Discovering Interesting Papers
Published:
Interesting NeuroAI/LLM Cognition/miscellaneous papers
We all know that kind of feeling when you discover some very interesting paper but you never really have time to read it. Maybe you just throw it to Zotero and it stays there forever. Pobably posting the interesting/useful papers here will give me some more motivation to revisit them later? Let’s try.
1.29.2024
Neural tuning and representational geometry, Nature Reviews Neuroscience, 2021 Nikolaus Kriegeskorte & Xue-Xin Wei
1.30.2024
Spatially embedded recurrent neural networks reveal widespread links between structural and functional neuroscience findings, Nature Machine Intelligence, 2023 Jascha Achterberg et al.
2.1.2024
Transformer as a hippocampal memory consolidation model based on NMDAR-inspired nonlinearity, NeurIPS, 2023
2.5.2024
Brains and algorithms partially converge in natural language processing, Communications Biology, 2022
2.7.2024
No Coincidence, George: Capacity-Limits as the Curse of Compositionality, PsyArXiv, 2022
2.12.2024
Structural constraints on the emergence of oscillations in multi-population neural networks, eLife, 2024
Oscillatory neural networks, YouTube
2.14
Dynamics of Sparsely Connected Networks of Excitatory and Inhibitory Spiking Neurons
2.16
Using large language models to study human memory for meaningful narratives
Mechanisms of Gamma Oscillations
2.17
2.18
Circular and unified analysis in network neuroscience
2.20-2.27
I was at AAAI 2024 for nearly a week. I learned a lot and will share some papers I came across from talks/posters at the conference.
On the Paradox of Learning to Reason from Data
CRAB: Assessing the Strength of Causal Relationships Between Real-World Events
Passive learning of active causal strategies in agents and language models
SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning
Hallucination is Inevitable: An Innate Limitation of Large Language Models
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
3.1
Three aspects of representation in neuroscience
Distributed representations of words and phrases and their compositionality
3.2
A Critical Review of Causal Reasoning Benchmarks for Large Language Models
3.3
Recurrent Models of Visual Attention
Massive Activations in Large Language Models
Multiple Object Recognition with Visual Attention
Attention is not all you need anymore
Attention and Memory in Deep Learning
3.7
Large language models surpass human experts in predicting neuroscience results
3.8
3.9
Memory in humans and deep language models: Linking hypotheses for model augmentation
3.11
Are Emergent Abilities of Large Language Models a Mirage?
Mathematical introduction to deep learning
3.12
Memory and attention in deep learning
Mastering Memory Tasks with World Models
Mechanism for feature learning in neural networks and backpropagation-free machine learning models
3.13
Brain-inspired intelligent robotics: The intersection of robotics and neuroscience
Papers mentioned in this article
3.14
One model for the learning of language
3.15
The pitfalls of next-token prediction
3.16
Do Llamas Work in English? On the Latent Language of Multilingual Transformers
Using large language models to study human memory for meaningful narratives
3.18
3.23
Traveling waves shape neural population dynamics enabling predictions and internal model updating
Task interference as a neuronal basis for the cost of cognitive flexibility
A Technical Critique of Some Parts of the Free Energy Principle
3.24
Theories of Error Back-Propagation in the Brain
3.26
Traveling waves shape neural population dynamics enabling predictions and internal model updating
3.27
Reconstructing computational system dynamics from neural data with recurrent neural networks
3.29
A useful guide of how to pronounce common math symbols
3.30
A Review of Neuroscience-Inspired Machine Learning
3.31
Collective intelligence: A unifying concept for integrating biology across scales and substrates
4.3
An Introduction to Model-Based Cognitive Neuroscience
What does it mean to understand a neural network?
4.5
Nonmonotonic Plasticity: How Memory Retrieval Drives Learning
Single Cortical Neurons as Deep Artificial Neural Networks
4.17
The brain's unique take on algorithms
Cognition is an emergent property
4.18
Catalyzing next-generation Artificial Intelligence through NeuroAI
4.19
Toward a formal theory for computing machines made out of whatever physics offers
4.22
Reasoning ability is (little more than) working-memory capacity?! - ScienceDirect
How do Large Language Models Handle Multilingualism?
4.24
Empowering Working Memory for Large Language Model Agents
4.26
Context-dependent computation by recurrent dynamics in prefrontal cortex
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
4.29
5.1
A formal model of capacity limits in working memory - ScienceDirect