MLLMs exhibit a Mirage effect by bypassing circuit diagrams in favor of header semantics for Verilog generation; VeriGround with identifier anonymization and D-ORPO training reaches 46% Functional Pass@1 while refusing blank images at >92%.
A survey on multimodal large language models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
The paper presents UniPPTBench and UniPPTEval, a unified benchmark and scenario-aware evaluation framework for presentation generation from vague prompts, long documents, multimodal documents, and multi-source inputs.
InfoTok uses mutual information constraints to regularize shared visual tokenization in unified MLLMs, improving both understanding and generation performance without extra training data.
A survey proposing a hierarchical taxonomy for multimodal tactile fusion datasets and methods across perception, generation, and interaction in embodied intelligence.
Zero-shot MLLMs on ShanghaiTech and CHAD exhibit strong conservative bias with high precision but collapsed recall; class-specific prompts raise peak F1 from 0.09 to 0.64 yet recall remains the bottleneck.
citing papers explorer
-
From Mirage to Grounding: Towards Reliable Multimodal Circuit-to-Verilog Code Generation
MLLMs exhibit a Mirage effect by bypassing circuit diagrams in favor of header semantics for Verilog generation; VeriGround with identifier anonymization and D-ORPO training reaches 46% Functional Pass@1 while refusing blank images at >92%.
-
UniPPTBench: A Unified Benchmark for Presentation Generation Across Diverse Input Settings
The paper presents UniPPTBench and UniPPTEval, a unified benchmark and scenario-aware evaluation framework for presentation generation from vague prompts, long documents, multimodal documents, and multi-source inputs.
-
InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs
InfoTok uses mutual information constraints to regularize shared visual tokenization in unified MLLMs, improving both understanding and generation performance without extra training data.
-
Tactile-based Multimodal Fusion in Embodied Intelligence: A Survey of Vision, Language, and Contact-Driven Paradigms
A survey proposing a hierarchical taxonomy for multimodal tactile fusion datasets and methods across perception, generation, and interaction in embodied intelligence.
-
Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild
Zero-shot MLLMs on ShanghaiTech and CHAD exhibit strong conservative bias with high precision but collapsed recall; class-specific prompts raise peak F1 from 0.09 to 0.64 yet recall remains the bottleneck.