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
Zhen Xu, Sida Peng, Haotong Lin +5 authors
4K4D, a 4D point cloud representation with a hybrid appearance model and differentiable depth peeling algorithm, achieves high-speed and high-quality dynamic view synthesis at 4K resolution.
Luka Ribar, Ivan Chelombiev, Luke Hudlass-Galley +3 authors
SparQ Attention reduces memory bandwidth requirements in LLM attention blocks, enhancing inference throughput without accuracy loss.
Peng Li, Yeye He, Dror Yashar +6 authors
A new table-tuning paradigm improves language models' understanding and generalization in table-related tasks by fine-tuning them with synthesized table data, resulting in enhanced performance.
Stephen Casper, Xander Davies, Claudia Shi +29 authors
RLHF is analyzed for its limitations and flaws, with suggestions for improvement, complementation, and oversight to enhance safer AI development.
Xuefei Ning, Zinan Lin, Zixuan Zhou +2 authors
"Skeleton-of-Thought" (SoT) method reduces generation latency and potentially improves answer quality by guiding LLMs to generate a skeleton first, followed by parallel content completion.
Hyeonho Jeong, Geon Yeong Park, Jong Chul Ye
The VMC framework enhances video generation by tuning temporal attention layers in diffusion models to accurately reproduce and diversify motion with a motion distillation objective.
SeungHeon Doh, Keunwoo Choi, Jongpil Lee +1 authors
A large-scale pseudo music caption dataset generated using LLMs improves music captioning performance over supervised models in zero-shot and transfer-learning settings.
Xingang Pan, Ayush Tewari, Thomas Leimkühler +3 authors
DragGAN enables precise user-controlled manipulation of image content through interactive point dragging, improving realism and flexibility over existing GAN-based methods.
Jinze Bai, Shuai Bai, Yunfei Chu +45 authors
Qwen, a series of large language models, including chat and specialized coding and mathematics variants, exhibit superior performance across various tasks and outperform open-source models.
Mengyang Feng, Jinlin Liu, Kai Yu +11 authors
DreaMoving is a diffusion-based framework that generates high-quality, customized human dance videos by controlling motion and preserving identity.
Haotian Liu, Chunyuan Li, Yuheng Li +1 authors
Modifications to LLaVA using CLIP-ViT-L-336px and academic VQA data improve multimodal performance, achieving state-of-the-art results with limited training data.
Juan A. Rodriguez, Shubham Agarwal, Issam H. Laradji +4 authors
StarVector integrates CodeLLMs and vision models to generate complex SVGs by aligning visual and code tokens, enhancing visual quality and complexity handling.
Ke Hong, Guohao Dai, Jiaming Xu +6 authors
FlashDecoding++ addresses challenges in LLM inference through asynchronized softmax, flat GEMM optimization, and heuristic dataflow adaptation, achieving significant speedups.
Jingkang Yang, Yuhao Dong, Shuai Liu +8 authors
Octopus, a novel vision-language model, integrates multimodal perception and reasoning to perform diverse tasks using GPT-4 and Reinforcement Learning with Environmental Feedback in an experimental environment called OctoVerse.
Kumar Tanmay, Aditi Khandelwal, Utkarsh Agarwal +1 authors
A new evaluation framework connects human psychology and AI to assess the moral reasoning and development stages of large language models using a Psychometric Assessment Tool.
Kai Zhang, Lingbo Mo, Wenhu Chen +2 authors
MagicBrush, a large-scale manually annotated dataset for text-guided real image editing, enhances InstructPix2Pix model performance and highlights challenges in current baselines.
Sondos Mahmoud Bsharat, Aidar Myrzakhan, Zhiqiang Shen
Guiding principles streamline querying and prompting of large language models, enhancing understanding and effectiveness across different scales.
Rishabh Agarwal, Nino Vieillard, Yongchao Zhou +4 authors
Generalized Knowledge Distillation addresses distribution mismatch in auto-regressive sequence models by training the student on its own output sequences and integrates with RL fine-tuning for effective distillation in tasks like summarization and instruction-tuning.
Izzeddin Gur, Hiroki Furuta, Austin Huang +4 authors
WebAgent uses Flan-U-PaLM and HTML-T5 to improve task success in real-world web navigation through decomposed instructions, HTML summarization, and Python code generation.
Haohe Liu, Qiao Tian, Yi Yuan +7 authors
A unified audio generation framework using a language of audio representation, AudioMAE, and latent diffusion model achieves state-of-the-art performance across different audio types.
Yiming Wang, Yu Lin, Xiaodong Zeng +1 authors
MultiLoRA improves multi-task adaptation for large language models by reducing the dominance of top singular vectors in LoRA parameter updates through horizontal scaling and modified initialization.
Cheng-Yu Hsieh, Si-An Chen, Chun-Liang Li +5 authors
LLMs can effectively use tool documentation instead of demonstrations to perform complex tasks, achieving performance comparable or superior to few-shot learning on both vision and language benchmarks.
Zihao Wang, Shaofei Cai, Anji Liu +9 authors
JARVIS-1, an open-world agent in Minecraft, uses multimodal perception and a memory system to perform complex tasks and improve over time.
Hu Ye, Jun Zhang, Sibo Liu +2 authors
IP-Adapter introduces a lightweight decoupled cross-attention mechanism to enhance pretrained text-to-image diffusion models with image prompt capabilities, enabling multimodal image generation and compatibility with existing tools.
Omar Khattab, Arnav Singhvi, Paridhi Maheshwari +10 authors
DSPy is a programming model for developing and optimizing language model pipelines by abstracting them as text transformation graphs with parameterized modules that learn through demonstrations.
Aaron Gokaslan, A. Feder Cooper, Jasmine Collins +6 authors
A transfer learning technique and efficient training recipe using Creative Commons images enable high-quality text-to-image models with synthetic captions and reduced computational requirements.
David Rein, Betty Li Hou, Asa Cooper Stickland +5 authors
A dataset of extremely difficult multiple-choice questions challenges both experts and AI systems, facilitating the development of scalable oversight methods for AI-generated knowledge.
Frano Rajič, Lei Ke, Yu-Wing Tai +3 authors
SAM-PT extends SAM for video object segmentation using robust and sparse point propagation, achieving strong zero-shot performance and demonstrating advantages on benchmarks like DAVIS, YouTube-VOS, MOSE, and UVO.
Mostafa Dehghani, Basil Mustafa, Josip Djolonga +12 authors
NaViT, a flexible Vision Transformer, processes images of arbitrary resolutions and aspect ratios, improving training efficiency and performance across various computer vision tasks.
Tian Lan, Deng Cai, Yan Wang +2 authors
Text generation is improved by copying text segments from a pre-existing collection, resulting in better quality and efficiency compared to traditional methods.
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