#paperthread — Public Fediverse posts

#paperThread #auditory #neuroscience
Our latest paper just came out in the Journal of Neuroscience “Neural Dynamics of the Processing of Speech Features: Evidence for a Progression of Features from Acoustic to Sentential Processing.” We follow the cortical processing of four different speech-like stimuli (https://dushk88.github.io/progression-of-neural-features) through the brain, using MEG, from early auditory cortex to areas processing semantic-level information. The results show that each language-sensitive processing stage shows both an early (bottom-up-like) cortical contribution and a late (top-down-like) cortical contribution consistent with predictive coding. https://www.jneurosci.org/content/45/11/e1143242025
https://fediscience.org/@jzsimon/111865220831291708

#paperThread #auditory #neuroscience
Our latest paper just came out in the Journal of Neuroscience “Neural Dynamics of the Processing of Speech Features: Evidence for a Progression of Features from Acoustic to Sentential Processing.” We follow the cortical processing of four different speech-like stimuli (https://dushk88.github.io/progression-of-neural-features) through the brain, using MEG, from early auditory cortex to areas processing semantic-level information. The results show that each language-sensitive processing stage shows both an early (bottom-up-like) cortical contribution and a late (top-down-like) cortical contribution consistent with predictive coding. https://www.jneurosci.org/content/45/11/e1143242025
https://fediscience.org/@jzsimon/111865220831291708

#neuroscience #paperThread A new #preprint by Dushyanthi Karunathilake https://doi.org/10.1101/2024.02.02.578603
Language has a hierarchical structure, and some neural processing stages seem to align with these levels. Here we record MEG responses from subjects listening to a progression of speech/speech-like passages: speech-modulated noise; non-words with well-formed phonemes; shuffled words; and true narrative. We can then trace the hierarchy of neural processing stages, from acoustical to full language. 1/7

#neuroscience #paperThread A new #preprint by Dushyanthi Karunathilake https://doi.org/10.1101/2024.02.02.578603
Language has a hierarchical structure, and some neural processing stages seem to align with these levels. Here we record MEG responses from subjects listening to a progression of speech/speech-like passages: speech-modulated noise; non-words with well-formed phonemes; shuffled words; and true narrative. We can then trace the hierarchy of neural processing stages, from acoustical to full language. 1/7

#neuroscience #paperThread New paper in PNAS by recent PhD Dushyanthi Karunathilake! https://doi.org/10.1073/pnas.2309166120
MEG responses from continuous speech listening lock to various stimulus features: acoustic, phonemic, lexical, & semantic. Could they provide an objective measure of when degraded speech is perceived as actually intelligible? This would give insight as to how the brain turns speech into language, and be a treasure mine for clinical populations ill-suited for behavioral testing. 1/5

#neuroscience #paperThread New paper in PNAS by recent PhD Dushyanthi Karunathilake! https://doi.org/10.1073/pnas.2309166120
MEG responses from continuous speech listening lock to various stimulus features: acoustic, phonemic, lexical, & semantic. Could they provide an objective measure of when degraded speech is perceived as actually intelligible? This would give insight as to how the brain turns speech into language, and be a treasure mine for clinical populations ill-suited for behavioral testing. 1/5

Interesting developments in subquadratic alternatives to self-attention based transformers for large sequence modeling (32k and more).

Hyena Hierarchy: Towards Larger Convolutional Language Models

https://arxiv.org/abs/2302.10866

They propose to replace the quadratic self-attention layers by an operator built with implicitly parametrized long kernel 1D convolutions.

#DeepLearning #LLMs #PaperThread

1/4

Interesting developments in subquadratic alternatives to self-attention based transformers for large sequence modeling (32k and more).

Hyena Hierarchy: Towards Larger Convolutional Language Models

https://arxiv.org/abs/2302.10866

They propose to replace the quadratic self-attention layers by an operator built with implicitly parametrized long kernel 1D convolutions.

