Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Pal, Arka"'
As fine-tuning large language models (LLMs) becomes increasingly prevalent, users often rely on third-party services with limited visibility into their fine-tuning processes. This lack of transparency raises the question: how do consumers verify that
Externí odkaz:
http://arxiv.org/abs/2411.06611
Many application domains, e.g., in medicine and manufacturing, can greatly benefit from pneumatic Soft Robots (SRs). However, the accurate control of SRs has remained a significant challenge to date, mainly due to their nonlinear dynamics and viscoel
Externí odkaz:
http://arxiv.org/abs/2408.03754
Autor:
White, Colin, Dooley, Samuel, Roberts, Manley, Pal, Arka, Feuer, Ben, Jain, Siddhartha, Shwartz-Ziv, Ravid, Jain, Neel, Saifullah, Khalid, Naidu, Siddartha, Hegde, Chinmay, LeCun, Yann, Goldstein, Tom, Neiswanger, Willie, Goldblum, Micah
Test set contamination, wherein test data from a benchmark ends up in a newer model's training set, is a well-documented obstacle for fair LLM evaluation and can quickly render benchmarks obsolete. To mitigate this, many recent benchmarks crowdsource
Externí odkaz:
http://arxiv.org/abs/2406.19314
Autor:
Kapoor, Sanyam, Gruver, Nate, Roberts, Manley, Collins, Katherine, Pal, Arka, Bhatt, Umang, Weller, Adrian, Dooley, Samuel, Goldblum, Micah, Wilson, Andrew Gordon
When using large language models (LLMs) in high-stakes applications, we need to know when we can trust their predictions. Some works argue that prompting high-performance LLMs is sufficient to produce calibrated uncertainties, while others introduce
Externí odkaz:
http://arxiv.org/abs/2406.08391
Direct Preference Optimisation (DPO) is effective at significantly improving the performance of large language models (LLMs) on downstream tasks such as reasoning, summarisation, and alignment. Using pairs of preferred and dispreferred data, DPO mode
Externí odkaz:
http://arxiv.org/abs/2402.13228
Autor:
Pal, Arka, Karkhanis, Deep, Roberts, Manley, Dooley, Samuel, Sundararajan, Arvind, Naidu, Siddartha
Modern large language models (LLMs) that rely on attention mechanisms are typically trained with fixed context lengths which enforce upper limits on the length of input sequences that they can handle at evaluation time. To use these models on sequenc
Externí odkaz:
http://arxiv.org/abs/2308.10882
Autor:
Burgess, Christopher P., Higgins, Irina, Pal, Arka, Matthey, Loic, Watters, Nick, Desjardins, Guillaume, Lerchner, Alexander
We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders. Taking a rate-distortion theory perspective, we show the circumstances under which representations aligned with the und
Externí odkaz:
http://arxiv.org/abs/1804.03599
Autor:
Higgins, Irina, Pal, Arka, Rusu, Andrei A., Matthey, Loic, Burgess, Christopher P, Pritzel, Alexander, Botvinick, Matthew, Blundell, Charles, Lerchner, Alexander
Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generali
Externí odkaz:
http://arxiv.org/abs/1707.08475
Autor:
Higgins, Irina, Sonnerat, Nicolas, Matthey, Loic, Pal, Arka, Burgess, Christopher P, Bosnjak, Matko, Shanahan, Murray, Botvinick, Matthew, Hassabis, Demis, Lerchner, Alexander
The seemingly infinite diversity of the natural world arises from a relatively small set of coherent rules, such as the laws of physics or chemistry. We conjecture that these rules give rise to regularities that can be discovered through primarily un
Externí odkaz:
http://arxiv.org/abs/1707.03389
Autor:
Higgins, Irina, Matthey, Loic, Glorot, Xavier, Pal, Arka, Uria, Benigno, Blundell, Charles, Mohamed, Shakir, Lerchner, Alexander
Automated discovery of early visual concepts from raw image data is a major open challenge in AI research. Addressing this problem, we propose an unsupervised approach for learning disentangled representations of the underlying factors of variation.
Externí odkaz:
http://arxiv.org/abs/1606.05579