Introduces the U-HOI task and shows MLLMs plus a language-to-graph pipeline can handle human-object interactions without any predefined vocabulary at training or inference time.
Visual instruction tuning towards general- purpose multimodal model: A survey.arXiv preprint arXiv:2312.16602,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
ASRU combines activation redirection and reward-optimized fine-tuning to unlearn cross-modal sensitive knowledge in MLLMs, reporting +24.6% better unlearning effectiveness and 5.8x higher generation quality on Qwen3-VL while preserving utility with limited retained data.
COMPACT synthesizes compositional visual instruction data to reduce VIT training data by 90% while achieving 100.2% of full performance across eight multimodal benchmarks.
citing papers explorer
-
Towards Unconstrained Human-Object Interaction
Introduces the U-HOI task and shows MLLMs plus a language-to-graph pipeline can handle human-object interactions without any predefined vocabulary at training or inference time.
-
ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
ASRU combines activation redirection and reward-optimized fine-tuning to unlearn cross-modal sensitive knowledge in MLLMs, reporting +24.6% better unlearning effectiveness and 5.8x higher generation quality on Qwen3-VL while preserving utility with limited retained data.
-
Visual Compositional Tuning
COMPACT synthesizes compositional visual instruction data to reduce VIT training data by 90% while achieving 100.2% of full performance across eight multimodal benchmarks.