Tootfinder

🔊 #NowPlaying on BBCRadio2's #TrevorNelsonsRhythmNation
The Capitols:
🎵 Cool Jerk
#TheCapitols
https://open.spotify.com/track/2AfjyqMB5kGuT9SWaIpefy
https://soulflip.bandcamp.com/track/cool-jerk-soul-flip-edit

This https://arxiv.org/abs/2310.09499 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models
Various Large Language Models(LLMs) from the Generative Pretrained Transformer(GPT) family have achieved outstanding performances in a wide range of text generation tasks. However, the enormous model sizes have hindered their practical use in real-world applications due to high inference latency. Therefore, improving the efficiencies of LLMs through quantization, pruning, and other means has been a key issue in LLM studies. In this work, we propose a method based on Hessian sensitivity-aware mi…

Teaching Higher-Order Logic Using Isabelle
Simon Tobias Lund (Technical University of Denmark), J{\o}rgen Villadsen (Technical University of Denmark)
https://arxiv.org/abs/2404.05458

Teaching Higher-Order Logic Using Isabelle
We present a formalization of higher-order logic in the Isabelle proof assistant, building directly on the foundational framework Isabelle/Pure and developed to be as small and readable as possible. It should therefore serve as a good introduction for someone looking into learning about higher-order logic and proof assistants, without having to study the much more complex Isabelle/HOL with heavier automation. To showcase our development and approach we explain a sample proof, describe the axiom…

🔊 #NowPlaying on BBCRadio2's #TrevorNelsonsRhythmNation
LL Cool J:
🎵 Hush
#LLCoolJ
https://open.spotify.com/track/7wemmhBfxfCsjW9MkzftqA
https://knighttheproducer1.bandcamp.com/track/ll-cool-j-hush-knight-jersey-club-mix

(Not) Understanding Latin Poetic Style with Deep Learning
Ben Nagy
https://arxiv.org/abs/2404.06150 https://arxiv.org/pdf/2404.06150<…

(Not) Understanding Latin Poetic Style with Deep Learning
This article summarizes some mostly unsuccessful attempts to understand authorial style by examining the attention of various neural networks (LSTMs and CNNs) trained on a corpus of classical Latin verse that has been encoded to include sonic and metrical features. Carefully configured neural networks are shown to be extremely strong authorship classifiers, so it is hoped that they might therefore teach `traditional' readers something about how the authors differ in style. Sadly their reasoning…

🔊 #NowPlaying on BBCRadio2's #TrevorNelsonsRhythmNation
LL Cool J:
🎵 Hush
#LLCoolJ
https://open.spotify.com/track/7wemmhBfxfCsjW9MkzftqA
https://knighttheproducer1.bandcamp.com/track/ll-cool-j-hush-knight-jersey-club-mix

Zero-shot LLM-guided Counterfactual Generation for Text
Amrita Bhattacharjee, Raha Moraffah, Joshua Garland, Huan Liu
https://arxiv.org/abs/2405.04793 http…

Zero-shot LLM-guided Counterfactual Generation for Text
Counterfactual examples are frequently used for model development and evaluation in many natural language processing (NLP) tasks. Although methods for automated counterfactual generation have been explored, such methods depend on models such as pre-trained language models that are then fine-tuned on auxiliary, often task-specific datasets. Collecting and annotating such datasets for counterfactual generation is labor intensive and therefore, infeasible in practice. Therefore, in this work, we f…

🔊 #NowPlaying on BBCRadio2's #TrevorNelsonsRhythmNation
CeeLo Green:
🎵 I'll Be Around
#CeeLoGreen
https://shmani.bandcamp.com/track/ill-be-around-ceelo-green-shman-remix

Zero-shot LLM-guided Counterfactual Generation for Text
Amrita Bhattacharjee, Raha Moraffah, Joshua Garland, Huan Liu
https://arxiv.org/abs/2405.04793 http…

Zero-shot LLM-guided Counterfactual Generation for Text
Counterfactual examples are frequently used for model development and evaluation in many natural language processing (NLP) tasks. Although methods for automated counterfactual generation have been explored, such methods depend on models such as pre-trained language models that are then fine-tuned on auxiliary, often task-specific datasets. Collecting and annotating such datasets for counterfactual generation is labor intensive and therefore, infeasible in practice. Therefore, in this work, we f…

🔊 #NowPlaying on BBCRadio2's #TrevorNelsonsRhythmNation
CeeLo Green:
🎵 I'll Be Around
#CeeLoGreen
https://shmani.bandcamp.com/track/ill-be-around-ceelo-green-shman-remix