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
Gemma Team, Morgane Riviere, Shreya Pathak +193 authors
Gemma 2 introduces improvements in the Transformer architecture through interleaving local-global attentions and group-query attention, showcasing superior performance relative to its size.
Zhengqing Yuan, Ruoxi Chen, Zhaoxu Li +4 authors
A new multi-agent framework Mora replicates Sora's generalist video generation capabilities using several advanced visual AI agents, achieving similar performance across various tasks.
Fanghua Yu, Jinjin Gu, Zheyuan Li +6 authors
SUPIR, an advanced image restoration method combining generative prior and model scaling, achieves high-quality results and flexible restoration guided by textual prompts.
Elizaveta Goncharova, Anton Razzhigaev, Matvey Mikhalchuk +6 authors
The OmniFusion model, leveraging pretrained LLMs and visual adapters, demonstrates superior performance across multiple visual-language benchmarks compared to open-source alternatives.
Lital Binyamin, Yoad Tewel, Hilit Segev +3 authors
CountGen enhances text-to-image diffusion models by accurately controlling the number of depicted objects using features that carry object identity information, surpassing existing methods on benchmark datasets.
Zhengyi Wang, Jonathan Lorraine, Yikai Wang +4 authors
The work demonstrates the capability of LLMs to generate 3D meshes from text by introducing a novel approach to tokenize 3D mesh data, allowing the unification of 3D and text modalities without expanding the model's vocabulary.
Taiming Lu, Tianmin Shu, Alan Yuille +2 authors
Generative World Explorer (Genex) enables agents to mentally explore 3D environments using imagined observations, updating their beliefs without physical exploration to improve decision-making.
Pavan Kumar Anasosalu Vasu, Fartash Faghri, Chun-Liang Li +8 authors
FastVLM, using FastViTHD, optimizes Vision Language Models by scaling image resolution to reduce latency and token count, improving time-to-first-token and maintaining performance.
Jinjie Ni, Yifan Song, Deepanway Ghosal +10 authors
MixEval-X is a benchmark designed to optimize and standardize multi-modal evaluations, addressing issues of inconsistency and bias in real-world applications.
Lin Chen, Xilin Wei, Jinsong Li +12 authors
The ShareGPT4Video series enhances video understanding and generation using dense captions and an efficient captioning strategy by addressing temporal and spatial challenges in video annotation.
Wenliang Dai, Nayeon Lee, Boxin Wang +7 authors
NVML 1.0, a family of multimodal large language models, achieves state-of-the-art results in vision-language tasks by combining text-only and multimodal training, utilizing a new architecture and dataset strategy.
Keyu Tian, Yi Jiang, Zehuan Yuan +2 authors
Visual AutoRegressive (VAR) modeling improves image generation performance and speed over autoregressive and diffusion transformer models, achieving superior results in image quality, data efficiency, and scalability.
Yang Shen, Xiu-Shen Wei, Yifan Sun +6 authors
An auto-regressive vision-language model trained with explanatory instructions achieves instruction-level zero-shot capabilities and strong zero-shot generalization in computer vision tasks.
Chanran Kim, Jeongin Lee, Shichang Joung +2 authors
InstantFamily uses masked cross-attention and multimodal embeddings to generate images with preserved multi-IDs and high visual coherence.
Zongyu Lin, Wei Liu, Chen Chen +14 authors
STIV, a text-image-conditioned video generation method integrating Diffusion Transformer and classifier-free guidance, achieves state-of-the-art performance in text-to-video, text-image-to-video, and image-to-video tasks.
Maciej Pióro, Kamil Ciebiera, Krystian Król +2 authors
A combination of Mixture of Experts (MoE) with State Space Models (SSMs) improves model efficiency and performance compared to both standalone SSMs and MoE-enhanced Transformers.
Kai Mei, Zelong Li, Shuyuan Xu +3 authors
AIOS, an operating system embedding large language models, addresses resource allocation, context switching, and concurrency challenges for intelligent agents, demonstrating reliability and efficiency.
