DataComp-VLM benchmark shows instruction-heavy data mixing outperforms filtering for VLM training, with DCVLM-Baseline achieving 63.6% on 33 tasks for 8B models (+5.4pp over FineVision).
Mixed citations
MapQA: A dataset for question answering on choropleth maps
Mixed citation behavior. Most common role is background (60%).
10
Pith papers citing it
Background
60% of classified citations
citation-role summary
background 3
dataset 2
citation-polarity summary
representative citing papers
PlanBench-V is a new benchmark and dataset for evaluating VLMs on spatial planning map interpretation via a four-stage framework of Perception, Reasoning, Association, and Implementation.
VLMs and CNNs complement each other on spectrum tasks, with CNNs strong on spatial localization and VLMs on semantic reasoning; a router combining them improves composite performance by 39% over CNN alone.
PolyMATH is a new 5,000-image benchmark where top MLLMs reach at most 41 percent accuracy on multi-modal mathematical reasoning, with ablation showing minimal gain from text over images.
IPO-Mine releases a toolkit and large multimodal dataset for structured analysis of IPO filings and shows state-of-the-art models diverge from human judgments on chart quality and misleadingness.
InternVL3-78B sets a new open-source SOTA of 72.2 on MMMU via native joint multimodal pre-training, V2PE, MPO, and test-time scaling while remaining competitive with proprietary models.
Iterative SFT-RL cycles enable a 7B LVLM to develop sophisticated visual chain-of-thought reasoning and improve performance on math and general reasoning benchmarks.
A two-stage RL framework first boosts text reasoning in 3B LMMs then adapts it to multimodal inputs, producing modest benchmark gains of 4.5-4.8%.
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
Mixed Preference Optimization with the MMPR dataset boosts multimodal CoT reasoning, lifting InternVL2-8B to 67.0 accuracy on MathVista (+8.7 points) and matching the 76B model.
citing papers explorer
-
PlanBench-V: A Spatial Planning Map Benchmark for Vision-Language Models
PlanBench-V is a new benchmark and dataset for evaluating VLMs on spatial planning map interpretation via a four-stage framework of Perception, Reasoning, Association, and Implementation.
-
When Does Multimodal AI Help? Diagnostic Complementarity of Vision-Language Models and CNNs for Spectrum Management in Satellite-Terrestrial Networks
VLMs and CNNs complement each other on spectrum tasks, with CNNs strong on spatial localization and VLMs on semantic reasoning; a router combining them improves composite performance by 39% over CNN alone.
-
Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark
PolyMATH is a new 5,000-image benchmark where top MLLMs reach at most 41 percent accuracy on multi-modal mathematical reasoning, with ablation showing minimal gain from text over images.
-
IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents
IPO-Mine releases a toolkit and large multimodal dataset for structured analysis of IPO filings and shows state-of-the-art models diverge from human judgments on chart quality and misleadingness.
-
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
A two-stage RL framework first boosts text reasoning in 3B LMMs then adapts it to multimodal inputs, producing modest benchmark gains of 4.5-4.8%.
-
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.