OpenCodePapers

question-answering-on-sqa3d

Question Answering
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAnswerExactMatch (Question Answering)ModelNameReleaseDate
Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models✓ Link63.9GeoVR-4B (ours)2026-06-04
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering✓ Link63.8Imagine3D-LLM2026-09-29
Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models✓ Link62.8Loc3R-VLM2026-03-18
Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding✓ Link59.6Qwen-3D-7B2026-08-04
CoPE-VideoLM: Codec Primitives For Efficient Video Language Models56.6CoPE 7B2026-02-13
CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs✓ Link55.1CoVeR (Video-3D LLM,16views,10%tokens)2026-09-08
CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion✓ Link54.6CREMA2024-02-08
Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA✓ Link52.91BridgeQA2024-02-24
Situational Awareness Matters in 3D Vision Language Reasoning✓ Link52.6Situation3D2024-06-11
Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding✓ Link50.7Lexicon3D2024-09-05
3D-LLM: Injecting the 3D World into Large Language Models✓ Link48.13D-LLM (BLIP2-flant5)2023-07-24
Frozen Transformers in Language Models Are Effective Visual Encoder Layers✓ Link48.09LM4VisualEncoding2023-10-19
SQA3D: Situated Question Answering in 3D Scenes✓ Link47.20ScanQA (w/ auxiliary loss)2022-10-14
SQA3D: Situated Question Answering in 3D Scenes✓ Link46.58ScanQA2022-10-14
Deep Modular Co-Attention Networks for Visual Question Answering✓ Link43.42MCAN2019-06-25
Check out how to contribute new results. Then edit this file on GitLab or GitHub.