LXAI @ NeurIPS 2024

12 papers

Top Research Directions

The 25 research directions with LXAI @ NeurIPS 2024 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Adapting Foundation Models with Fractional Parameter Updates18.3%
2Anomaly Detection under Extreme Class Imbalance18.3%
3Automated Knowledge Synthesis from Scientific Literature18.3%
4Black-Box Adversarial Attacks18.3%
5Causal Discovery with Latent Confounders18.3%
6Causal Inference with Ancestral Graph Representations18.3%
7Contextual Detection of Real Word Errors18.3%
8Cross-Modal Structural Divergence in Sign Language Translation18.3%
9Generalizing Deep Learning Methods Beyond Image Classification18.3%
10Learning Causal Relations Under Severe Data Scarcity18.3%
11Mapping Scientific Frontiers with Bibliometric Datasets18.3%
12Masked Patch Reconstruction for Vision Transformers18.3%
13Parallelizing Recurrent Models via Linear State Transitions18.3%
14Parametric and Contextual Knowledge Conflicts in Language Models18.3%
15Perceptually Stealthy Adversarial Attacks18.3%
16Probabilistic Frameworks for Causal Uncertainty18.3%
17Shifting from Static Benchmarks to Dynamic Evaluation18.3%
18Synthesizing Intermediate Rationales for Multi Step Reasoning18.3%
19Task Specific Specialization of Small Language Models18.3%
20The Real World Limits of White Box Security Assumptions18.3%
21The Text to Text Paradigm for Task Unification18.3%
22The Theoretical Gap in Complex Iterative Algorithms18.3%
23Transferable Adversarial Attacks across Black Box Systems18.3%
24Unsupervised Model Selection for Disentangled Representations18.3%
25Why Subword Tokenization Fails on Noisy Text18.3%

Download all directions as CSV

Institutions

Institutions credited by LXAI @ NeurIPS 2024 papers: a paper credits every institution named in its affiliations, once. 21 institutions share 6 credited papers.

#InstitutionPapersShare
101ebs6k31 116.7%
202s7sax82 116.7%
3Aalto University 116.7%
4Brown University 116.7%
5Consejo Nacional de Investigaciones Científicas y Técnicas 116.7%
6Fundação Getulio Vargas 116.7%
7Imperial College London 116.7%
8Intel (United States) 116.7%
9Max Planck Institute for Software Systems 116.7%
10Mila - Quebec Artificial Intelligence Institute 116.7%
11New York University 116.7%
12Princeton University 116.7%
13Rice University 116.7%
14The University of Texas at Austin 116.7%
15Universidad de Buenos Aires 116.7%
16Universidad Nacional 116.7%
17Universidade de Pernambuco 116.7%
18Universidade Federal de Pernambuco 116.7%
19University of Manchester 116.7%
20University of Münster 116.7%
21Université de Montréal 116.7%

Download all institutions as CSV

About this data

Papers. LXAI @ NeurIPS 2024 lists 12 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 6 of 12 papers (50.0%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-18 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “LXAI @ NeurIPS 2024”, https://lacuna.tiptreesystems.com/venue/lxai-neurips/2024.

Top Authors

AuthorPapers
Cleber Zanchettin2
Randall Balestriero2
Adèle H. Ribeiro1
Ahmed Imtiaz Humayun1
Alexander Huth1
Antonio de Padua Braga1
António Góis1
César Quilodrán-Casas1
CJ Barberan1
Daniel Otero1
Diego Mesquita1
Eliezer de Souza da Silva1
Enzo Ferrante1
Facundo Manuel Quiroga1
Flávio Santos1
Javier S. Turek1
Jesus Solano1
Jianing Mu1
Jose Geraldo Fernandes1
Josue Casco-Rodriguez1

Impactful Papers

Papers from LXAI @ NeurIPS 2024 that shaped research clusters.

Influential

Papers

Title
Anomaly Detection In The Wild: Can SSL Handle Strong Distribution Imbalances?
A proposal for post-OCR spelling correction using Language Models
Enhancing the Generation of Predictions and Natural Language Explanations via Sparse Few-shot Fine-tuning and Prompting
Evaluating the Usefulness of Large Language Models for Synthetic Samples Generation via Few-shot Learning
Human-Aided Discovery of Ancestral Graphs
Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System
Optimizing the Gabriel graph construction algorithm
SignAttention: On the Interpretability of Transformer Models for Sign Language Translation
Subnormal Number Attacks on Binarized Neural Networks
Testing Memory Capabilities in Large Language Models with the Sequence Order Recall Task
Towards unearthing neglected climate innovations from scientific literature using Large Language Models
Visualizing Linear RNNs Through Unrolling