#DeepLearning #LLMs #PaperThread

1/4

It's not the first time! A dream team of Eve Fleisig (human eval), Adam Lopez (remembers the Stat MT era), Kyunghyun Cho (helped end it), and me (pun in title) are here to teach you the history of scale crises and what lessons we can take from them. https://arxiv.org/abs/2311.05020 🧵 #paperthread #LLMs

It's not the first time! A dream team of Eve Fleisig (human eval), Adam Lopez (remembers the Stat MT era), Kyunghyun Cho (helped end it), and me (pun in title) are here to teach you the history of scale crises and what lessons we can take from them. https://arxiv.org/abs/2311.05020 🧵 #paperthread #LLMs

📝 Now reading: "From empirical problem-solving to theoretical problem-finding perspectives on the cognitive sciences -- by @fedeadolfi #LauraVandeBraak, and @mariekewoe (2023, PsyArXiv) #PaperThread 🧵

https://doi.org/10.31234/osf.io/jthxf

📝 Now reading: "From empirical problem-solving to theoretical problem-finding perspectives on the cognitive sciences -- by @fedeadolfi #LauraVandeBraak, and @mariekewoe (2023, PsyArXiv) #PaperThread 🧵

https://doi.org/10.31234/osf.io/jthxf

@jkanev I follow #NewPaper OR #preprint OR #PaperThread and it's *very* quiet.

@jkanev I follow #NewPaper OR #preprint OR #PaperThread and it's *very* quiet.

DINOv2: Learning Robust Visual Features without Supervision

Tricks applied to DINO and iBOT to learn robust/generic features for many downstream tasks

My summary on HFPapers: https://huggingface.co/papers/2304.07193#64f81a7f35a0a9fc54363373
arXiv: https://arxiv.org/abs/2304.07193
Demo: https://dinov2.metademolab.com/

#arXiv #PaperThread #FoundationModels

LidarCLIP or: How I Learned to Talk to Point Clouds

Align LiDAR encoder to CLIP image encoder and you can query LiDAR through image similarity or even text.

My summary on HFPapers: https://huggingface.co/papers/2212.06858#64f6f05910a91217c38874b7
arXiv: https://arxiv.org/abs/2212.06858
PWC: https://paperswithcode.com/paper/lidarclip-or-how-i-learned-to-talk-to-point

#arXiv #PaperThread #FoundationModels

SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding

Top-view and ground-view images can make neural maps that aid visual positioning.

My summary on HFPapers: https://huggingface.co/papers/2306.05407#64c3fcb171947b03ffcf314c
arXiv: https://arxiv.org/abs/2306.05407
PapersWithCode: https://paperswithcode.com/paper/snap-self-supervised-neural-maps-for-visual

#arXiv #PaperThread #NewPaper #SSL

Diffusion Models Beat GANs on Image Classification

Extract features (activations) at a block at a diffusion time step gives a decent classifier.

My summary on HFPapers: https://huggingface.co/papers/2307.08702#64c3fb7ebf1103bae84618a6

arXiv: https://arxiv.org/abs/2307.08702

Links: [PapersWithCode](https://paperswithcode.com/paper/diffusion-models-beat-gans-on-image)

#arxiv #NewPaper #PaperThread #sd

How is ChatGPT's behavior changing over time?

Monitors trends in performance of GPT-4 and GPT-3.5 (backend LLMs of ChatGPT) from March 2023 to June 2023 on diverse tasks.

My summary on HFPapers: https://huggingface.co/papers/2307.09009#64c3f9c2979493279b41df28
arXiv: https://arxiv.org/abs/2307.09009
GitHub: https://github.com/lchen001/LLMDrift

#arxiv #NewPaper #PaperThread #llm

LightGlue: Local Feature Matching at Light Speed

Improving SuperGlue with changes to transformer (GNN matching). Iterative design gives speed boost.

My summary on HFPapers: https://huggingface.co/papers/2306.13643#64ba93f75e13c0d8659b4ce8

Links: [PapersWithCode](https://paperswithcode.com/paper/lightglue-local-feature-matching-at-light), [GitHub](https://github.com/cvg/lightglue), [arxiv](https://arxiv.org/abs/2306.13643)

#lfm #arxiv #PaperThread #NewPaper #gnn

Llama 2: Open Foundation and Fine-Tuned Chat Models

Improving LLaMA with hacks.
Gotta admit (being a critic of Meta) they have tested it well.

