7 Papers & Radios | MiniGPT-4看图聊天、还能草图建网站;视频版Stable Diffusion来了
机器之心 & ArXiv Weekly
参与:楚航、罗若天、梅洪源
本周论文包括慕尼黑大学、英伟达等机构的研究者利用潜在扩散模型(latent diffusion model, LDM)实现了高分辨率的长视频合成;MiniGPT-4 发布,能看图聊天、还能草图建网站。
目录
Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models MiniGPT-4:Enhancing Vision-language Understanding with Advanced Large Language Models OpenAssistant Conversations - Democratizing Large Language Model Alignment Inpaint Anything: Segment Anything Meets Image Inpainting Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP Plan4MC: Skill Reinforcement Learning and Planning for Open-World Minecraft Tasks T2Ranking: A large-scale Chinese Benchmark for Passage Ranking ArXiv Weekly Radiostation:NLP、CV、ML 更多精选论文(附音频)
作者:Andreas Blattmann 、 Robin Rombach 等 论文地址:https://arxiv.org/pdf/2304.08818.pdf
作者:朱德尧、陈军、沈晓倩、李祥、Mohamed H. Elhoseiny 论文地址:https://minigpt-4.github.io/
作者:Andreas Köpf、Yannic Kilcher 等 论文地址:https://drive.google.com/file/d/10iR5hKwFqAKhL3umx8muOWSRm7hs5FqX/view
作者:Tao Yu、Runseng Feng 等 论文地址:http://arxiv.org/abs/2304.06790
作者:Feng Liang 、 Bichen Wu 等 论文地址:https://arxiv.org/pdf/2210.04150.pdf
作者:Haoqi Yuan、Chi Zhang 等 论文地址:https://arxiv.org/abs/2303.16563
作者:Xiaohui Xie、Qian Dong 等 论文地址:https://arxiv.org/abs/2304.03679
1. Task-oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10. (from Hermann Ney)
2. Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task. (from Wei Liu, Dinggang Shen)
3. On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training. (from Tat-Seng Chua)
4. Stochastic Parrots Looking for Stochastic Parrots: LLMs are Easy to Fine-Tune and Hard to Detect with other LLMs. (from Rachid Guerraoui)
5. Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models. (from Kai-Wei Chang, Song-Chun Zhu, Jianfeng Gao)
6. MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning. (from Meng Wang, Erik Cambria, Guoying Zhao)
7. GeneGPT: Teaching Large Language Models to Use NCBI Web APIs. (from Zhiyong Lu)
8. A Survey on Biomedical Text Summarization with Pre-trained Language Model. (from Sophia Ananiadou)
9. Emotion fusion for mental illness detection from social media: A survey. (from Sophia Ananiadou)
10. Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes. (from Christopher Ré)
本周 10 篇 CV 精选论文是:
1. NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models. (from Antonio Torralba)
2. Align-DETR: Improving DETR with Simple IoU-aware BCE loss. (from Xiangyu Zhang)
3. Exploring Incompatible Knowledge Transfer in Few-shot Image Generation. (from Shuicheng Yan)
4. Learning Situation Hyper-Graphs for Video Question Answering. (from Mubarak Shah)
5. Video Generation Beyond a Single Clip. (from Ming-Hsuan Yang)
6. A Data-Centric Solution to NonHomogeneous Dehazing via Vision Transformer. (from Huan Liu)
7. Neuromorphic Optical Flow and Real-time Implementation with Event Cameras. (from Luca Benini, Davide Scaramuzza)
8. Language Guided Local Infiltration for Interactive Image Retrieval. (from Lei Zhang)
9. LipsFormer: Introducing Lipschitz Continuity to Vision Transformers. (from Lei Zhang)
10. UVA: Towards Unified Volumetric Avatar for View Synthesis, Pose rendering, Geometry and Texture Editing. (from Dacheng Tao)
本周 10 篇 ML 精选论文是:
1. Bridging RL Theory and Practice with the Effective Horizon. (from Stuart Russell)
2. Towards transparent and robust data-driven wind turbine power curve models. (from Klaus-Robert Müller)
3. Open-World Continual Learning: Unifying Novelty Detection and Continual Learning. (from Bing Liu)
4. Learning in latent spaces improves the predictive accuracy of deep neural operators. (from George Em Karniadakis)
5. Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One. (from Xuelong Li)
6. Generalization and Estimation Error Bounds for Model-based Neural Networks. (from Yonina C. Eldar)
7. RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment. (from Tong Zhang)
8. Adaptive Consensus Optimization Method for GANs. (from Pawan Kumar)
9. Angle based dynamic learning rate for gradient descent. (from Pawan Kumar)
10. AGNN: Alternating Graph-Regularized Neural Networks to Alleviate Over-Smoothing. (from Wenzhong Guo)
© THE END
转载请联系本公众号获得授权
投稿或寻求报道:[email protected]
微信扫码关注该文公众号作者