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
Lianghui Zhu, Bencheng Liao, Qian Zhang +3 authors
A new vision backbone using bidirectional Mamba blocks (Vim) outperforms established vision transformers like DeiT in terms of performance and efficiency on high-resolution image tasks.
Corby Rosset, Ching-An Cheng, Arindam Mitra +3 authors
A Direct Nash Optimization (DNO) algorithm is introduced for post-training large language models using preference feedback, achieving state-of-the-art performance with polynomial parameters.
Ziyu Liu, Tao Chu, Yuhang Zang +8 authors
A new benchmark (MMDU) and instruction tuning dataset (MMDU-45k) are introduced to evaluate and enhance large vision-language models' performance in multi-turn and multi-image conversations, highlighting the need for improved conversational instruction tuning data.
Trung Dao, Thuan Hoang Nguyen, Thanh Le +4 authors
Enhancements to SwiftBrush through improved weight initialization, efficient LoRA training, and novel clamped CLIP loss achieve state-of-the-art image quality while maintaining generative diversity.
Yu Zhao, Huifeng Yin, Bo Zeng +6 authors
Marco-o1 extends reasoning models to open-ended domains without clear standards using Chain-of-Thought fine-tuning, Monte Carlo Tree Search, reflection mechanisms, and innovative reasoning strategies.
Mateusz Łajszczak, Guillermo Cámbara, Yang Li +16 authors
BASE TTS, a large-scale text-to-speech model, demonstrates advanced naturalness and emergent abilities using autoregressive Transformers and novel speech tokenization techniques.
Sharath Turuvekere Sreenivas, Saurav Muralidharan, Raviraj Joshi +6 authors
Models Llama 3.1 8B and Mistral NeMo 12B are compressed using pruning and distillation, achieving state-of-the-art performance in a reduced parameter setting.
Bo Li, Yuanhan Zhang, Dong Guo +7 authors
LLaVA-OneVision is a unified multimodal model that advances performance across single-image, multi-image, and video scenarios with strong transfer learning capabilities.
Xun Wu, Shaohan Huang, Wenhui Wang +1 authors
MH-MoE enhances SMoE by splitting tokens into sub-tokens processed by diverse experts in parallel, improving expert activation, context understanding, and overfitting, and demonstrating effectiveness across various modeling tasks.
Fanqing Meng, Jin Wang, Chuanhao Li +9 authors
The Multimodal Multi-image Understanding (MMIU) benchmark assesses LVLMs across various multi-image tasks, highlighting challenges in spatial understanding.
Maosong Cao, Alexander Lam, Haodong Duan +3 authors
CompassJudger-1 is an open-source, all-in-one judge LLM that evaluates LLMs through unitary scoring, model comparisons, critiques, and various tasks, supported by the JudgerBench benchmark.
Zhenxiong Tan, Songhua Liu, Xingyi Yang +2 authors
OminiControl, a parameter-efficient framework, integrates image conditions into Diffusion Transformer models using a parameter reuse mechanism, excelling in subject-driven and spatially-aligned conditional generation.
Qihang Yu, Mark Weber, Xueqing Deng +3 authors
Transformer-based 1D Tokenizer (TiTok) reduces computational demands and enhances image synthesis efficiency by significantly decreasing token count and outperforming state-of-the-art methods in both speed and quality.
Hakim Sidahmed, Samrat Phatale, Alex Hutcheson +16 authors
Parameter-efficient reinforcement learning using LoRA in RLHF matches conventional RLHF performance with reduced computational cost and memory usage.
Tianle Cai, Yuhong Li, Zhengyang Geng +4 authors
Medusa enhances Large Language Model inference by adding parallel decoding heads and using tree-based attention to predict multiple tokens simultaneously, achieving significant speedup with minimal latency.
Mingzhe Zheng, Yongqi Xu, Haojian Huang +8 authors
VGoT generates high-quality, coherent multi-shot videos by structuring the process into script, keyframe, and shot-level generation, using IP embeddings and smoothing mechanisms for consistency and narrative flow.
Ryan Teknium, Jeffrey Quesnelle, Chen Guang
Hermes 3, a neutrally-aligned instruct and tool use model with strong reasoning and creative capabilities, achieves top performance on public benchmarks.
Zhe Chen, Weiyun Wang, Hao Tian +24 authors
InternVL 1.5, an open-source multimodal language model, improves visual understanding and high-resolution image processing through continuous learning, dynamic tile division, and a high-quality bilingual dataset, achieving state-of-the-art results in several benchmarks.
Liang Chen, Zekun Wang, Shuhuai Ren +24 authors
A comprehensive taxonomy unifies multimodal understanding and generation through Next Token Prediction, covering aspects like tokenization, model architectures, task representation, datasets, and open challenges.
Qingkai Fang, Shoutao Guo, Yan Zhou +3 authors
LLaMA-Omni integrates a speech encoder, adaptor, LLM, and decoder for low-latency and high-quality speech interaction with LLMs, outperforming previous models in both content and style.
Christopher E. Mower, Yuhui Wan, Hongzhan Yu +19 authors
A framework enables non-experts to program robots using natural language prompts and contextual information from the Robot Operating System (ROS), supported by large language models and offering various behavior modes, imitation learning, and feedback mechanisms.
Junxiong Wang, Tushaar Gangavarapu, Jing Nathan Yan +1 authors
MambaByte, a token-free byte-level autoregressive model, demonstrates computational efficiency and competitive performance compared to subword token-based models, with the added benefit of fast inference due to linear length scaling.
Junlin Wang, Jue Wang, Ben Athiwaratkun +2 authors
A Mixture-of-Agents (MoA) methodology combines multiple large language models (LLMs) to achieve state-of-the-art performance on various evaluations.
Abhishek Thakur
AutoTrain, an open-source tool, streamlines training and fine-tuning of various machine learning models across multiple tasks and modalities using best practices.
Rundi Wu, Ruiqi Gao, Ben Poole +4 authors
CAT4D is a method that uses a multi-view video diffusion model to generate 4D dynamic scenes from monocular video by optimizing a deformable 3D Gaussian representation.
Maurice Weber, Daniel Fu, Quentin Anthony +16 authors
The RedPajama datasets are introduced to address core challenges for open-source language models by providing transparent data curation, large volumes of high-quality text, and quality signals for web data analysis.
Wei Chen, Zhiyuan Li
A new on-device method improves the performance of a large language model, matching GPT-4's accuracy and latency while reducing context length and enhancing deployment on edge devices.
Junjie Zhou, Zheng Liu, Ze Liu +6 authors
MegaPairs, a data synthesis method using vision language models and open-domain images, generates high-quality multimodal retrieval data, outperforming larger existing datasets and achieving state-of-the-art zero-shot performance.
Santosh V. Patapati
A BiLSTM-based multi-modal model combines audio, facial, and text data using a GPT-4 model to classify depression, achieving state-of-the-art performance in binary classification tasks.
Takuya Akiba, Makoto Shing, Yujin Tang +2 authors
An evolutionary algorithm automates model merging, discovering effective combinations of open-source models without additional training data or compute, achieving state-of-the-art performance on benchmarks and culturally-aware tasks.
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