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
Ning Miao, Yee Whye Teh, Tom Rainforth
A zero-shot verification scheme improves LLMs' question-answering performance by identifying and correcting errors in step-by-step reasoning.
Wenxuan Zhou, Sheng Zhang, Yu Gu +2 authors
Targeted distillation using mission-focused instruction tuning distills ChatGPT into the smaller UniversalNER model, achieving higher NER accuracy across diverse domains than both general and state-of-the-art multi-task tuned models.
Lichang Chen, Shiyang Li, Jun Yan +8 authors
A data selection strategy using a strong LLM improves instruction-following models by filtering high-quality data, enhancing performance and reducing training time.
Aditya Sanghi, Pradeep Kumar Jayaraman, Arianna Rampini +4 authors
A pre-trained vision model's features enable generation of 3D shapes from sketches without paired datasets by leveraging synthetic renderings during training.
Jiaao Chen, Xiaoman Pan, Dian Yu +4 authors
A novel prompting strategy called skills-in-context (SKiC) enhances compositional generalization in large language models by enabling them to solve unseen complex problems through the synergistic activation and combination of internal skills.
Jerry Wei, Da Huang, Yifeng Lu +2 authors
Studies reveal that language models exhibit sycophancy, altering responses to align with user views, and a synthetic-data intervention can mitigate this behavior.
Liang Wang, Nan Yang, Furu Wei
A framework is proposed for training dense retrievers to select high-quality in-context examples for large language models, enhancing their performance across various tasks.
Quan Sun, Qiying Yu, Yufeng Cui +7 authors
Emu, a Transformer-based multimodal model, generates images and texts in various contexts and demonstrates superior performance across zero-shot and few-shot tasks compared to existing models.
Deepanway Ghosal, Yew Ken Chia, Navonil Majumder +1 authors
Fine-tuning VICUNA on a customized instruction dataset called FLANMINI enhances its problem-solving skills, leading to improved performance across various benchmarks.
Zhen Qin, Dong Li, Weigao Sun +9 authors
TransNormerLLM, a linear attention-based LLM, outperforms softmax attention models through advanced modifications like positional embedding, lightning attention, gating mechanisms, and tensor normalization, achieving better accuracy and efficiency.
Yu-Ting Lan, Kan Ren, Yansen Wang +4 authors
A pipeline named NeuroImagen uses EEG signals and a latent diffusion model to reconstruct high-resolution visual images, demonstrating superior performance in image reconstruction.
Yuxian Gu, Li Dong, Furu Wei +1 authors
MiniLLM distills knowledge from large generative language models to smaller models using reverse KLD for better precision, quality, and performance.
Haocheng Xi, Changhao Li, Jianfei Chen +1 authors
A novel method for training transformers with 4-bit quantization achieves competitive accuracy and accelerates training on current GPUs.
Yuheng Li, Haotian Liu, Yangming Wen +1 authors
A text-to-image diffusion model is enhanced with adapter layers and regionally-guided sampling to achieve controlled generation of personalized objects with high fidelity.
Zheng Yuan, Hongyi Yuan, Chengpeng Li +3 authors
Rejection sampling fine-tuning enhances mathematical reasoning in large language models by generating auxiliary datasets of correct reasoning paths, leading to higher performance and better scalability compared to supervised fine-tuning.
George E. Dahl, Frank Schneider, Zachary Nado +22 authors
A new benchmark, AlgoPerf: Training Algorithms, addresses challenges in evaluating training algorithms by providing a competitive, time-to-result benchmark across workloads and optimizers.
Shengming Yin, Chenfei Wu, Jian Liang +4 authors
DragNUWA is a diffusion-based video generation model that integrates text, image, and trajectory controls for fine-grained and open-domain video creation.
Xiaoxiao Long, Yuan-Chen Guo, Cheng Lin +8 authors
Wonder3D leverages cross-domain diffusion models and geometry-aware normal fusion for high-quality, efficient, and consistent 3D mesh generation from single-view images.
Jun Chen, Deyao Zhu, Xiaoqian Shen +7 authors
MiniGPT-v2 is a unified vision-language model that uses task-specific identifiers to perform diverse tasks with high performance.
Yang Wu, Shilong Wang, Hao Yang +4 authors
GPT-4V demonstrates strong visual understanding but has limitations in language comprehension, handling sensitive data, modalities like depth and audio, and fine visual nuances.
Tung Phung, Victor-Alexandru Pădurean, José Cambronero +5 authors
Systematic evaluation of ChatGPT and GPT-4 in educational scenarios demonstrates GPT-4's superior performance over ChatGPT and identifies areas needing improvement.
Joan Puigcerver, Carlos Riquelme, Basil Mustafa +1 authors
Soft MoE, a differentiable sparse Transformer, stabilizes training, reduces inference cost, and outperforms traditional Transformers and MoE variants in visual recognition.
Mihir Prabhudesai, Anirudh Goyal, Deepak Pathak +1 authors
AlignProp refines text-to-image diffusion models using backpropagation through the denoising process, leveraging low-rank adapters and gradient checkpointing to optimize for various objectives with higher efficiency.
Samuel L. Smith, Andrew Brock, Leonard Berrada +1 authors
ConvNets pre-trained on a large dataset match the performance of Vision Transformers on ImageNet with comparable computational resources.
Andrea Gesmundo, Kaitlin Maile
The research introduces methods to incrementally enlarge transformer-based neural networks while preserving their functionality, enabling efficient training of larger models.
Weiran Yao, Shelby Heinecke, Juan Carlos Niebles +12 authors
A framework using policy gradient optimization to enhance large language agents by learning from environment feedback, improving their performance over time.
Ruoxi Sun, Sercan O Arik, Hootan Nakhost +4 authors
SQL-PaLM, an LLM-based Text-to-SQL model, outperforms existing systems in few-shot learning and fine-tuning settings and demonstrates superior generalization on diverse variants of the Spider dataset.
Xiang Deng, Yu Gu, Boyuan Zheng +5 authors
Mind2Web, a dataset for generalist web agents, uses real-world websites and crowdsourced actions to improve LLM performance and generalizability.
Theo X. Olausson, Jeevana Priya Inala, Chenglong Wang +2 authors
GPT-4 demonstrates superior self-repair capabilities on APPS dataset compared to GPT-3.5, with performance boosted when feedback is provided by GPT-4 or human programmers.
Yujun Shi, Chuhui Xue, Jiachun Pan +3 authors
DragDiffusion extends interactive point-based image editing to diffusion models, offering precise spatial control and high-quality editing across diverse scenarios.
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