paper-with-me

홈 › Papers

Neuro-symbolic Training for Reasoning over Spatial Language

2024-06-19 · Tanawan Premsri, Parisa Kordjamshidi

Recent research shows that more data and larger models can provide more accurate solutions to natural language problems requiring reasoning. However, models can easily fail to provide solutions in unobserved complex input compositions due to not achieving the level of abstraction required for generalizability. To alleviate this issue, we propose training the language models with neuro-symbolic techniques that can exploit the logical rules of reasoning as constraints and provide additional supervision sources to the model. Training models to adhere to the regulations of reasoning pushes them to make more effective abstractions needed for generalizability and transfer learning. We focus on a challenging problem of spatial reasoning over text. Our results on various benchmarks using multiple language models confirm our hypothesis of effective domain transfer based on neuro-symbolic training.

📄 PDF Abstract BibTeX arXiv:2406.13828

Code (1)

premsrit/SPARTUNQChain 공식 구현 pytorch

Tasks

Spatial ReasoningTransfer Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding

2026-06-21 · Danial Kamali, Tanawan Premsri, Shreya Rajpal, Amir Zadeh 외 arxiv

Vision-Language Models (VLMs) remain unreliable when spatial reasoning requires composing relations whose meanings depend on frames of reference. Existing neuro-symbolic methods make reasoning more explicit, but often de…

Referring ExpressionSpatial Reasoning

Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs

2026-05-31 · Wentao Mo, Yang Liu arxiv

Current 3D spatial reasoning methods face a fundamental trade-off: neuro-symbolic 3D (NS3D) concept learners achieve interpretable reasoning through compositional programs but are constrained to closed-set concept vocabu…

Question AnsweringSpatial Reasoning

Open-World Visual Reasoning by a Neuro-Symbolic Program of Zero-Shot Symbols

2024-07-18 · Gertjan Burghouts, Fieke Hillerström, Erwin Walraven, Michael van Bekkum 외

We consider the problem of finding spatial configurations of multiple objects in images, e.g., a mobile inspection robot is tasked to localize abandoned tools on the floor. We define the spatial configuration of objects …

Visual Reasoning

A Multi-Modal Neuro-Symbolic Approach for Spatial Reasoning-Based Visual Grounding in Robotics

2025-10-30 · Simindokht Jahangard, Mehrzad Mohammadi, Abhinav Dhall, Hamid Rezatofighi arxiv

Visual reasoning, particularly spatial reasoning, is a challenging cognitive task that requires understanding object relationships and their interactions within complex environments, especially in robotics domain. Existi…

Spatial ReasoningVisual ReasoningVisual Grounding

The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models

2025-05-30 · Adam Stein, Aaditya Naik, Neelay Velingker, Mayur Naik 외

Neuro-symbolic learning was proposed to address challenges with training neural networks for complex reasoning tasks with the added benefits of interpretability, reliability, and efficiency. Neuro-symbolic learning metho…