Zhenting Qi, Mingyuan Ma, Jiahang Xu +3 authors
rStar enhances small language models' reasoning capabilities through a self-play mutual generation-discrimination process without fine-tuning, improving accuracy across various reasoning tasks.
Lucas Beyer, Andreas Steiner, André Susano Pinto +32 authors
PaliGemma, a versatile Vision-Language Model based on SigLIP-So400m and Gemma-2B, demonstrates strong performance across numerous open-world tasks, including specialized areas like remote sensing and segmentation.
Saleh Ashkboos, Maximilian L. Croci, Marcelo Gennari do Nascimento +2 authors
SliceGPT, a novel post-training sparsification method, reduces model parameters by up to 25% without significant performance decrease, optimizing inference speed and GPU usage on large language models.
Daya Guo, Qihao Zhu, Dejian Yang +10 authors
DeepSeek-Coder, a series of open-source code models trained from scratch, outperforms both open-source and closed-source models across multiple benchmarks.
Tianjun Zhang, Shishir G. Patil, Naman Jain +4 authors
Retrieval Augmented FineTuning (RAFT) enhances pre-trained large language models' in-domain performance by filtering out irrelevant documents and citing relevant passages.
Guanting Dong, Chenghao Zhang, Mengjie Deng +3 authors
AR-MCTS enhances multimodal large language models' reasoning capabilities through active retrieval, Monte Carlo Tree Search, and a process reward model, improving performance across multimodal reasoning tasks.
Zhangchen Xu, Fengqing Jiang, Luyao Niu +4 authors
Magpie, a self-synthesis method, generates high-quality instruction data from aligned LLMs, enabling competitive performance in alignment benchmarks compared to models fine-tuned with larger, supervised datasets.
Egor Cherepanov, Nikita Kachaev, Artem Zholus +2 authors
The paper provides a framework for understanding and evaluating different types of memory in reinforcement learning agents, using cognitive science-inspired definitions and a standardized experimental methodology.
Jake Bruce, Michael Dennis, Ashley Edwards +22 authors
Genie, a 11B parameter unsupervised generative model, creates action-controllable virtual worlds from unlabelled videos using spatiotemporal tokenization and autoregressive dynamics, enabling agent training from unseen video behaviors.
Bofei Gao, Feifan Song, Yibo Miao +21 authors
Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM's output with human preferences. This alignment process often requires only a small amount of data to efficiently enhance the LLM's performance. While effective, research in this area spans multiple domains, and the methods involved are relatively complex to understand. The relationships between different methods have been under-explored, limiting the development of the preference alignment. In light of this, we break down the existing popular alignment strategies into different components and provide a unified framework to study the current alignment strategies, thereby establishing connections among them. In this survey, we decompose all the strategies in preference learning into four components: model, data, feedback, and algorithm. This unified view offers an in-depth understanding of existing alignment algorithms and also opens up possibilities to synergize the strengths of different strategies. Furthermore, we present detailed working examples of prevalent existing algorithms to facilitate a comprehensive understanding for the readers. Finally, based on our unified perspective, we explore the challenges and future research directions for aligning large language models with human preferences.
Axel Sauer, Frederic Boesel, Tim Dockhorn +3 authors
Latent Adversarial Diffusion Distillation (LADD) simplifies the training and improves the performance of diffusion models by using generative features from latent diffusion models, enabling fast and high-resolution image synthesis.
Pat Verga, Sebastian Hofstatter, Sophia Althammer +6 authors
Evaluating Large Language Models using a Panel of smaller evaluators outperforms single large evaluators with reduced bias and cost.
Sushant Gautam, Andrea Storås, Cise Midoglu +4 authors
Kvasir-VQA is a dataset with question-and-answer annotations for GI diagnostics, supporting image captioning, VQA, synthetic image generation, object detection, and classification.
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