E-LIB Suche - Ergebnisse für: Korbak, Tomasz

1

A continuity of Markov blanket interpretations under the fr..:

Seth, Anil ; Korbak, Tomasz ; Tschantz, Alexander
Behavioral and Brain Sciences. 45 (2022) - p. , 2022

Link: https://doi.org/10.1017/..

2

Enough blanket metaphysics, time for data-driven heuristics:

Rorot, Wiktor ; Korbak, Tomasz ; Litwin, Piotr.
Behavioral and Brain Sciences. 45 (2022) - p. , 2022

Link: https://doi.org/10.1017/..

3

Self-organisation, (M, R)–systems and enactive cognitive sc..:

Korbak, Tomasz
Adaptive Behavior. 31 (2022) 1 - p. 35-49 , 2022

Link: https://doi.org/10.1177/..

4

Interaction history as a source of compositionality in emer..:

Korbak, Tomasz ; Zubek, Julian ; Kuciński, Łukasz..
Interaction Studies; Interaction Studies. Social Behaviour and Communication in Biological and Artificial Systems; Interaction Studies / Social Behaviour and Communication in Biological and Artificial Systems. 22 (2021) 2 - p. 212-243 , 2021

Link: https://doi.org/10.1075/..

5

Fine-Tuning Tree-LSTM for Phrase-Level Sentiment Classifica..:

, In: Human Language Technology. Challenges for Computer Science and Linguistics; Lecture Notes in Computer Science,

Korbak, Tomasz ; Żak, Paulina - p. 31-42 , 2020

Link: https://doi.org/10.1007/..

6

Computational enactivism under the free energy principle:

Korbak, Tomasz
Synthese. 198 (2019) 3 - p. 2743-2763 , 2019

Link: https://doi.org/10.1007/..

7

Scaffolded Minds And The Evolution Of Content In Signaling ..:

Korbak, Tomasz
Studies in Logic, Grammar and Rhetoric. 41 (2015) 1 - p. 89-103 , 2015

Link: https://doi.org/10.1515/..

8

The Reversal Curse: LLMs trained on "A is B" fail to learn ..:

Berglund, Lukas ; Tong, Meg ; Kaufmann, Max...
http://arxiv.org/abs/2309.12288. , 2023

Link: http://arxiv.org/abs/230..

9

Open Problems and Fundamental Limitations of Reinforcement ..:

Casper, Stephen ; Davies, Xander ; Shi, Claudia...
http://arxiv.org/abs/2307.15217. , 2023

Link: http://arxiv.org/abs/230..

10

Taken out of context: On measuring situational awareness in..:

Berglund, Lukas ; Stickland, Asa Cooper ; Balesni, Mikita...
http://arxiv.org/abs/2309.00667. , 2023

Link: http://arxiv.org/abs/230..

11

Aligning Language Models with Preferences through f-diverge..:

Go, Dongyoung ; Korbak, Tomasz ; Kruszewski, Germán...
http://arxiv.org/abs/2302.08215. , 2023

Link: http://arxiv.org/abs/230..

12

Open Problems and Fundamental Limitations of Reinforcement ..:

Casper, Stephen ; Davies, Xander ; Shi, Claudia...
http://hdl.handle.net/20.500.11850/651806. , 2023

Link: https://hdl.handle.net/2..

13

Inverse Scaling: When Bigger Isn't Better:

McKenzie, Ian R ; Lyzhov, Alexander ; Pieler, Michael...
http://arxiv.org/abs/2306.09479. , 2023

Link: http://arxiv.org/abs/230..

14

Compositional preference models for aligning LMs:

Go, Dongyoung ; Korbak, Tomasz ; Kruszewski, Germán..
http://arxiv.org/abs/2310.13011. , 2023

Link: http://arxiv.org/abs/231..

15

Improving Code Generation by Training with Natural Language..:

Chen, Angelica ; Scheurer, Jérémy ; Korbak, Tomasz...
http://arxiv.org/abs/2303.16749. , 2023

Link: http://arxiv.org/abs/230..