NeuroQA is a large-scale 3D brain MRI visual question answering benchmark with verified image-grounded QA pairs, multi-domain coverage, and baseline evaluations showing current models lag behind text-only performance.
hub Baseline reference
Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi
Baseline reference. 62% of citing Pith papers use this work as a benchmark or comparison.
14
Pith papers citing it
Baseline
62% of classified citations
hub tools
citation-role summary
dataset 5
background 3
citation-polarity summary
years
2026 14representative citing papers
TraceAV-Bench is the first benchmark for multi-hop trajectory reasoning over long audio-visual videos, showing top models reach only 51-68% accuracy with substantial room for improvement.
DriveSpatial benchmark shows the best of 15 VLMs trails humans by 28.4 points on spatiotemporal driving tasks, with cognitive scene construction as the main failure mode.
VA-OPD improves VLM performance over standard on-policy distillation by reweighting rollouts and separating KL terms according to token-level visual advantage on math and visual benchmarks.
SADU benchmark shows top VLMs reach only 70% accuracy on software architecture diagram tasks, revealing gaps in visual reasoning for engineering artifacts.
LatentUMM proposes dual latent alignment at modality and capacity levels plus latent dynamics stabilization to reduce semantic drift and improve consistency in unified multimodal models.
Continued pre-training with balanced long-document VQA data extends a 7B LVLM to 128K context, improving long-document VQA by 7.1% and generalizing to 512K without further training.
SpatialForge synthesizes 10 million spatial QA pairs from in-the-wild 2D images to train VLMs for better depth ordering, layout, and viewpoint-dependent reasoning.
LLaVA-UHD v4 reduces visual-encoding FLOPs by 55.8% for high-resolution images in MLLMs via slice-based encoding plus intra-ViT early compression while matching or exceeding baseline performance on document, OCR, and VQA benchmarks.
Modality representations share dominant semantic geometry but have an anisotropic residual gap; AnisoAlign corrects source representations boundedly using target geometry for unpaired alignment.
ModelLens learns a performance-aware latent space from 1.62M leaderboard records to rank unseen models on unseen datasets without forward passes on the target.
SLQ adapts frozen MLLMs for multimodal retrieval by appending shared latent queries to text and image tokens and introduces KARR-Bench to test knowledge-aware reasoning retrieval.
ZAYA1-VL-8B is a new MoE vision-language model with vision-specific LoRA adapters and bidirectional image attention that reports competitive performance against several 3B-4B models on image, reasoning, and counting benchmarks.
citing papers explorer
-
NeuroQA: A Large-Scale Image-Grounded Benchmark for 3D Brain MRI Understanding
NeuroQA is a large-scale 3D brain MRI visual question answering benchmark with verified image-grounded QA pairs, multi-domain coverage, and baseline evaluations showing current models lag behind text-only performance.
-
TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos
TraceAV-Bench is the first benchmark for multi-hop trajectory reasoning over long audio-visual videos, showing top models reach only 51-68% accuracy with substantial room for improvement.
-
DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
DriveSpatial benchmark shows the best of 15 VLMs trails humans by 28.4 points on spatiotemporal driving tasks, with cognitive scene construction as the main failure mode.
-
Visual-Advantage On-Policy Distillation for Vision-Language Models
VA-OPD improves VLM performance over standard on-policy distillation by reweighting rollouts and separating KL terms according to token-level visual advantage on math and visual benchmarks.
-
Benchmarking and Evaluating VLMs for Software Architecture Diagram Understanding
SADU benchmark shows top VLMs reach only 70% accuracy on software architecture diagram tasks, revealing gaps in visual reasoning for engineering artifacts.
-
LatentUMM: Dual Latent Alignment for Unified Multimodal Models
LatentUMM proposes dual latent alignment at modality and capacity levels plus latent dynamics stabilization to reduce semantic drift and improve consistency in unified multimodal models.
-
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
Continued pre-training with balanced long-document VQA data extends a 7B LVLM to 128K context, improving long-document VQA by 7.1% and generalizing to 512K without further training.
-
SpatialForge: Bootstrapping 3D-Aware Spatial Reasoning from Open-World 2D Images
SpatialForge synthesizes 10 million spatial QA pairs from in-the-wild 2D images to train VLMs for better depth ordering, layout, and viewpoint-dependent reasoning.
-
LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?
LLaVA-UHD v4 reduces visual-encoding FLOPs by 55.8% for high-resolution images in MLLMs via slice-based encoding plus intra-ViT early compression while matching or exceeding baseline performance on document, OCR, and VQA benchmarks.
-
Anisotropic Modality Align
Modality representations share dominant semantic geometry but have an anisotropic residual gap; AnisoAlign corrects source representations boundedly using target geometry for unpaired alignment.
-
ModelLens: Finding the Best for Your Task from Myriads of Models
ModelLens learns a performance-aware latent space from 1.62M leaderboard records to rank unseen models on unseen datasets without forward passes on the target.
-
SLQ: Bridging Modalities via Shared Latent Queries for Retrieval with Frozen MLLMs
SLQ adapts frozen MLLMs for multimodal retrieval by appending shared latent queries to text and image tokens and introduces KARR-Bench to test knowledge-aware reasoning retrieval.
-
ZAYA1-VL-8B Technical Report
ZAYA1-VL-8B is a new MoE vision-language model with vision-specific LoRA adapters and bidirectional image attention that reports competitive performance against several 3B-4B models on image, reasoning, and counting benchmarks.
- RISE: Reliable Improvement in Self-Evolving Vision-Language Models