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
Bo Li, Peiyuan Zhang, Jingkang Yang +3 authors
OtterHD-8B, an advanced multimodal model from Fuyu-8B, excels in processing high-resolution inputs and discerning detailed spatial relationships through MagnifierBench, an evaluation framework highlighting the importance of vision encoder flexibility.
Xingchao Liu, Xiwen Zhang, Jianzhu Ma +2 authors
Rectified Flow is used to develop an ultra-fast one-step text-to-image generator named InstaFlow, achieving high image quality with significantly reduced inference time compared to existing methods.
Ming Yan, Ruihao Li, Hao Zhang +3 authors
LARP is a language agent framework for open-world games, incorporating memory and decision-making capabilities to enhance interaction and coherence in a diverse range of applications.
Chengsong Huang, Qian Liu, Bill Yuchen Lin +3 authors
LoraHub, a framework for combining LoRA modules, enables few-shot cross-task generalization and facilitates community sharing of LRA modules for large language models.
Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner +9 authors
Naive finetuning of strong pretrained models with weak supervision can improve performance but is insufficient to match full model capabilities, highlighting challenges for aligning superhuman models.
Tianlu Wang, Ping Yu, Xiaoqing Ellen Tan +7 authors
Shepherd, a small language model tuned for critique, outperforms or ties with larger models like ChatGPT in refining language model outputs using a high-quality feedback dataset.
Niklas Muennighoff, Qian Liu, Armel Zebaze +7 authors
Instruction tuning using Git commits improves performance on natural language and coding tasks compared to other benchmarks, with models achieving state-of-the-art results on expanded HumanEvalPack.
Peike Li, Boyu Chen, Yao Yao +3 authors
JEN-1, a diffusion model combining autoregressive and non-autoregressive training, achieves superior performance in text-to-music generation, music inpainting, and continuation, while maintaining computational efficiency.
Zilong Chen, Feng Wang, Huaping Liu
Gaussian Splatting based text-to-3D generation improves geometry accuracy and fidelity through progressive optimization, including geometry optimization and appearance refinement.
Xiaoliang Dai, Ji Hou, Chih-Yao Ma +23 authors
Quality-tuning enhances the aesthetic appeal of text-to-image models through supervised fine-tuning with a small set of high-quality images.
Haoran Xu, Young Jin Kim, Amr Sharaf +1 authors
A novel fine-tuning approach for moderate-sized language models significantly improves translation performance with less parallel data compared to traditional methods.
Linoy Tsaban, Apolinário Passos
LEDITS combines Edit Friendly DDPM inversion and Semantic Guidance to enable versatile and efficient real-image editing using text prompts.
Houwen Peng, Kan Wu, Yixuan Wei +17 authors
A new FP8 automatic mixed-precision framework for training large language models reduces memory usage and increases speed compared to BF16 and Nvidia Transformer Engine.
Jingxiang Sun, Bo Zhang, Ruizhi Shao +4 authors
DreamCraft3D uses a hierarchical approach with diffusion models and tailored 3D priors to generate high-fidelity and coherent 3D objects from 2D references, addressing geometry consistency and texture fidelity.
Yiheng Xu, Hongjin Su, Chen Xing +13 authors
Lemur and Lemur-Chat are open-source language models combining language and coding capabilities, achieving state-of-the-art performance across various benchmarks and agent tasks.
Tero Karras, Miika Aittala, Jaakko Lehtinen +3 authors
Modifications to network layers in the ADM diffusion model architecture improve training stability and synthesis quality, reducing FID from 2.41 to 1.81, and a novel method for post-hoc EMA parameter tuning is introduced.
Jiahao Li, Hao Tan, Kai Zhang +7 authors
Instant3D rapidly generates high-quality 3D assets from text using a two-stage approach involving a fine-tuned 2D diffusion model and a transformer-based reconstructor.
Ali Hatamizadeh, Greg Heinrich, Hongxu Yin +4 authors
FasterViT, a hybrid CNN-ViT model, enhances CV tasks with high image throughput through Hierarchical Attention (HAT) and achieves state-of-the-art performance in accuracy versus throughput.
Zhengqing Yuan, Zhaoxu Li, Lichao Sun
TinyGPT-V, built on Phi-2 with vision modules from BLIP-2 or CLIP, offers high performance with low computational requirements, enabling efficient multimodal large language modeling.
Dimitri von Rütte, Elisabetta Fedele, Jonathan Thomm +1 authors
FABRIC is a training-free method that uses feedback images and self-attention layers to enhance diffusion-based text-to-image models through iterative human feedback.
Zhiqing Sun, Sheng Shen, Shengcao Cao +9 authors
The paper presents Factually Augmented RLHF to address multimodal misalignment in large multimodal models, significantly improving hallucination reduction and overall performance on vision-language tasks compared to existing methods.
In Gim, Guojun Chen, Seung-seob Lee +3 authors
Prompt Cache improves inference speed for large language models by reusing precomputed attention states of common text segments in user prompts.
Anthony Brohan, Noah Brown, Justice Carbajal +51 authors
Vision-language-action models, trained on large-scale vision and language data, are integrated into robotic control to enhance generalization and semantic reasoning.
Wenyi Hong, Weihan Wang, Qingsong Lv +8 authors
CogAgent, a visual language model with strong GUI understanding and navigation capabilities, outperforms LLM-based methods in both PC and Android GUI tasks using only screenshots.
Yuxuan Yan, Chi Zhang, Rui Wang +3 authors
A hybrid guidance framework for identity-preserving image synthesis efficiently generates stylistic portraits by combining stylized images, facial images, and textual prompts.
Shunsuke Saito, Gabriel Schwartz, Tomas Simon +2 authors
Relightable Gaussian Codec Avatars model high-fidelity head avatars with real-time relighting capabilities using 3D Gaussians for geometry and learnable radiance transfer for appearance.
Di Chang, Yichun Shi, Quankai Gao +6 authors
MagicDance, a diffusion-based model, transfers human motion and facial expression across identities in dance videos, achieving high generalization and robust appearance control.
Yunpeng Bai, Xintao Wang, Yanpei Cao +3 authors
DreamDiffusion generates high-quality images from EEG signals using pre-trained text-to-image models and CLIP image encoder for improved alignment and robust representations, overcoming noise and data limitations.
Wenhan Xiong, Jingyu Liu, Igor Molybog +18 authors
Long-context LLMs achieve significant advancements in handling extended contexts through continual pretraining and efficient instruction tuning, surpassing existing models on various benchmarks.
Kai Lv, Yuqing Yang, Tengxiao Liu +3 authors
A new optimizer reduces memory usage for full parameter fine-tuning of large language models, enabling 65B model training on a single machine with limited GPUs.
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