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。
598 篇论文 · 按点赞排序
Peng Xia, Siwei Han, Shi Qiu +9 authors
MMIE is a large-scale benchmark for evaluating interleaved multimodal comprehension and generation in Large Vision-Language Models using diverse data and reliable automated evaluation metrics.
Ziyue Li, Tianyi Zhou
Mixture-of-Experts (MoE) LLMs can serve as effective embedding models without finetuning, with their routing weights and hidden states complementing each other to enhance performance.
Hyungjoo Chae, Yeonghyeon Kim, Seungone Kim +8 authors
Think-and-Execute is a novel framework that enhances algorithmic reasoning in large language models by decomposing the reasoning process into task-level logic expressed as pseudocode and instance-specific execution.
Yoav HaCohen, Nisan Chiprut, Benny Brazowski +13 authors
LTX-Video, a transformer-based latent diffusion model, integrates Video-VAE and denoising transformer for efficient high-resolution video generation with temporal consistency.
Haoyu Lu, Wen Liu, Bo Zhang +11 authors
DeepSeek-VL is an open-source vision-language model that achieves state-of-the-art performance in real-world applications by combining a hybrid vision encoder with effective pretraining strategies to preserve language model capabilities.
Xin Dong, Yonggan Fu, Shizhe Diao +10 authors
Hymba, a family of small language models with a hybrid-head architecture combining transformer attention and state space models, achieves state-of-the-art performance with improved efficiency and reduced cache size.
Wei Huang, Yangdong Liu, Haotong Qin +5 authors
BiLLM, a 1-bit post-training quantization scheme for pretrained LLMs, achieves high-accuracy inference with reduced computational and memory requirements.
Jintao Zhang, Jia wei, Pengle Zhang +2 authors
A new quantization method for attention mechanisms, named SageAttention, enhances inference speed and accuracy without significant loss in performance across various models.
Terry Yue Zhuo, Minh Chien Vu, Jenny Chim +30 authors
Benchmark Bench assesses LLMs' capability to solve practical programming tasks by invoking function calls from various libraries, revealing significant performance gaps compared to human developers.
Cong Wei, Zheyang Xiong, Weiming Ren +3 authors
An omnipotent image editor trained on multisource supervision, importance sampling, and a versatile architecture excels in multiple tasks with diverse aspect ratios and high data quality.
Dingjie Song, Sicheng Lai, Shunian Chen +2 authors
A framework called MM-Detect is introduced to detect data contamination in multimodal large language models, demonstrating sensitivity across different contamination levels and identifying potential contamination stages during pre-training and fine-tuning.
Zhiyong Wu, Zhenyu Wu, Fangzhi Xu +8 authors
OS-Atlas improves GUI agent performance through a large open-source GUI grounding dataset and model innovations.
Richard Yuanzhe Pang, Weizhe Yuan, Kyunghyun Cho +3 authors
An iterative preference optimization method using a modified DPO loss improves reasoning accuracy on various datasets by optimizing winning and losing reasoning steps in Chain-of-Thought candidates.
Ning-Hsu Wang, Yu-Lun Liu
A new depth estimation framework for 360-degree imagery uses pseudo-labels generated by perspective depth models to improve accuracy, especially in zero-shot scenarios.
Xiaotian Han, Yiren Jian, Xuefeng Hu +8 authors
InfiMM-WebMath-40B, a large multimodal dataset, significantly improves mathematical reasoning capabilities in LLMs, achieving state-of-the-art performance on multimodal benchmarks.
Abhilash Nandy, Yash Agarwal, Ashish Patwa +5 authors
Current Vision-Language models struggle with satirical image detection, understanding, and completion tasks on a newly released high-quality dataset called YesBut.
Ting Jiang, Shaohan Huang, Shengyue Luo +8 authors
MoRA, a high-rank updating method using square matrices, enhances the ability of large language models to learn and memorize new knowledge, especially in memory-intensive tasks, compared to LoRA.
Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen +14 authors
Chronos, a framework using pretrained transformer-based models for time series forecasting, outperforms classical methods and achieves comparable zero-shot performance on unseen datasets using tokenized time series data.
Chaoyou Fu, Haojia Lin, Zuwei Long +12 authors
VITA, an open-source Multimodal Large Language Model, excels in processing Video, Image, Text, and Audio with seamless interaction, showcasing advancements in multimodal understanding and human-computer interaction.
Shengpeng Ji, Ziyue Jiang, Xize Cheng +13 authors
WavTokenizer provides extreme audio compression and state-of-the-art quality by expanding the VQ space, contextual windows, attention networks, and using a multi-scale discriminator and inverse Fourier transform.
Yutao Sun, Hangbo Bao, Wenhui Wang +5 authors
LatentLM integrates continuous and discrete data using causal Transformers, VAEs, and next-token diffusion, achieving superior performance in multimodal tasks like image generation, large language model integration, and text-to-speech synthesis.
Run Luo, Haonan Zhang, Longze Chen +13 authors
MMEvol, a multimodal instruction data evolution framework, enhances the capabilities of Multimodal Large Language Models by generating diverse and complex image-text instruction datasets, leading to improved performance across various vision-language tasks.
Ivan Rubachev, Nikolay Kartashev, Yury Gorishniy +1 authors
TabReD is a new collection of industry-grade tabular datasets that address temporal dynamics and feature engineering, revealing that simpler models outperform more complex deep learning architectures in these settings.
Weimin Wang, Jiawei Liu, Zhijie Lin +9 authors
MagicVideo-V2 generates high-fidelity and smooth videos from text using an integrated pipeline that includes text-to-image, video motion generation, and frame interpolation modules, outperforming existing systems in user evaluations.
Mihir Prabhudesai, Russell Mendonca, Zheyang Qin +2 authors
Utilizing pre-trained reward models to adapt video diffusion models with gradient-based feedback enhances efficiency and performance compared to gradient-free methods.
Chien-Yao Wang, I-Hau Yeh, Hong-Yuan Mark Liao
The paper addresses data loss in deep networks through programmable gradient information (PGI) and introduces the Generalized Efficient Layer Aggregation Network (GELAN) to improve parameter utilization and achieve competitive results in object detection.
Aleksandar Botev, Soham De, Samuel L Smith +59 authors
RecurrentGemma, using Griffin architecture, achieves excellent language performance with efficient memory usage and fewer training tokens compared to Gemma-2B.
Erik Wijmans, Brody Huval, Alexander Hertzberg +2 authors
Cut Cross-Entropy reduces the memory footprint of large language models during training by efficiently computing cross-entropy loss without materializing logits for all tokens.
Yanwei Li, Yuechen Zhang, Chengyao Wang +5 authors
Mini-Gemini enhances multi-modality Vision Language Models through high-resolution visual tokens, high-quality datasets, and VLM-guided generation, achieving leading performance in zero-shot benchmarks.
Ming Li, Taojiannan Yang, Huafeng Kuang +4 authors
ControlNet++ enhances text-to-image generation controllability through pixel-level cycle consistency optimization using an efficient noise-disturbed reward strategy.
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