HFPapers: https://huggingface.co/papers/2307.09288
My summary: https://huggingface.co/papers/2307.09288#64b79ed1104e7af01c0c6425

Links: [website](https://ai.meta.com/llama/), [Meta AI blog post](https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/), [arxiv](https://arxiv.org/abs/2307.09288), [Meta news](https://about.fb.com/news/2023/07/llama-2/), [GitHub](https://github.com/facebookresearch/llama) ([Older LLaMA - v1](https://github.com/facebookresearch/llama/tree/llama_v1))

#NewPaper #PaperThread #arxiv #llm

Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence

Fusing diffusion features into per-pixel image features (specific for downstream tasks)

@ducha_aiki's tweet: https://twitter.com/ducha_aiki/status/1661310529846013955
arXiv: https://arxiv.org/abs/2305.14334
website: https://diffusion-hyperfeatures.github.io/
GitHub: https://github.com/diffusion-hyperfeatures/diffusion_hyperfeatures

My summary on HFPapers: https://huggingface.co/papers/2305.14334#64b79bcafe6a108d0308f9b5

#NewPaper #PaperThread #diffusion

SketchMetaFace: A Learning-based Sketching Interface for High-fidelity 3D Character Face Modeling

An exciting mix of Pix2Pix, PIFu (SDF generation), and mesh refinement hacks to create a facial mesh from interactive sketching.

@_akhaliq tweet: https://twitter.com/_akhaliq/status/1676090852697841664

My summary post on HFPapers: https://huggingface.co/papers/2307.00804#64b79817b5d293ec95a50f13

arXiv: https://arxiv.org/abs/2307.00804

GitHub: https://github.com/zhongjinluo/SketchMetaFace

#NewPaper #PaperThread #arxiv

AI systems fail to generalize to novel environments, that differ from their training environment. Crucially, they are vulnerable to spurious correlations.

To facilitate progress, we introduce Spawrious 🐾, a benchmark suite for robustness/OOD/domain generalization algorithms.

- Paper link https://arxiv.org/abs/2303.05470

#PaperThread [1/7]

#ai #NewPaper #arxiv #CV #genAI #machinelearning #artificialintelligence

Now reading: Epistemic Exploitation -- by Nora Berenstain (Ergo, 2016) https://quod.lib.umich.edu/e/ergo/12405314.0003.022/--epistemic-exploitation?rgn=main;view=fulltext #PaperThread 🧵 1/n

Now reading: Epistemic Exploitation -- by Nora Berenstain (Ergo, 2016) https://quod.lib.umich.edu/e/ergo/12405314.0003.022/--epistemic-exploitation?rgn=main;view=fulltext #PaperThread 🧵 1/n

📖 Now reading: The New Eugenics of Transhumanism: A Feminist Assessment -- by Nikila Lakshmanan (Gender Forum . 2018, Issue 68, p41-56. 16p.) http://genderforum.org/wp-content/uploads/2018/05/5_Lakshmanan_Transhumanism.pdf… 🧵 #PaperThread

📖 Now reading: The New Eugenics of Transhumanism: A Feminist Assessment -- by Nikila Lakshmanan (Gender Forum . 2018, Issue 68, p41-56. 16p.) http://genderforum.org/wp-content/uploads/2018/05/5_Lakshmanan_Transhumanism.pdf… 🧵 #PaperThread

Very happy that "Altered Directional Functional Connectivity Underlies Post-stroke Cognitive Recovery" is out in Brain Comms. https://doi.org/10.1093/braincomms/fcad149 This multi-lab collaboration was led by Behrad Soleimani and directed by Behtash Babadi & Elisabeth Marsh, with critical contributions from Proloy Das, Joshua Kulasingham, Marsh lab members, and me. The 1st application of NLGC: a wild, crazy, and principled method of #MEG functional connectivity. https://doi.org/10.1016/j.neuroimage.2022.119496
#paperThread #researchPaper

New #preprint 🧠📉

Typical human cerebral cortex development unfolds along patterns of molecular and cellular brain organization. We identify specific biological processes that can explain developmental trajectories down to the individual level!

https://doi.org/10.1101/2023.05.05.539537

🧵 1/n

#Neuroscience #Neurodevelopment #Neuro #Brain #Science #Research #Paper #PaperThread #NewPaper @neuroscience @cognition @neuro

New #preprint 🧠📉

Typical human cerebral cortex development unfolds along patterns of molecular and cellular brain organization. We identify specific biological processes that can explain developmental trajectories down to the individual level!

https://doi.org/10.1101/2023.05.05.539537

🧵 1/n

#Neuroscience #Neurodevelopment #Neuro #Brain #Science #Research #Paper #PaperThread #NewPaper @neuroscience @cognition @neuro

One can't judge a click model only by how well it ranks documents, we also need to make sure it actively identified and removed biases hidden in the logged data.

