Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Purushwalkam, Senthil"'
Vision-Language Models (VLMs) often generate plausible but incorrect responses to visual queries. However, reliably quantifying the effect of such hallucinations in free-form responses to open-ended queries is challenging as it requires visually veri
Externí odkaz:
http://arxiv.org/abs/2410.13121
Autor:
Ming, Yifei, Purushwalkam, Senthil, Pandit, Shrey, Ke, Zixuan, Nguyen, Xuan-Phi, Xiong, Caiming, Joty, Shafiq
Ensuring faithfulness to context in large language models (LLMs) and retrieval-augmented generation (RAG) systems is crucial for reliable deployment in real-world applications, as incorrect or unsupported information can erode user trust. Despite adv
Externí odkaz:
http://arxiv.org/abs/2410.03727
Autor:
Nguyen, Xuan-Phi, Pandit, Shrey, Purushwalkam, Senthil, Xu, Austin, Chen, Hailin, Ming, Yifei, Ke, Zixuan, Savarese, Silvio, Xong, Caiming, Joty, Shafiq
Retrieval Augmented Generation (RAG), a paradigm that integrates external contextual information with large language models (LLMs) to enhance factual accuracy and relevance, has emerged as a pivotal area in generative AI. The LLMs used in RAG applica
Externí odkaz:
http://arxiv.org/abs/2409.09916
Autor:
Qin, Can, Xia, Congying, Ramakrishnan, Krithika, Ryoo, Michael, Tu, Lifu, Feng, Yihao, Shu, Manli, Zhou, Honglu, Awadalla, Anas, Wang, Jun, Purushwalkam, Senthil, Xue, Le, Zhou, Yingbo, Wang, Huan, Savarese, Silvio, Niebles, Juan Carlos, Chen, Zeyuan, Xu, Ran, Xiong, Caiming
We present xGen-VideoSyn-1, a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions. Building on recent advancements, such as OpenAI's Sora, we explore the latent diffusion model (LDM) architecture and i
Externí odkaz:
http://arxiv.org/abs/2408.12590
Autor:
Xue, Le, Shu, Manli, Awadalla, Anas, Wang, Jun, Yan, An, Purushwalkam, Senthil, Zhou, Honglu, Prabhu, Viraj, Dai, Yutong, Ryoo, Michael S, Kendre, Shrikant, Zhang, Jieyu, Qin, Can, Zhang, Shu, Chen, Chia-Chih, Yu, Ning, Tan, Juntao, Awalgaonkar, Tulika Manoj, Heinecke, Shelby, Wang, Huan, Choi, Yejin, Schmidt, Ludwig, Chen, Zeyuan, Savarese, Silvio, Niebles, Juan Carlos, Xiong, Caiming, Xu, Ran
This report introduces xGen-MM (also known as BLIP-3), a framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resulting suite of LMMs. xGen-MM, s
Externí odkaz:
http://arxiv.org/abs/2408.08872
Recent text-to-image generation models have demonstrated incredible success in generating images that faithfully follow input prompts. However, the requirement of using words to describe a desired concept provides limited control over the appearance
Externí odkaz:
http://arxiv.org/abs/2401.13974
Autor:
Wallace, Bram, Dang, Meihua, Rafailov, Rafael, Zhou, Linqi, Lou, Aaron, Purushwalkam, Senthil, Ermon, Stefano, Xiong, Caiming, Joty, Shafiq, Naik, Nikhil
Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has not been wi
Externí odkaz:
http://arxiv.org/abs/2311.12908
Autor:
Purushwalkam, Senthil, Naik, Nikhil
We present a novel method for reconstructing 3D objects from a single RGB image. Our method leverages the latest image generation models to infer the hidden 3D structure while remaining faithful to the input image. While existing methods obtain impre
Externí odkaz:
http://arxiv.org/abs/2311.05230
Autor:
Nijkamp, Erik, Xie, Tian, Hayashi, Hiroaki, Pang, Bo, Xia, Congying, Xing, Chen, Vig, Jesse, Yavuz, Semih, Laban, Philippe, Krause, Ben, Purushwalkam, Senthil, Niu, Tong, Kryściński, Wojciech, Murakhovs'ka, Lidiya, Choubey, Prafulla Kumar, Fabbri, Alex, Liu, Ye, Meng, Rui, Tu, Lifu, Bhat, Meghana, Wu, Chien-Sheng, Savarese, Silvio, Zhou, Yingbo, Joty, Shafiq, Xiong, Caiming
Large Language Models (LLMs) have become ubiquitous across various domains, transforming the way we interact with information and conduct research. However, most high-performing LLMs remain confined behind proprietary walls, hindering scientific prog
Externí odkaz:
http://arxiv.org/abs/2309.03450
Self-supervised learning (SSL) aims to eliminate one of the major bottlenecks in representation learning - the need for human annotations. As a result, SSL holds the promise to learn representations from data in-the-wild, i.e., without the need for f
Externí odkaz:
http://arxiv.org/abs/2203.12710