Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Ohmer, Xenia"'
Emergent language research has made significant progress in recent years, but still largely fails to explore how communication emerges in more complex and situated multi-agent systems. Existing setups often employ a reference game, which limits the r
Externí odkaz:
http://arxiv.org/abs/2408.14649
From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency
The staggering pace with which the capabilities of large language models (LLMs) are increasing, as measured by a range of commonly used natural language understanding (NLU) benchmarks, raises many questions regarding what "understanding" means for a
Externí odkaz:
http://arxiv.org/abs/2404.12145
This paper presents GRASP, a novel benchmark to evaluate the language grounding and physical understanding capabilities of video-based multimodal large language models (LLMs). This evaluation is accomplished via a two-tier approach leveraging Unity s
Externí odkaz:
http://arxiv.org/abs/2311.09048
Autor:
Ackermann, Leon, Ohmer, Xenia
Prompt Tuning is a popular parameter-efficient finetuning method for pre-trained large language models (PLMs). Based on experiments with RoBERTa, it has been suggested that Prompt Tuning activates specific neurons in the transformer's feed-forward ne
Externí odkaz:
http://arxiv.org/abs/2309.12263
At the staggering pace with which the capabilities of large language models (LLMs) are increasing, creating future-proof evaluation sets to assess their understanding becomes more and more challenging. In this paper, we propose a novel paradigm for e
Externí odkaz:
http://arxiv.org/abs/2305.11662
In natural language, referencing objects at different levels of specificity is a fundamental pragmatic mechanism for efficient communication in context. We develop a novel communication game, the hierarchical reference game, to study the emergence of
Externí odkaz:
http://arxiv.org/abs/2203.13176
Language interfaces with many other cognitive domains. This paper explores how interactions at these interfaces can be studied with deep learning methods, focusing on the relation between language emergence and visual perception. To model the emergen
Externí odkaz:
http://arxiv.org/abs/2112.14518
Autor:
Ohmer, Xenia1 (AUTHOR) xenia.ohmer@uni-osnabrueck.de, Marino, Michael1 (AUTHOR), Franke, Michael1,2 (AUTHOR), König, Peter1,3 (AUTHOR)
Publikováno v:
PLoS Computational Biology. 10/31/2022, Vol. 18 Issue 10, p1-28. 28p. 1 Color Photograph, 4 Diagrams, 2 Charts, 4 Graphs.
Publikováno v:
Psychological Science, 2016 Apr 01. 27(4), 542-548.
Externí odkaz:
http://www.jstor.org/stable/24763502
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.