Skip to content
Reasoning/Symbolic: A Survey
Table
Name
Journals/Conferences
Year
Categories
Issues
Motivations
Contributions
Potential ideas
URL
Name
Journals/Conferences
Year
Categories
Issues
Motivations
Contributions
Potential ideas
URL
1
Nature
2023
Network Architecture
2
A simple neural network module for relational reasoning
NIPS
2017
Network Architecture
- Symbol grounding problem. - Not robust to small task. - Input variations. - data-poor problems → sparse but complex relations.
- Relation networks (RNs): single function to compute/score all relations. - RN-augmented architecture.
3
Deep Logic: Joint Learning of Neural Perception and Logical Reasoning
TPAMI
2023
Network Architecture
- Hard to reach global optima. - Not designed to deal with semantic data (images & text).
- Joint learning framework.
- Build Logical Network consists of: + Multi-nomial(x ; h_k). + h_k: output of BiLSTM (model dependencies between different layers). + The representations operates the finite recursion to feed through the logical gate multiple times. - Training (Optimization Stage): + Optimize encoder, fix logical network: + Optimize logical network, fix encoder:
- Disentangle to reasoning. - Disentangled representations as symbolics. - The network is not adaptive, the logical nodes are fixed. There should be an approach to reuse the logical nodes (via LSTM/RNN) or Regularization like Pruning/Quantization etc.
4
Bayesian Inverse Contextual Reasoning for Heterogeneous Semantics-Native Communication
TCOM
2023
Apps: SemCom
5
Trading off Utility, Informativeness, and Complexity in Emergent Communication.
NIPS
2022
Loss Design
6
Alexa Arena: A User-Centric Interactive Plaform for Embodied AI
NIPS
2023
7
Human-like systematic generalization through a meta-learning neural network
Nature
2023
8
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
NIPS
2023
9
Iterated Learning Improves Compositionality in Large Vision-Language Models
CVPR
2024
.
10
Nethack is Hard to Hack
NIPS
2023
11
Grounding Neural Inference with Satisfiability Modulo Theories
NIPS
2023
12
Active Reasoning in an Open-World Environment
NIPS
2023
13
Egocentric Planning for Scalable Embodied Task Achievement
NIPS
2023
14
Efficient Symbolic Policy Learning with Differentiable Symbolic Expression
NIPS
2023
15
What’s Left? Concept Grounding with Logic-Enhanced Foundation Models
NIPS
2023
16
A social path to human-like artificial intelligence
Nature
2024
17
A Dual Representation Framework for Robot Learning with Human Guidance
CoRL
2023
18
Neurosymbolic AI for Reasoning Over
Knowledge Graphs: A Survey
TNNLS
2024
19
Scene-Driven Multi-modal Knowledge Graph
Construction for Embodied AI
TKDE
2024
20
Semantic HELM: A Human-Readable Memory
for Reinforcement Learning
NIPS
2024
21
Describe, Explain, Plan and Select:
Interactive Planning with Large Language Models
Enables Open-World Multi-Task Agents
NIPS
2023
22
Leveraging Symbolic Knowledge Bases
for Commonsense Natural Language
Inference Using Pattern Theory
TPAMI
2023
23
State2Explanation: Concept-Based Explanations to
Benefit Agent Learning and User Understanding
NIPS
2023
24
Read and Reap the Rewards:
Learning to Play Atari with the Help of Instruction
Manuals
NIPS
2023
25
3D Concept Learning and Reasoning from Multi-View Images
CVPR
2023
26
Large Language Models Are Neurosymbolic Reasoners
AAAI
2024
27
Interactive Visual Reasoning under Uncertainty
NIPS
2023
28
Interactive Visual Reasoning under Uncertainty
NIPS
2023
29
EgoTV : Egocentric Task Verification from Natural Language Task Descriptions
ICCV
2023
30
Interpretable Imitation Learning with Symbolic Rewards
ACM TIST
2023
31
EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning
CVPR
2023
32
Interpretable and Explainable Logical Policies
via Neurally Guided Symbolic Abstraction
NIPS
2023
There are no rows in this table
Want to print your doc?
This is not the way.
This is not the way.
Try clicking the ⋯ next to your doc name or using a keyboard shortcut (
CtrlP
) instead.