AI Paper Atlas

Research map / Benchmarks / VizWiz

VizWiz leaderboard

56 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on VizWiz. Best accuracy: 71.5 (LIRA-8B, ICCV 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

VizWiz · accuracy

41 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
171.5LIRA-8B
InternVL2-8B
LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance
ICCV 2025 · Table 1
Multimodal LLMs
271.4IPK (Ours)
LLaMA-7B + ViT/14
Leveraging Image as Compressed Visual Prompt and Hierarchical Visual Knowledge for Effective Image Utilization in MLLMs
AAAI 2026 · Table 1
Multimodal LLMs
370.4OURO-7B
Qwen2-VL-7B-Instruct
OURO: A Self-Bootstrapped Framework for Enhancing Multimodal Scene Understanding
ICCV 2025 · Table 1
Multimodal LLMs
461.4DeFacto
Qwen2.5-VL-7B
DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning
ICML 2026 · Table 1
Multimodal LLMs
560.61STV
Idefics2-8B
Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning
AAAI 2026 · Table 1
Language, safety and interpretability
660.4Sugar
VILA-7B
Unified Generative and Discriminative Training for Multi-modal Large Language Models
NeurIPS 2024 · Table: Multimodal Comprehensio
CLIP and zero-shot
760.35Contrastive attention (ours)
LLaVA-1.5
Where Does Vision Meet Language? Understanding and Refining Visual Fusion in MLLMs via Contrastive Attention
CVPR 2026 · Table 1
Multimodal LLMs
858.7Eagle-X5 (+Pre-Align)
Vicuna-7B
Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
ICLR 2025 · Main results table
Multimodal LLMs
958.1RoboMamba, 336
Mamba-2.7B
RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation
NeurIPS 2024 · Table 1
Robot action and navigation
1057.9LLaVA-HR
LLaVA-1.5
Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models
ICLR 2025 · Table: Comparison with existin
Multimodal LLMs
31 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

VizWiz · score

15 papers, each with its best reported number for its own method; higher is better.

#score ↑MethodPaperTopic
174.4AutoV
Qwen2.5-VL 7B
AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs
ECCV 2026 · Table 1
CLIP and zero-shot
261.2Monkey
Qwen-VL
Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models
CVPR 2024 · Table 2
Visual question answering
357.9LEO
7B LLM
Rethinking the Mixture of Vision Encoders Paradigm for Enhanced Visual Understanding in Multimodal LLMs
NeurIPS 2026 · Table 4
Multimodal LLMs
457.6CCA-LLaVA
Vicuna-7B
Mitigating Object Hallucination via Concentric Causal Attention
NeurIPS 2024 · Evaluation on Multiple-Choice
Multimodal LLMs
555.8BASIC
Vicuna-13B
BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models
ICCV 2025 · Table 1
Multimodal LLMs
654.1EMMA-V2
MambaV2-2.7B
EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment
ICLR 2025 · Table 1
Cross-modal learning
753.9HAWAII
Vicuna-1.5-7B
Hawaii: Hierarchical Visual Knowledge Transfer for Efficient Vision-Language Models
NeurIPS 2025 · Main results table
Multimodal LLMs
853.7VAR
LLaVA-1.5-7B
See What You Are Told: Visual Attention Sink in Large Multimodal Models
ICLR 2025 · General vision-language result
Multimodal LLMs
953.6LLaVA-v1.5--7B-Ours
LLaVA-v1.5-7B
Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels
CVPR 2025 · General VQA results table
Multimodal LLMs
1053.45AHA-13B
LLaVA-13B (LLaMA-2)
AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation
ICLR 2025 · Table: Quantitative Evaluation
Robot action and navigation
5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.