WorldSense provides the first benchmark requiring synergistic audio-video-text understanding on 1,662 real-world videos and 3,172 QA pairs, where the best current multimodal LLM reaches only 65.1% accuracy.
Revisiting mllms: An in-depth analysis of image classification abilities
4 Pith papers cite this work. Polarity classification is still indexing.
fields
cs.CV 4verdicts
UNVERDICTED 4representative citing papers
SpeciaRL applies a dynamic verifier-based reward in reinforcement learning to steer reasoning LMMs toward correct and specific predictions on fine-grained open-world image classification tasks.
Fine-R1 uses chain-of-thought supervised fine-tuning on a structured FGVR reasoning dataset plus triplet augmented policy optimization to outperform general MLLMs and CLIP models on seen and unseen fine-grained categories with 4-shot training.
HyMOR combines MLLM for coarse open-ended recognition with CLIP for fine-grained domain objects, achieving near-CLIP fine performance and 2.5% better general recognition plus 23.2% overall SBert gain on a new TBO textbook dataset.
citing papers explorer
-
WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
WorldSense provides the first benchmark requiring synergistic audio-video-text understanding on 1,662 real-world videos and 3,172 QA pairs, where the best current multimodal LLM reaches only 65.1% accuracy.
-
Specificity-aware reinforcement learning for fine-grained open-world classification
SpeciaRL applies a dynamic verifier-based reward in reinforcement learning to steer reasoning LMMs toward correct and specific predictions on fine-grained open-world image classification tasks.
-
Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning
Fine-R1 uses chain-of-thought supervised fine-tuning on a structured FGVR reasoning dataset plus triplet augmented policy optimization to outperform general MLLMs and CLIP models on seen and unseen fine-grained categories with 4-shot training.
-
Bridging Coarse and Fine Recognition: A Hybrid Approach for Open-Ended Multi-Granularity Object Recognition in Interactive Educational Games
HyMOR combines MLLM for coarse open-ended recognition with CLIP for fine-grained domain objects, achieving near-CLIP fine performance and 2.5% better general recognition plus 23.2% overall SBert gain on a new TBO textbook dataset.