Github repository for "Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas" (ICML 2025)
☆70May 2, 2025Updated 10 months ago
Alternatives and similar repositories for AdaptVis
Users that are interested in AdaptVis are comparing it to the libraries listed below
Sorting:
- Code and datasets for "What’s “up” with vision-language models? Investigating their struggle with spatial reasoning".☆70Feb 28, 2024Updated 2 years ago
- ☆79Nov 5, 2024Updated last year
- Code for "CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally"☆20Feb 14, 2025Updated last year
- ☆132Mar 22, 2025Updated 11 months ago
- Code for "Are “Hierarchical” Visual Representations Hierarchical?" in NeurIPS Workshop for Symmetry and Geometry in Neural Representation…☆22Nov 8, 2023Updated 2 years ago
- Training recipe for SpatialReasoner☆38Sep 21, 2025Updated 5 months ago
- DisTime: Distribution-based Time Representation for Video Large Language Models.☆18Jul 10, 2025Updated 7 months ago
- ☆18Aug 7, 2025Updated 6 months ago
- [ICCV 2023] Going Beyond Nouns With Vision & Language Models Using Synthetic Data☆14Sep 30, 2023Updated 2 years ago
- This is a repository contains the implementation of our NeurIPS'24 paper "Temporal Sentence Grounding with Relevance Feedback in Videos"☆13Aug 22, 2025Updated 6 months ago
- [ICLR2023] Video Scene Graph Generation from Single-Frame Weak Supervision☆12Sep 17, 2023Updated 2 years ago
- SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability☆16May 8, 2025Updated 9 months ago
- Repo for paper "MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding".☆39Jun 9, 2025Updated 8 months ago
- [ICCV 2025] Factorized Learning for Temporally Grounded Video-Language Models☆24Jan 1, 2026Updated 2 months ago
- ☆54Jan 17, 2025Updated last year
- (NeurIPS 2023) Open-set visual object query search & localization in long-form videos☆26Feb 1, 2024Updated 2 years ago
- Adapting LLaMA Decoder to Vision Transformer☆30May 20, 2024Updated last year
- This is the official implementation of ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos☆43Nov 5, 2025Updated 3 months ago
- Code release for 'Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs' (NeurIPS 2025)☆30Oct 28, 2025Updated 4 months ago
- Official implementation of the paper: "ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigation"☆47Feb 11, 2026Updated 2 weeks ago
- The official code of Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval (AAAI2024)☆32Mar 29, 2024Updated last year
- [TACL'23] VSR: A probing benchmark for spatial undersranding of vision-language models.☆139Mar 25, 2023Updated 2 years ago
- ViewSpatial-Bench:Evaluating Multi-perspective Spatial Localization in Vision-Language Models☆70Jan 8, 2026Updated last month
- PyTorch implementation of StableMask (ICML'24)☆15Jun 27, 2024Updated last year
- ☆68Sep 15, 2025Updated 5 months ago
- [ICML 2023] "Data Efficient Neural Scaling Law via Model Reusing" by Peihao Wang, Rameswar Panda, Zhangyang Wang☆14Jan 4, 2024Updated 2 years ago
- [ICCV2025] All in One: Visual-Description-Guided Unified Point Cloud Segmentation☆28Jul 25, 2025Updated 7 months ago
- [NAACL'25] Contains code and documentation for our VANE-Bench paper.☆17Aug 19, 2025Updated 6 months ago
- ☆16Apr 4, 2025Updated 10 months ago
- [NeurIPS'24] This repository is the implementation of "SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models"☆313Dec 14, 2024Updated last year
- [ECCV 2024] Learning Video Context as Interleaved Multimodal Sequences☆43Mar 11, 2025Updated 11 months ago
- [AAAI 2023 Oral] VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning☆68Feb 16, 2024Updated 2 years ago
- ☆21Aug 8, 2024Updated last year
- [NeurIPS 2025] Source codes for the paper "MindJourney: Test-Time Scaling with World Models for Spatial Reasoning"☆133Nov 4, 2025Updated 3 months ago
- [ICLR2024] (EvALign-ICL Benchmark) Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context …☆22Mar 1, 2024Updated 2 years ago
- ☆44Jan 14, 2026Updated last month
- Rui Qian, Xin Yin, Dejing Dou†: Reasoning to Attend: Try to Understand How <SEG> Token Works (CVPR 2025)☆51Feb 4, 2026Updated 3 weeks ago
- Official implementation of the paper "Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synth…☆93Oct 2, 2023Updated 2 years ago
- This is the first released survey paper on hallucinations of large vision-language models (LVLMs). To keep track of this field and contin…☆92Jul 26, 2024Updated last year