Perceval is a perception-centric PRM that detects token-level perceptual errors in VLMs, supporting token-advantage RL training and iterative test-time scaling for improved reasoning.
Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3representative citing papers
SceneBench shows VLMs lose accuracy on scene-level questions in long videos due to forgetting, and Scene-RAG retrieval improves performance by 2.5%.
VLMs show systematic drops in counting accuracy as visual and linguistic complexity rise, with modest gains from targeted attention reweighting in the decoder.
citing papers explorer
-
Improving Vision-language Models with Perception-centric Process Reward Models
Perceval is a perception-centric PRM that detects token-level perceptual errors in VLMs, supporting token-advantage RL training and iterative test-time scaling for improved reasoning.
-
Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark
SceneBench shows VLMs lose accuracy on scene-level questions in long videos due to forgetting, and Scene-RAG retrieval improves performance by 2.5%.
-
Can Vision-Language Models Count? A Synthetic Benchmark and Analysis of Attention-Based Interventions
VLMs show systematic drops in counting accuracy as visual and linguistic complexity rise, with modest gains from targeted attention reweighting in the decoder.