M³Att poisons medical multimodal RAG by pairing covert textual misinformation with query-agnostic visual perturbations that increase retrieval of the bad content, causing LLMs to generate clinically plausible but incorrect responses.
hub
Nitesh Methani, Pritha Ganguly, Mitesh M Khapra, and Pratyush Kumar
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
MKG-RAG-Bench is a cross-domain benchmark for retrieval in multimodal knowledge graph-augmented generation, constructed via LLM curation from two MKGs with aligned QA datasets.
Evidence utility is defined as information gain on the model's output distribution, with ranking by gain on a latent helpfulness variable shown equivalent to answer-space utility under mild assumptions, enabling a training-free surrogate framework that outperforms baselines.
ZipRerank delivers state-of-the-art multimodal listwise reranking accuracy for long documents at up to 10x lower latency via early interaction and single-pass scoring.
A text-supervised global layout embedding augments local patch representations in late-interaction VDR, yielding +2.4 nDCG@5 and +2.3 MAP@5 gains over ColPali/ColQwen baselines on ViDoRe-v2.
FES-RAG reframes multimodal RAG as fragment-level selection using Fragment Information Gain to outperform document-level methods with up to 27% relative CIDEr gains on M2RAG while shortening context.
Prune-then-Merge combines adaptive pruning of low-signal patches with hierarchical merging to achieve higher compression rates and better performance than prior single-stage methods in visual document retrieval.
M2Note stores failed VLM trajectories as subject-guidance notes in an external notebook and retrieves them via multimodal RAG to avoid past errors during inference.
Presents Invoice Haystack benchmark for homogeneous document retrieval and VL-RAG hybrid framework achieving 60% Recall@1 and up to 13.5 point gains over prior methods.
MM-BizRAG applies layout-aware document splitting and decoupled multimodal assembly to raise generative recall on enterprise Q&A tasks by up to 32 points over vision-centric baselines while adding FastRAGEval as a cheaper LLM judge.
HyperEmo-RAG uses hierarchical hyperbolic embeddings and graph-based evidence injection to outperform prior methods in multimodal emotion recognition.
PVM adds a parallel branch to LVLMs that directly supplies visual embeddings to prevent attention decay over long generated sequences, yielding accuracy gains on reasoning tasks with minimal overhead.
MEG-RAG defines a new MEG metric based on Semantic Certainty Anchoring and trains a multimodal reranker to select evidence aligned with ground-truth semantic anchors, yielding higher accuracy and consistency on the M²RAG benchmark.
LMM-Searcher uses file-based visual UIDs and a fetch tool plus 12K synthesized trajectories to fine-tune a multimodal agent that scales to 100-turn horizons and reaches SOTA among open-source models on MM-BrowseComp and MMSearch-Plus.
MoRE enables MLLMs to dynamically coordinate heterogeneous retrieval experts via Step-GRPO training, yielding over 7% average gains on open-domain QA benchmarks.
Qwen3-VL-Embedding-8B achieves state-of-the-art performance with a 77.8 overall score on the MMEB-V2 multimodal embedding benchmark.
A systematic survey of Multimodal RAG for document understanding proposing a taxonomy based on domain, retrieval modality, and granularity while reviewing graph structures, agentic frameworks, datasets, benchmarks, applications, and open challenges.
The paper presents the Agentic Engineering Intelligence (AEI) framework for modeling automotive engineering workflows as sequential decision processes with AI agent support.
citing papers explorer
-
Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation
M³Att poisons medical multimodal RAG by pairing covert textual misinformation with query-agnostic visual perturbations that increase retrieval of the bad content, causing LLMs to generate clinically plausible but incorrect responses.
-
MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation
MKG-RAG-Bench is a cross-domain benchmark for retrieval in multimodal knowledge graph-augmented generation, constructed via LLM curation from two MKGs with aligned QA datasets.
-
Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation
Evidence utility is defined as information gain on the model's output distribution, with ranking by gain on a latent helpfulness variable shown equivalent to answer-space utility under mild assumptions, enabling a training-free surrogate framework that outperforms baselines.
-
Very Efficient Listwise Multimodal Reranking for Long Documents
ZipRerank delivers state-of-the-art multimodal listwise reranking accuracy for long documents at up to 10x lower latency via early interaction and single-pass scoring.
-
Beyond Bag-of-Patches: Learning Global Layout via Textual Supervision for Late-Interaction Visual Document Retrieval
A text-supervised global layout embedding augments local patch representations in late-interaction VDR, yielding +2.4 nDCG@5 and +2.3 MAP@5 gains over ColPali/ColQwen baselines on ViDoRe-v2.
-
Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG
FES-RAG reframes multimodal RAG as fragment-level selection using Fragment Information Gain to outperform document-level methods with up to 27% relative CIDEr gains on M2RAG while shortening context.
-
Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework
Prune-then-Merge combines adaptive pruning of low-signal patches with hierarchical merging to achieve higher compression rates and better performance than prior single-stage methods in visual document retrieval.
-
M2Note: Continual Evolution of Vision Language Models via Mistake Notebook Learning
M2Note stores failed VLM trajectories as subject-guidance notes in an external notebook and retrieves them via multimodal RAG to avoid past errors during inference.
-
Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity
Presents Invoice Haystack benchmark for homogeneous document retrieval and VL-RAG hybrid framework achieving 60% Recall@1 and up to 13.5 point gains over prior methods.
-
MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A
MM-BizRAG applies layout-aware document splitting and decoupled multimodal assembly to raise generative recall on enterprise Q&A tasks by up to 32 points over vision-centric baselines while adding FastRAGEval as a cheaper LLM judge.
-
Navigating the Emotion Tree: Hierarchical Hyperbolic RAG for Multimodal Emotion Recognition
HyperEmo-RAG uses hierarchical hyperbolic embeddings and graph-based evidence injection to outperform prior methods in multimodal emotion recognition.
-
Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
PVM adds a parallel branch to LVLMs that directly supplies visual embeddings to prevent attention decay over long generated sequences, yielding accuracy gains on reasoning tasks with minimal overhead.
-
MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG
MEG-RAG defines a new MEG metric based on Semantic Certainty Anchoring and trains a multimodal reranker to select evidence aligned with ground-truth semantic anchors, yielding higher accuracy and consistency on the M²RAG benchmark.
-
Towards Long-horizon Agentic Multimodal Search
LMM-Searcher uses file-based visual UIDs and a fetch tool plus 12K synthesized trajectories to fine-tune a multimodal agent that scales to 100-turn horizons and reaches SOTA among open-source models on MM-BrowseComp and MMSearch-Plus.
-
Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation
MoRE enables MLLMs to dynamically coordinate heterogeneous retrieval experts via Step-GRPO training, yielding over 7% average gains on open-domain QA benchmarks.
-
Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
Qwen3-VL-Embedding-8B achieves state-of-the-art performance with a 77.8 overall score on the MMEB-V2 multimodal embedding benchmark.
-
Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
A systematic survey of Multimodal RAG for document understanding proposing a taxonomy based on domain, retrieval modality, and granularity while reviewing graph structures, agentic frameworks, datasets, benchmarks, applications, and open challenges.
-
Automotive Engineering-Centric Agentic AI Workflow Framework
The paper presents the Agentic Engineering Intelligence (AEI) framework for modeling automotive engineering workflows as sequential decision processes with AI agent support.
- AffectAgent: Collaborative Multi-Agent Reasoning for Retrieval-Augmented Multimodal Emotion Recognition