Current MLLMs show weak performance on small object understanding tasks, but fine-tuning with the new SOU-Train dataset measurably improves their capabilities.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 2
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
dataset 2polarities
use dataset 2representative citing papers
HyLaR with DePO enables effective RL in hybrid discrete-continuous spaces for multimodal models, outperforming prior MLLMs on perception and understanding benchmarks.
Attention sinks in LVLM create a global-vs-local trade-off that a layer-wise gating module can balance to improve multimodal benchmark performance.
OpenSpatial supplies a principled open-source data engine and 3-million-sample dataset that raises spatial-reasoning model performance by an average of 19 percent on benchmarks.
citing papers explorer
-
Can Multimodal Large Language Models Truly Understand Small Objects?
Current MLLMs show weak performance on small object understanding tasks, but fine-tuning with the new SOU-Train dataset measurably improves their capabilities.
-
Hybrid Latent Reasoning with Decoupled Policy Optimization
HyLaR with DePO enables effective RL in hybrid discrete-continuous spaces for multimodal models, outperforming prior MLLMs on perception and understanding benchmarks.
-
When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models
Attention sinks in LVLM create a global-vs-local trade-off that a layer-wise gating module can balance to improve multimodal benchmark performance.
-
OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence
OpenSpatial supplies a principled open-source data engine and 3-million-sample dataset that raises spatial-reasoning model performance by an average of 19 percent on benchmarks.