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
Dongchao Yang, Jinchuan Tian, Xu Tan +9 authors
UniAudio, a unified language model system, generates various audio types effectively using tokenization, sequence concatenation, and next-token prediction, with a multi-scale Transformer model handling extended sequences.
Tu Vu, Mohit Iyyer, Xuezhi Wang +8 authors
FreshQA evaluates LLMs' factuality and hallucination in responding to current knowledge questions, revealing limitations and demonstrating improvements through FreshPrompt, an augmented prompting method using search engine data.
Kevin Lin, Faisal Ahmed, Linjie Li +9 authors
MM-VID integrates GPT-4V with specialized tools to transcribe and understand long-form, multimodal videos, supporting advanced tasks like audio description and character identification.
Jifan Yu, Xiaozhi Wang, Shangqing Tu +32 authors
A benchmark for evaluating large language models emphasizes knowledge-related abilities, uses a mix of datasets, and incorporates self-contrast metrics to detect knowledge hallucination.
Hang Zhang, Xin Li, Lidong Bing
Video-LLaMA is a multi-modal framework that integrates visual and auditory understanding into LLMs by extending image encoders to video and aligning audio signals, achieving effective video-language correspondence.
Wenqi Shao, Mengzhao Chen, Zhaoyang Zhang +7 authors
OmniQuant improves LLM deployment by optimizing quantization parameters through Learnable Weight Clipping and Learnable Equivalent Transformation, enhancing performance across various quantization settings.
Bo Peng, Eric Alcaide, Quentin Anthony +27 authors
A new architecture, RWKV, combines the parallelizable training of Transformers with the efficient inference of RNNs, achieving linear scaling and matching performance.
Zhiwei Liu, Weiran Yao, Jianguo Zhang +12 authors
A comprehensive comparison and new orchestration strategy for LLM-augmented Autonomous Agents (LAAs) demonstrate their effectiveness in decision-making and multi-step reasoning tasks.
Thomas McGrath, Matthew Rahtz, Janos Kramar +2 authors
Analysis reveals adaptive computation and downregulation mechanisms in language models, showing loose coupling among layers even without dropout.
Yaqi Zhang, Di Huang, Bin Liu +7 authors
MotionGPT generates realistic human motion using multimodal control signals by adapting a small portion of LLM parameters to handle unified input instructions.
Ruida Wang, Wangchunshu Zhou, Mrinmaya Sachan
Synthesis Step by Step (S3) iteratively refines synthesized pseudo training examples using a large language model to reduce distributional discrepancies and improve small model performance on NLP tasks.
Juan Rocamonde, Victoriano Montesinos, Elvis Nava +2 authors
Pretrained vision-language models can serve as zero-shot reward models in reinforcement learning, enabling complex task learning from minimal natural language prompts.
Kangfu Mei, Mauricio Delbracio, Hossein Talebi +3 authors
A novel single-stage distillation method for generative diffusion models reduces sampling time while maintaining performance across tasks like super-resolution and image editing.
Weizhi Wang, Li Dong, Hao Cheng +4 authors
A framework called LongMem enables large language models to utilize long-term memory, overcoming input length limitations and improving performance on long-context tasks.
Zhengyu Huang, Haoran Xie, Tsukasa Fukusato +1 authors
A latent space exploration of StyleGAN is used for generating high-quality anime portraits from incomplete sketches with a stroke-level disentanglement approach.
Arno Candel, Jon McKinney, Philipp Singer +12 authors
h2oGPT provides open-source, fine-tuned LLMs based on Generative Pretrained Transformers with 100% private document search capabilities.
Jie Huang, Wei Ping, Peng Xu +3 authors
RAVEN enhances in-context learning in retrieval-augmented encoder-decoder models by combining masked and prefix language modeling, achieving superior performance with fewer parameters.
Ke Chen, Yusong Wu, Haohe Liu +3 authors
A text-to-music model named MusicLDM, based on Stable Diffusion and AudioLDM, overcomes limitations in music data and plagiarism with beat tracking and mixup strategies, enhancing music quality, novelty, and text correspondence.
Weihao Yu, Zhengyuan Yang, Linjie Li +5 authors
MM-Vet evaluates large multimodal models across complicated tasks using defined vision-language capabilities and a unified LLM-based evaluator.
Nan Ding, Tomer Levinboim, Jialin Wu +2 authors
Theoretical analysis shows that prefix language models outperform causal language models in in-context learning by converging to optimal solutions, while causal models exhibit dynamics similar to online gradient descent.
Eric Nguyen, Michael Poli, Marjan Faizi +10 authors
HyenaDNA, a genomic foundation model based on implicit convolutions, achieves state-of-the-art performance on various benchmarks with longer context lengths, single nucleotide resolution, and fewer parameters.
Dani Valevski, Danny Wasserman, Yossi Matias +1 authors
A method to condition text-to-image generation models on face embeddings in real-time, enhancing generative capabilities and bias mitigation.
Kaiyu Yang, Aidan M. Swope, Alex Gu +6 authors
LeanDojo provides open-source tools, data, and benchmarks to facilitate research on machine learning methods for theorem proving, introducing ReProver, an LLM-based prover that uses retrieval for premise selection.
Nikos Kolotouros, Thiemo Alldieck, Andrei Zanfir +3 authors
DreamHuman generates realistic animatable 3D human avatars using text by integrating text-to-image synthesis, neural radiance fields, and statistical human body models.
Sriram Yenamandra, Arun Ramachandran, Karmesh Yadav +15 authors
The HomeRobot OVMM benchmark evaluates robots' ability to manipulate unseen objects in new environments using a combination of simulated and real-world testing.
Ohad Rubin, Jonathan Berant
The Retrieval-Pretrained Transformer jointly trains a retrieval-augmented language model to model long texts by fusing retrieved information for improved prediction.
Gregor Bachmann, Sotiris Anagnostidis, Thomas Hofmann
MLPs achieve competitive performance on vision tasks with large-scale pre-training, challenging the narrative that inductive bias is necessary for high accuracy.
Tiange Luo, Chris Rockwell, Honglak Lee +1 authors
Cap3D generates high-quality descriptive text for 3D objects using pretrained models and datasets, surpassing human performance in quality, cost, and speed.
Chaoning Zhang, Dongshen Han, Yu Qiao +4 authors
MobileSAM enhances the Segment Anything Model (SAM) for mobile devices by decoupling the image encoder and mask decoder to create a lightweight version that maintains performance while significantly reducing size and improving speed.
Zalán Borsos, Matt Sharifi, Damien Vincent +3 authors
SoundStorm, a non-autoregressive audio generation model, delivers high-quality and consistent audio two orders of magnitude faster than autoregressive 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