That's what we showed in our recent #SIGIR23 paper with Philipp Hager, Jean-Michel Renders and Maarten de Rijke.

https://arxiv.org/abs/2304.09560

#PaperThread #ULTR #ClickModels #IR

Happy to announce our #preprint “Effects of Aging on Cortical Representations of Continuous Speech” by Dushyanthi Karunathilake et al (including @StefKuchinsky) https://doi.org/10.1101/2022.08.22.504825
(A fall announcement was delayed by the rise-of-mastodon-downfall-of-twitter process)
Using magnetoencephalography (MEG), we investigated how continuous speech is represented in auditory cortex in the presence of interfering speech, in younger & older adults.
#tootPrint #paperThread #researchPaper
1/5

LLM-based assistants can speed up software development, but what should they do when they aren't sure what code to write? We're excited to share R-U-SURE, a drop-in system for adding uncertainty annotations to code suggestions!

Read our paper here: https://arxiv.org/abs/2303.00732

#PaperThread [1/11]

Formalizing verbal theories: A tutorial by dialogue (van Rooij & Blokpoel, 2020)

📖 Published paper version: https://econtent.hogrefe.com/doi/epdf/10.1027/1864-9335/a000428

📝 Preprint (open access): https://psyarxiv.com/k79nv/

Summary in #PaperThread below 🧵 1/n

#PaperThread about the new 📜 #arxiv #preprint with Marvin Hofer, Alieh Saeedi, Hanna Köpcke and Erhard Rahm about the state and challenges of #KnowledgeGraph construction: https://arxiv.org/abs/2302.11509

In the latest SIGIR Forum issue, we discussed offline evaluation for RL-based #RecommenderSystems and noted that the most common evaluation protocol, i.e., next-item prediction, is unsuited to such approaches.

(with Thibaut Thonet, Jean-Michel Renders, @mdr )
Paper ➡️ https://sigir.org/wp-content/uploads/2023/01/p03.pdf

#RecSys #ReinforcementLearning #PaperThread

@lili @debivort @tuthill Thank you so much for sharing this really cool #PaperThread with us! Super interesting 😃 I hope there will be more!

The full connectome of the fruit fly is slowly being mapped out.
But how do we make sense of it? Sometimes the anatomy is highly suggestive of a function, but more often than not there are much more connections than we expect and the interpretation is complicated.

I've been slowly collecting papers that try to link a simulation of the connectome with a fly behavior.

Here, I'd like to share one such paper, which uses modeling and connectomics to study the link between development and fly preferences for a particular odor.

The paper is:
"Neural correlates of individual odor preference in Drosophila"
Churgin & Lavrentovich et al
(senior author @debivort )
https://www.biorxiv.org/content/10.1101/2021.12.24.474127v1

I presented the paper in the @tuthill journal club this week and wanted to share it here while it's still in my head! 🧵

#modeling #connectomics #Drosophila #neuroscience #PaperThread #JournalClub

Hot off the press! 🔥​
https://doi.org/10.1016/j.neubiorev.2023.105042

We performed a meta-analysis of neuroimaging studies looking at interpersonal neural synchronization (INS) and contextualized the results using diverse public databases to develop new hypotheses on physiological processes potentially involved in INS.

What is he talking about, you ask? See below ⏬​

1/9

#NewPaper #PaperThread #NeuroPaper #NeuroPaperThread #NewNeuroPaper #NeuroScience #Neuro #Psych #Psychiatry #Psychology #Cognition #Brain #Communication #Science #Research #DataViz #DataScience
@neuroscience @neuro @cognition @fmri @phdstudents @academicchatter

New paper "Cross-validatory model selection for Bayesian autoregressions with exogenous regressors" with Alex Cooper, @dan_p_simpson, Lauren Kennedy, and Catherine Forbes

One FAQ is "Can you use LOO or cross-validation in general for time series?" The short answer is "Yes", and I've had a longer answer in CV-FAQ https://avehtari.github.io/modelselection/CV-FAQ.html#9_Can_cross-validation_be_used_for_time_series

Now we have a better answer on what kind of cross-validation is good with timeseries!

#PaperThread #Bayesian #CrossValidation