Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Cărbune, Victor"'
Large-language models and large-vision models are increasingly capable of solving compositional reasoning tasks, as measured by breakthroughs in visual-question answering benchmarks. However, state-of-the-art solutions often involve careful construct
Externí odkaz:
http://arxiv.org/abs/2405.19773
Cascades are a common type of machine learning systems in which a large, remote model can be queried if a local model is not able to accurately label a user's data by itself. Serving stacks for large language models (LLMs) increasingly use cascades d
Externí odkaz:
http://arxiv.org/abs/2404.01041
Autor:
Carbune, Victor, Mansoor, Hassan, Liu, Fangyu, Aralikatte, Rahul, Baechler, Gilles, Chen, Jindong, Sharma, Abhanshu
Vision-language models (VLMs) are achieving increasingly strong performance on multimodal tasks. However, reasoning capabilities remain limited particularly for smaller VLMs, while those of large-language models (LLMs) have seen numerous improvements
Externí odkaz:
http://arxiv.org/abs/2403.12596
Autor:
Baechler, Gilles, Sunkara, Srinivas, Wang, Maria, Zubach, Fedir, Mansoor, Hassan, Etter, Vincent, Cărbune, Victor, Lin, Jason, Chen, Jindong, Sharma, Abhanshu
Screen user interfaces (UIs) and infographics, sharing similar visual language and design principles, play important roles in human communication and human-machine interaction. We introduce ScreenAI, a vision-language model that specializes in UI and
Externí odkaz:
http://arxiv.org/abs/2402.04615
While self-correction has shown promise in improving LLM outputs in terms of style and quality (e.g. Chen et al., 2023b; Madaan et al., 2023), recent attempts to self-correct logical or reasoning errors often cause correct answers to become incorrect
Externí odkaz:
http://arxiv.org/abs/2311.08516
Despite recent advances, evaluating how well large language models (LLMs) follow user instructions remains an open problem. While evaluation methods of language models have seen a rise in prompt-based approaches, limited work on the correctness of th
Externí odkaz:
http://arxiv.org/abs/2310.08394
Autor:
Lee, Harrison, Phatale, Samrat, Mansoor, Hassan, Mesnard, Thomas, Ferret, Johan, Lu, Kellie, Bishop, Colton, Hall, Ethan, Carbune, Victor, Rastogi, Abhinav, Prakash, Sushant
Publikováno v:
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26874-26901, 2024
Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but gathering high-quality preference labels is expensive. RL from AI Feedback (RLAIF), introduced in Bai et al.,
Externí odkaz:
http://arxiv.org/abs/2309.00267
Autor:
Hsiao, Yu-Chung, Zubach, Fedir, Baechler, Gilles, Carbune, Victor, Lin, Jason, Wang, Maria, Sunkara, Srinivas, Zhu, Yun, Chen, Jindong
We present a new benchmark and dataset, ScreenQA, for screen content understanding via question answering. The existing screen datasets are focused either on structure and component-level understanding, or on a much higher-level composite task such a
Externí odkaz:
http://arxiv.org/abs/2209.08199
Autor:
Soboleva, Daria, Skopek, Ondrej, Šajgalík, Márius, Cărbune, Victor, Weissenberger, Felix, Proskurnia, Julia, Prisacari, Bogdan, Valcarce, Daniel, Lu, Justin, Prabhavalkar, Rohit, Miklos, Balint
We present a novel multi-modal unspoken punctuation prediction system for the English language which combines acoustic and text features. We demonstrate for the first time, that by relying exclusively on synthetic data generated using a prosody-aware
Externí odkaz:
http://arxiv.org/abs/2010.10203
Autor:
Carbune, Victor, Gonnet, Pedro, Deselaers, Thomas, Rowley, Henry A., Daryin, Alexander, Calvo, Marcos, Wang, Li-Lun, Keysers, Daniel, Feuz, Sandro, Gervais, Philippe
We describe an online handwriting system that is able to support 102 languages using a deep neural network architecture. This new system has completely replaced our previous Segment-and-Decode-based system and reduced the error rate by 20%-40% relati
Externí odkaz:
http://arxiv.org/abs/1902.10525