VLM-DeflectionBench is a new benchmark showing that current large vision-language models rarely deflect and instead hallucinate when given conflicting or insufficient multimodal evidence.
hub
arXiv preprint arXiv:2402.04252 (2023) 32 Leong, et al
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
baseline 2
background 1
method 1
citation-polarity summary
verdicts
UNVERDICTED 10representative citing papers
HiCrew improves long-form video question answering on EgoSchema and NExT-QA via a hybrid tree for temporal topology, question-aware captioning, and adaptive multi-agent planning, with gains in temporal and causal reasoning.
The MOSS module learns and combines multi-order space-time self-similarity features to enhance temporal dynamics modeling in videos across action recognition, VQA, and robotic tasks.
CoM-PT trains vision foundation models in ascending size order using inverse knowledge transfer, allowing larger models to achieve superior performance with significantly reduced overall computational cost compared to individual training.
MG²-RAG proposes a multi-granularity graph RAG framework that constructs hierarchical multimodal nodes via entity-driven visual grounding and performs structured retrieval, delivering SOTA results on four multimodal tasks with 43.3× faster graph construction.
CoME-VL fuses contrastive and self-supervised vision encoders via entropy-guided multi-layer aggregation and RoPE cross-attention to improve vision-language model performance on benchmarks.
QKVQA proposes a question-focused filtering method with QFF and CDA modules that boosts accuracy by 3.2 points on Encyclopedic-VQA and 2.2 points on InfoSeek over prior state-of-the-art.
CogniGPT uses an interactive loop between a Multi-Granular Perception Agent and an Active Verification Agent to identify reliable clues in long videos with high accuracy and low frame usage.
Intermediate layers of a contrastively trained vision-language encoder yield stronger general embeddings than the output layer, enabling state-of-the-art performance across image/video classification, multimodal QA, and dense prediction after simple alignment.
Introduces Explicit Logic Channel (ELC) with LLM, VFM and probabilistic inference for validating, selecting and enhancing MLLMs on zero-shot tasks using Consistency Rate and cross-channel integration.
citing papers explorer
-
Exploring High-Order Self-Similarity for Video Understanding
The MOSS module learns and combines multi-order space-time self-similarity features to enhance temporal dynamics modeling in videos across action recognition, VQA, and robotic tasks.