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
Lingmin Ran, Xiaodong Cun, JiaWei Liu +5 authors
X-Adapter upgrades text-to-image diffusion models like SDXL to work with existing plugins without retraining, through feature remapping and a null-text training strategy.
Yuelang Xu, Benwang Chen, Zhe Li +4 authors
The method uses controllable 3D Gaussians and a fully learned MLP-based deformation field for high-fidelity 3D head avatar modeling under sparse views, employing geometry-guided initialization with implicit SDF and Deep Marching Tetrahedra for stability and high rendering quality.
Qiying Yu, Quan Sun, Xiaosong Zhang +4 authors
CapsFusion is an advanced framework that improves multimodal pretraining data by combining web-based image-text pairs and synthetic captions, leading to enhanced model performance, sample efficiency, and scalability.
Tianxing Wu, Chenyang Si, Yuming Jiang +2 authors
FreeInit addresses the temporal consistency and unnatural dynamics issues in diffusion-based video generation by refining spatial-temporal low-frequency components during inference, improving subject appearance and consistency.
Saurabh Saxena, Junhwa Hur, Charles Herrmann +2 authors
A generic diffusion model with log-scale depth parameterization and FOV conditioning achieves state-of-the-art zero-shot metric depth estimation by handling indoor and outdoor scenes effectively and reducing relative error significantly.
Xiangpeng Wei, Haoran Wei, Huan Lin +15 authors
PolyLM, a multilingual LLM trained on 640 billion tokens, enhances multilingual capabilities through bilingual data and curriculum learning, outperforming other models on multilingual tasks while maintaining English performance.
Yifeng Ma, Shiwei Zhang, Jiayu Wang +3 authors
DreamTalk enables expressive talking head generation using diffusion models with specialized components for denoising, lip-sync, and style prediction.
Yi Wang, Yinan He, Yizhuo Li +10 authors
InternVid, a large-scale video-text multimodal dataset, and ViCLIP, a video-text representation model based on ViT-L, enable advanced video and text understanding and generation tasks.
Arnav Chavan, Zhuang Liu, Deepak Gupta +2 authors
GLoRA, an advanced method for parameter-efficient fine-tuning, enhances LoRA with a generalized prompt module and modular layer-wise structure search, offering superior performance across diverse tasks with fewer parameters and computational costs.
Tan Wang, Linjie Li, Kevin Lin +5 authors
DISCO addresses the challenges of human-centric dance synthesis by introducing a model architecture for better faithfulness and compositionality, and pre-training for generalizability.
Cheng Li, Mingyang Zhang, Qiaozhu Mei +4 authors
A multistage and multitask framework using large language models enhances personalized text generation by improving retrieval, ranking, summarization, synthesis, and generation skills.
Benjamin Spector, Chris Re
A staged speculative decoding algorithm enhances LLM inference efficiency in small-batch, on-device settings by restructuring speculative batches and adding a second decoding stage.
Xiao Liu, Hao Yu, Hanchen Zhang +19 authors
AgentBench is a multi-dimensional benchmark for evaluating LLMs as autonomous agents across various interactive environments, highlighting performance differences between commercial and open-source models.
Yecheng Jason Ma, William Liang, Guanzhi Wang +6 authors
Eureka, an LLM-powered reward design algorithm, generates human-level reward functions enhancing reinforcement learning for complex manipulation tasks and RLHF, including pen spinning with a simulated Shadow Hand.
Chaoning Zhang, Dongshen Han, Sheng Zheng +3 authors
A new approach improves MobileSAM's efficiency for the SegEvery task by directly generating valid masks, boosting performance and reducing computation time.
Bichen Wu, Ching-Yao Chuang, Xiaoyan Wang +6 authors
Fairy, an adaptation of image-editing diffusion models for video editing, uses anchor-based cross-frame attention to enhance temporal coherence and efficiency, outperforming existing methods.
Binhui Liu, Xin Liu, Anbo Dai +3 authors
The dual-stream diffusion net (DSDN) enhances video consistency and smoothness in text-to-video generation by using separate content and motion diffusion streams with a cross-transformer interaction module and motion decomposer/combiner.
Aojun Zhou, Ke Wang, Zimu Lu +8 authors
A novel code-based self-verification method significantly improves math reasoning in GPT-4 Code Interpreter, enhancing accuracy on the MATH dataset.
Ariel N. Lee, Cole J. Hunter, Nataniel Ruiz
A fine-tuned and merged family of large language models named Platypus, using LoRA modules and a curated dataset, achieves top performance on the Open LLM Leaderboard with reduced data and compute.
Elad Richardson, Kfir Goldberg, Yuval Alaluf +1 authors
Creative text-to-image generation leverages Diffusion Prior models to produce unique images by optimizing with adaptive constraints and creating hybrid concepts.
Zeju Qiu, Weiyang Liu, Haiwen Feng +6 authors
Orthogonal Finetuning and Constrained Orthogonal Finetuning methods enhance text-to-image diffusion models by preserving hyperspherical energy and improving stability, leading to better generation quality and speed.
Huichao Zhang, Bowen Chen, Hao Yang +7 authors
AvatarVerse generates high-fidelity 3D avatars from text descriptions and pose guidance using a 2D diffusion model and progressive high-resolution synthesis.
Joey Hejna, Rafael Rafailov, Harshit Sikchi +4 authors
A new regret-based algorithm, Contrastive Preference Learning (CPL), learns optimal policies directly from human preferences without learning a reward function, addressing optimization challenges in Reinforcement Learning from Human Feedback (RLHF).
Lingjiao Chen, Matei Zaharia, James Zou
The performance and behavior of GPT-3.5 and GPT-4 fluctuated significantly between March and June 2023 across various tasks, emphasizing the necessity for ongoing LLM quality monitoring.
Michael Moor, Qian Huang, Shirley Wu +6 authors
Med-Flamingo, an adaptation of OpenFlamingo-9B for the medical domain, demonstrates few-shot capabilities in generative visual question answering with significant performance improvements as evaluated by clinicians.
Vladislav Lialin, Namrata Shivagunde, Sherin Muckatira +1 authors
ReLoRA, a low-rank training method, demonstrates comparable performance to traditional training for large transformer language models and becomes more efficient with increased model size.
Haoxiang Wang, Pavan Kumar Anasosalu Vasu, Fartash Faghri +6 authors
A unified model combining CLIP and SAM using multi-task learning, continual learning, and distillation techniques achieves state-of-the-art zero-shot semantic segmentation performance with reduced computational and data requirements.
Tianyi Chen, Tianyu Ding, Badal Yadav +2 authors
LoRAShear is an efficient method for pruning and knowledge recovery in Large Language Models, reducing their size by 20% with minimal performance loss.
Dingyao Yu, Kaitao Song, Peiling Lu +5 authors
MusicAgent is a system that integrates various music-related tools and uses large language models to automate music processing tasks based on user requests.
Ziqi Wang, Le Hou, Tianjian Lu +4 authors
A new framework, ImPlicit Self-ImprovemenT (PIT), uses human preference data to implicitly enhance the quality of Large Language Model responses, outperforming prompting-based 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