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。
50 篇论文 · 按点赞排序
Dongseong Hwang, Weiran Wang, Zhuoyuan Huo +2 authors
Feedback Attention Memory (FAM) enhances Transformer architecture by enabling long-context processing without additional weights, significantly improving performance on large sequences across various model sizes.
Cheng-Ping Hsieh, Simeng Sun, Samuel Kriman +4 authors
RULER is a comprehensive benchmark that extends beyond simple retrieval tasks to evaluate long-context language models' performance on diverse tasks and context lengths.
Taishi Nakamura, Mayank Mishra, Simone Tedeschi +42 authors
Aurora-M, a 15B parameter multilingual open-source model trained on multiple languages and code, addresses challenges of catastrophic forgetting and AI safety through continual pretraining and human-reviewed safety instructions.
Aitor Ormazabal, Che Zheng, Cyprien de Masson d'Autume +22 authors
Reka Core, Flash, and Edge are multimodal language models that achieve state-of-the-art performance across text, image, video, and audio tasks, offering high efficiency and competitive results relative to their compute class.
Eric Wallace, Kai Xiao, Reimar Leike +3 authors
A hierarchical instruction framework for LLMs increases robustness against malicious prompts by selectively prioritizing system instructions over user inputs.
Lin Xu, Yilin Zhao, Daquan Zhou +3 authors
Pooling LLaVA improves video-language pre-trained models by smoothing high-norm visual features, achieving state-of-the-art performance in video question-answering, captioning, and benchmark tasks.
Bo Peng, Daniel Goldstein, Quentin Anthony +24 authors
Eagle and Finch, improvements over RWKV-4, use multi-headed matrix-valued states and dynamic recurrence for enhanced expressivity and efficiency, trained on a multilingual corpus.
Yikang Shen, Zhen Guo, Tianle Cai +1 authors
JetMoE-8B, a cost-effective large language model with 8 billion parameters, achieves impressive performance using a Sparsely-gated Mixture-of-Experts architecture, demonstrating efficient use of resources and computational savings.
Tianle Li, Ge Zhang, Quy Duc Do +2 authors
LIConBench evaluates long-context LLMs on extreme-label classification tasks with sequences up to 50K tokens, highlighting performance dips beyond 20K tokens and favoring of recent labels.
Sunny Sanyal, Sujay Sanghavi, Alexandros G. Dimakis
Inheritune leverages transformer blocks from large language models and minimal data to create smaller, efficient base models with performance competitive to larger models.
Dongzhi Jiang, Guanglu Song, Xiaoshi Wu +5 authors
CoMat, an end-to-end diffusion model fine-tuning strategy with an image-to-text concept matching mechanism, improves text-to-image alignment in SDXL without additional data.
Raehyuk Jung, Hyojun Go, Jaehyuk Yi +41 authors
Pegasus-1 is a multimodal language model designed for video content comprehension, handling spatiotemporal information and demonstrated in benchmarks for video conversation, zero-shot video question answering, and video summarization.
Luchang Li, Sheng Qian, Jie Lu +3 authors
Transformer-Lite optimizes LLM deployment on device GPUs through various techniques to achieve significant speedups in prefill and decoding over CPU and GPU-based methods.
Zhen Zeng, William Watson, Nicole Cho +4 authors
FlowMind uses Large Language Models with a generic prompt recipe to generate automatic workflows, addressing spontaneous tasks and ensuring data integrity, and it is evaluated using a new financial dataset NCEN-QA.
Haotian Zhang, Haoxuan You, Philipp Dufter +8 authors
Ferret-v2 improves on Ferret by incorporating flexible high-resolution grounding, multi-granularity visual encoding with DINOv2, and a three-stage training paradigm, leading to enhanced visual understanding and performance.
Shenghai Yuan, Jinfa Huang, Yujun Shi +6 authors
MagicTime enhances Text-to-Video synthesis by integrating real-world physics knowledge through metamorphic time-lapse videos, using the MagicAdapter, Dynamic Frames Extraction, and Magic Text-Encoder techniques.
Zhen Ye, Zeqian Ju, Haohe Liu +10 authors
FlashSpeech, using latent consistency model and adversarial consistency training, achieves fast and high-quality zero-shot speech synthesis with enhanced prosody generation.
Ruibo Liu, Jerry Wei, Fangyu Liu +8 authors
The success of AI models relies on the availability of large, diverse, and high-quality datasets, which can be challenging to obtain due to data scarcity, privacy concerns, and high costs. Synthetic data has emerged as a promising solution by generating artificial data that mimics real-world patterns. This paper provides an overview of synthetic data research, discussing its applications, challenges, and future directions. We present empirical evidence from prior art to demonstrate its effectiveness and highlight the importance of ensuring its factuality, fidelity, and unbiasedness. We emphasize the need for responsible use of synthetic data to build more powerful, inclusive, and trustworthy language models.
Chuofan Ma, Yi Jiang, Jiannan Wu +2 authors
Groma, a Multimodal Large Language Model, utilizes region-level visual tokenization to enhance visual understanding and localization accuracy in image-grounded tasks.
Xiaoyi Dong, Pan Zhang, Yuhang Zang +21 authors
InternLM-XComposer2-4KHD enhances high-resolution understanding capabilities in LVLMs up to 4K, surpassing existing models with dynamic patch configuration and consistent performance improvements.
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