Franz Nowak
@franznowak.bsky.social
PhD student in Computer Science and Natural Language Processing at ETH Zürich
franznowak.github.io
franznowak.github.io
Pinned
Franz Nowak
@franznowak.bsky.social
· Nov 18
Transformer LLMs are Turing Complete after all !?
YouTube video by AI Coffee Break with Letitia
youtu.be
Transformer language models like Chat GPT, when using chain-of-thought reasoning, are Turing complete. Specifically, they can execute probabilistic algorithms and generate any computable weighted language
youtu.be/MMIJKKNxvec?...
youtu.be/MMIJKKNxvec?...
Reposted by Franz Nowak
Clemente Pasti, Talu Karag\"oz, Anej Svete, Franz Nowak, Reda Boumasmoud, Ryan Cotterell
An $\mathbf{L^*}$ Algorithm for Deterministic Weighted Regular Languages
https://arxiv.org/abs/2411.06228
An $\mathbf{L^*}$ Algorithm for Deterministic Weighted Regular Languages
https://arxiv.org/abs/2411.06228
November 12, 2024 at 8:01 AM
Clemente Pasti, Talu Karag\"oz, Anej Svete, Franz Nowak, Reda Boumasmoud, Ryan Cotterell
An $\mathbf{L^*}$ Algorithm for Deterministic Weighted Regular Languages
https://arxiv.org/abs/2411.06228
An $\mathbf{L^*}$ Algorithm for Deterministic Weighted Regular Languages
https://arxiv.org/abs/2411.06228
Reposted by Franz Nowak
Eleftheria Tsipidi, Franz Nowak, Ryan Cotterell, Ethan Wilcox, Mario Giulianelli, Alex Warstadt
Surprise! Uniform Information Density Isn't the Whole Story: Predicting Surprisal Contours in Long-form Discourse
https://arxiv.org/abs/2410.16062
Surprise! Uniform Information Density Isn't the Whole Story: Predicting Surprisal Contours in Long-form Discourse
https://arxiv.org/abs/2410.16062
October 22, 2024 at 4:00 PM
Eleftheria Tsipidi, Franz Nowak, Ryan Cotterell, Ethan Wilcox, Mario Giulianelli, Alex Warstadt
Surprise! Uniform Information Density Isn't the Whole Story: Predicting Surprisal Contours in Long-form Discourse
https://arxiv.org/abs/2410.16062
Surprise! Uniform Information Density Isn't the Whole Story: Predicting Surprisal Contours in Long-form Discourse
https://arxiv.org/abs/2410.16062
Reposted by Franz Nowak
Anej Svete, Franz Nowak, Anisha Mohamed Sahabdeen, Ryan Cotterell
Lower Bounds on the Expressivity of Recurrent Neural Language Models
https://arxiv.org/abs/2405.19222
Lower Bounds on the Expressivity of Recurrent Neural Language Models
https://arxiv.org/abs/2405.19222
June 19, 2024 at 9:00 PM
Anej Svete, Franz Nowak, Anisha Mohamed Sahabdeen, Ryan Cotterell
Lower Bounds on the Expressivity of Recurrent Neural Language Models
https://arxiv.org/abs/2405.19222
Lower Bounds on the Expressivity of Recurrent Neural Language Models
https://arxiv.org/abs/2405.19222
Reposted by Franz Nowak
Franz Nowak, Anej Svete, Alexandra Butoi, Ryan Cotterell
On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning
https://arxiv.org/abs/2406.14197
On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning
https://arxiv.org/abs/2406.14197
June 21, 2024 at 4:31 PM
Franz Nowak, Anej Svete, Alexandra Butoi, Ryan Cotterell
On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning
https://arxiv.org/abs/2406.14197
On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning
https://arxiv.org/abs/2406.14197
Transformer language models like Chat GPT, when using chain-of-thought reasoning, are Turing complete. Specifically, they can execute probabilistic algorithms and generate any computable weighted language
youtu.be/MMIJKKNxvec?...
youtu.be/MMIJKKNxvec?...
Transformer LLMs are Turing Complete after all !?
YouTube video by AI Coffee Break with Letitia
youtu.be
November 18, 2024 at 2:32 PM
Transformer language models like Chat GPT, when using chain-of-thought reasoning, are Turing complete. Specifically, they can execute probabilistic algorithms and generate any computable weighted language
youtu.be/MMIJKKNxvec?...
youtu.be/MMIJKKNxvec?...
Yes… turning 30 soon - am I old now??
November 15, 2024 at 9:34 AM
Yes… turning 30 soon - am I old now??