NeurIPS 2024 Workshop Sys2-Reasoning Submissions

PROOF OF THOUGHT : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoning
Debargha Ganguly, Srinivasan Iyengar, Vipin Chaudhary, Shivkumar Kalyanaraman
- Published: 10 Oct 2024, Last Modified: 23 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
Not All LLM Reasoners Are Created Equal
Arian Hosseini, Alessandro Sordoni, Daniel Kenji Toyama, Aaron Courville, Rishabh Agarwal
- Published: 10 Oct 2024, Last Modified: 10 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
ALTA: Compiler-Based Analysis of Transformers
Peter Shaw, James Cohan, Jacob Eisenstein, Kenton Lee, Jonathan Berant, Kristina Toutanova
- Published: 10 Oct 2024, Last Modified: 24 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
Improving LLM Generation with Inverse and Forward Alignment: Reward Modeling, Prompting, Fine-Tuning, and Inference-Time Optimization
Hao Sun, Thomas Pouplin, Nicolás Astorga, Tennison Liu, Mihaela van der Schaar
- Published: 10 Oct 2024, Last Modified: 28 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
System 1.5: Designing Metacognition in Artificial Intelligence
Nick Oh, Fernand Gobet
- Published: 10 Oct 2024, Last Modified: 28 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
System-2 Reasoning via Generality and Adaptation
Sejin Kim, Sundong Kim
- Published: 10 Oct 2024, Last Modified: 14 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
Can Language Models Perform Implicit Bayesian Inference Over User Preference States?
Linlu Qiu, Fei Sha, Kelsey R Allen, Yoon Kim, Tal Linzen, Sjoerd van Steenkiste
- Published: 10 Oct 2024, Last Modified: 28 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
Diffusion On Syntax Trees For Program Synthesis
Shreyas Kapur, Erik Jenner, Stuart Russell
- Published: 10 Oct 2024, Last Modified: 10 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
A Llama Sunk My Battleship! Asking Rational Questions with LLMs via Bayesian Inference
Gabriel Grand, Valerio Pepe, Jacob Andreas, Joshua B. Tenenbaum
- Published: 10 Oct 2024, Last Modified: 29 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
MovieCORE: COgnitive REasoning in Movies
Gueter Josmy Faure, Min-Hung Chen, Jia-Fong Yeh, Ying Cheng, Hung-Ting Su, Shang-Hong Lai, Winston H. Hsu
- Published: 10 Oct 2024, Last Modified: 26 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
The Turing Game
Michal Lewandowski, Simon Lucas Schmid, Patrick Mederitsch, Alexander Aufreiter, Gregor Aichinger, Felix Nessler, Severin Bergsmann, Viktor Szolga, Tobias Halmdienst, Bernhard Nessler
- Published: 10 Oct 2024, Last Modified: 28 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
Alireza Rezazadeh, Zichao Li, Wei Wei, Yujia Bao
- Published: 10 Oct 2024, Last Modified: 15 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs
Siyuan Wang, zhongyu wei, Yejin Choi, Xiang Ren
- Published: 10 Oct 2024, Last Modified: 10 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
softmax is not enough (for sharp out-of-distribution)
Petar Veličković, Christos Perivolaropoulos, Federico Barbero, Razvan Pascanu
- Published: 10 Oct 2024, Last Modified: 28 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
Implicit Reasoning in Deep Time Series Forecasting
Willa Potosnak, Cristian Ignacio Challu, Mononito Goswami, Michał Wiliński, Nina Żukowska, Artur Dubrawski
- Published: 10 Oct 2024, Last Modified: 28 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
Thought of Search: Planning with Language Models Through The Lens of Efficiency
Michael Katz, Harsha Kokel, Kavitha Srinivas, Shirin Sohrabi
- Published: 10 Oct 2024, Last Modified: 10 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus
Terufumi Morishita, Gaku Morio, Atsuki Yamaguchi, Yasuhiro Sogawa
- Published: 10 Oct 2024, Last Modified: 28 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
CausalBench: A Comprehensive Benchmark for Evaluating Causal Reasoning Capabilities of Large Language Models
ZEYU WANG
- Published: 10 Oct 2024, Last Modified: 01 Nov 2024
- Sys2-Reasoning Poster
- Readers: Everyone
Compositional Generalization Across Distributional Shifts with Sparse Tree Operations
Paul Soulos, Henry Conklin, Mattia Opper, Paul Smolensky, Jianfeng Gao, Roland Fernandez
- Published: 10 Oct 2024, Last Modified: 27 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
Recurrent Transformers Trade-off Parallelism for Length Generalization on Regular Languages
Paul Soulos, Aleksandar Terzic, Michael Hersche, Abbas Rahimi
- Published: 10 Oct 2024, Last Modified: 09 Dec 2024
- Sys2-Reasoning Poster
- Readers: Everyone
Automated Design of Agentic Systems
Shengran Hu, Cong Lu, Jeff Clune
- Published: 10 Oct 2024, Last Modified: 22 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
Your Context Is Not an Array: Unveiling Random Access Limitations in Transformers
MohammadReza Ebrahimi, Sunny Panchal, Roland Memisevic
- Published: 10 Oct 2024, Last Modified: 10 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints
Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, Nanyun Peng
- Published: 10 Oct 2024, Last Modified: 16 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
Harry Zhao, Safa Alver, Harm van Seijen, Romain Laroche, Doina Precup, Yoshua Bengio
- Published: 10 Oct 2024, Last Modified: 10 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone
LLMs on interactive feature collections with implicit look-ahead strategies
Juyeon Heo, Vihari Piratla, Kyunghyun Lee, Hyonkeun Joh, Adrian Weller
- Published: 10 Oct 2024, Last Modified: 10 Oct 2024
- Sys2-Reasoning Poster
- Readers: Everyone