quality and efficiency with diverse instructions, achieving state-of-the-art performance and user preference.
Renrui Zhang, Zhengkai Jiang, Ziyu Guo +5 authors
A training-free and fine-tuning variant of the Segment Anything Model (SAM), PerSAM and PerSAM-F, achieves personalized image and video segmentation using a single reference image and minimal fine-tuning, improving performance on personalized and dreambooth applications.
Lili Yu, Dániel Simig, Colin Flaherty +3 authors
Megabyte, a multi-scale decoder architecture, enables efficient byte-level modeling of long sequences through sub-quadratic self-attention, larger feedforward layers, and improved parallelism, achieving performance competitive with subword models and state-of-the-art results.
Youngjin Jin, Eugene Jang, Jian Cui +3 authors
DarkBERT, a language model trained on Dark Web data, outperforms existing models in various use cases due to its specialized training on the Dark Web's unique linguistic characteristics.
Zhengyi Wang, Cheng Lu, Yikai Wang +4 authors
Variational score distillation addresses issues in text-to-3D generation by modeling 3D parameters as random variables, improving sample quality and diversity.
Zeyue Xue, Guanglu Song, Qiushan Guo +4 authors
A text-conditional image diffusion model named RAPHAEL generates high-quality and artistic images by stacking mixture-of-experts layers, outperforming existing models in style switching and zero-shot FID score.
Nouha Dziri, Ximing Lu, Melanie Sclar +13 authors
Transformers solve compositional tasks by reducing multi-step reasoning to linearized subgraph matching, leading to performance decay with increased complexity.
Yuxin Wen, John Kirchenbauer, Jonas Geiping +1 authors
A novel technique called Tree-Ring Watermarking robustly fingerprints diffusion model outputs by embedding a pattern into the initial noise vector and is invariant to various image transformations.
Shashank Rajput, Nikhil Mehta, Anima Singh +10 authors
A generative retrieval model using Semantic IDs and a Transformer sequence-to-sequence approach improves recommendation system performance and generalization, especially for cold-start items.
Rohan Anil, Andrew M. Dai, Orhan Firat +125 authors
PaLM 2, a Transformer-based language model, improves multilingual and reasoning capabilities with enhanced efficiency and performance across various tasks compared to its predecessor.
Zhibin Gou, Zhihong Shao, Yeyun Gong +4 authors
CRITIC, a framework that uses external tools to validate and improve LLM outputs, consistently enhances performance across various tasks.
Omri Avrahami, Kfir Aberman, Ohad Fried +2 authors
The method decomposes a single image into distinct text tokens for each concept and fine-tunes textual embeddings using masked diffusion loss to enable synthesis with fine-grained control.
Jing Yu Koh, Daniel Fried, Ruslan Salakhutdinov
A method to integrate text-only large language models with image encoders and decoders through embedding space mapping achieves multimodal capabilities including image retrieval, generation, and dialogue.
Yabo Zhang, Yuxiang Wei, Dongsheng Jiang +3 authors
ControlVideo, a training-free framework adapted from ControlNet, improves text-to-video generation by ensuring appearance coherence, reducing flicker, and efficiently producing long videos.
Chen-Yu Lee, Chun-Liang Li, Hao Zhang +13 authors
FormNetV2 uses a centralized multimodal graph contrastive learning approach to improve self-supervised pre-training and achieves state-of-the-art performance on form understanding benchmarks with a compact model.
Ravid Shwartz-Ziv, Yann LeCun
A unified framework integrating information theory to formalize the self-supervised learning problem is presented, exploring the intersection with deep neural networks.
Minghua Liu, Ruoxi Shi, Kaiming Kuang +6 authors
OpenShape learns multi-modal representations for text, images, and 3D point clouds, achieving superior zero-shot performance and fine-grained interactions through novel strategies and hard negative mining.
Yao Zhao, Rishabh Joshi, Tianqi Liu +3 authors
Sequence Likelihood Calibration (SLiC) is shown to be an effective and simpler alternative to Reinforcement Learning from Human Feedback (RLHF) for learning from human preferences in language models.
Yue Wang, Hung Le, Akhilesh Deepak Gotmare +3 authors
CodeT5+, a family of flexible encoder-decoder LLMs initialized with frozen LLMs and trained with a mixture of pretraining objectives, achieves state-of-the-art performance across various code-related tasks.
Joseph Zhu, Peiye Zhuang
Reformulating optimization loss with diffusion prior and introducing depth supervision improve text-to-3D synthesis quality and multi-view consistency.
Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao +3 authors
Model dementia, caused by the use of model-generated content in training, affects the quality of generative models like LLMs, VAEs, and GMMs, highlighting the need for genuine human interaction data.
Zhen Ye, Wei Xue, Xu Tan +3 authors
CoMoSpeech, a consistency model-based method, achieves high-quality speech synthesis with a single diffusion sampling step, significantly speeding up inference compared to traditional models.
Ning Ding, Yulin Chen, Bokai Xu +6 authors
A large-scale dataset, UltraChat, and a fine-tuned model, UltraLLaMA, are created to improve open-source chat language models' performance.
Lingjiao Chen, Matei Zaharia, James Zou
Strategies including prompt adaptation, LLM approximation, and LLM cascade are proposed to reduce costs and maintain or improve performance when using large language models.
Bo Li, Yuanhan Zhang, Liangyu Chen +3 authors
Multimodal instruction tuning improves the performance of models like Otter, based on OpenFlamingo, with an optimized dataset and reduced training resource requirements.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号