Papers with Code 아카이브
Spatial Reasoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 16
- 보존된 평가 기록
- 12
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/mineanybuild/mineanybuild
공식 코드MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents
https://github.com/mlpc-ucsd/bliva
공식 코드BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions
https://github.com/mneuronico/griw-world-spatial-orientation-task
공식 코드From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task
https://github.com/mobarakol/Surgical_SceneGraph_Generation
공식 코드Learning and Reasoning with the Graph Structure Representation in Robotic Surgery
https://github.com/modelscope/data-juicer
공식 코드DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?
https://github.com/mohamedaghzal/llms-as-path-planners
공식 코드https://github.com/nkkbr/vica
공식 코드Towards Visuospatial Cognition via Hierarchical Fusion of Visual Experts
https://github.com/nzantout/sort3d
공식 코드https://github.com/oceanhao/CoNav
공식 코드CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation
https://github.com/openai/evals
공식 코드https://github.com/ouyangkun10/spacer
공식 코드https://github.com/ouyangkun10/spatial-r1
공식 코드https://github.com/palaashagrawal/stupd
공식 코드STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning
https://github.com/peijin360/vsre
공식 코드https://github.com/philippds/sphyr
공식 코드SPhyR: Spatial-Physical Reasoning Benchmark on Material Distribution
https://github.com/pickxiguapi/embodied-fsd
공식 코드From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation
https://github.com/pjlab-adg/gpt4v-ad-exploration
공식 코드On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving
https://github.com/polymathbenchmark/PolyMATH
공식 코드Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark
https://github.com/premsrit/SPARTUNQChain
공식 코드https://github.com/princeton-vl/SpatialSense
공식 코드SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition
https://github.com/protagolabs/SpatialEval
공식 코드https://github.com/pzyseere/metaspatial
공식 코드MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse
https://github.com/qwenlm/qwen-vl
공식 코드Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
https://github.com/rajeswar18/pix2shape
공식 코드Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images using a View-based Representation
https://github.com/rbler1234/ost-bench
공식 코드OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding
https://github.com/reallm-labs/infigui-r1
공식 코드InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners
https://github.com/riddickzhou/llm-graph-synthetic-reasoning
공식 코드Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data
https://github.com/rshnk73/pistaq-sreqa
공식 코드Disentangling Extraction and Reasoning in Multi-hop Spatial Reasoning
https://github.com/salesforce/BiST
공식 코드BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues
https://github.com/salesforceairesearch/taco
공식 코드TACO: Learning Multi-modal Action Models with Synthetic Chains-of-Thought-and-Action
https://github.com/sayazhang/spatial-query-by-sketch
공식 코드DeepSSN: a deep convolutional neural network to assess spatial scene similarity
https://github.com/sdesabbata/geospatial-mechanistic-interpretability
공식 코드Geospatial Mechanistic Interpretability of Large Language Models
https://github.com/sharlinu/marc
공식 코드Investigating Relational State Abstraction in Collaborative MARL
https://github.com/shiqichen17/adaptvis
공식 코드Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
https://github.com/shrivatsagrawal/are-llms-the-master-of-all-trades-exploring-domain-agnostic-reasoning-skills-of-llms
공식 코드Are LLMs the Master of All Trades? : Exploring Domain-Agnostic Reasoning Skills of LLMs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.