EntropyScan detects backdoored LVLMs by quantifying structural anomalies in visual attention distributions on benign samples via Tsallis entropy and reference-anchored Z-score normalization.
National Science Review11(12), nwae403 (2024)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
SpecVQA is a new benchmark dataset and evaluation suite for testing multimodal large language models on scientific spectral image understanding and visual question answering, supported by a curve-preserving sampling method that improves results.
Low-rank LLM adaptation during vision-language alignment outperforms full fine-tuning by preserving per-token visual structure and favoring flat, noise-robust subspaces.
Introduces CORTEX benchmark supplying 76,177 validated four-stage diagnostic reasoning traces for open/closed VQA and report generation on chest CT to enable traceable MLLM supervision and evaluation.
citing papers explorer
-
EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy
EntropyScan detects backdoored LVLMs by quantifying structural anomalies in visual attention distributions on benign samples via Tsallis entropy and reference-anchored Z-score normalization.
-
SpecVQA: A Benchmark for Spectral Understanding and Visual Question Answering in Scientific Images
SpecVQA is a new benchmark dataset and evaluation suite for testing multimodal large language models on scientific spectral image understanding and visual question answering, supported by a curve-preserving sampling method that improves results.
-
Dive Into the Implicit Biases of Low-rank Vision-language Alignment
Low-rank LLM adaptation during vision-language alignment outperforms full fine-tuning by preserving per-token visual structure and favoring flat, noise-robust subspaces.
-
CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs
Introduces CORTEX benchmark supplying 76,177 validated four-stage diagnostic reasoning traces for open/closed VQA and report generation on chest CT to enable traceable MLLM supervision and evaluation.