LingoLoop traps MLLMs into generating up to 367 times more tokens by applying POS-aware attention adjustments to postpone EOS tokens and pruning generative paths to sustain repetitive loops.
Gonzalez, Ion Stoica, and Eric P
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
baseline 1
method 1
citation-polarity summary
representative citing papers
InternVid supplies 7M videos and LLM captions to train ViCLIP, which reaches leading zero-shot action recognition and competitive retrieval performance.
GPT-4 as an LLM judge achieves over 80% agreement with human preferences on MT-Bench and Chatbot Arena, matching human agreement levels and providing a scalable evaluation method.
PMC-VQA dataset and MedVInT model achieve better generative performance on medical VQA benchmarks by visual instruction tuning on a newly constructed large-scale dataset.
CAMEL proposes a role-playing framework with inception prompting that enables autonomous multi-agent cooperation among LLMs and generates conversational data for studying their behaviors.
HuggingGPT is an agent system where ChatGPT plans and orchestrates calls to Hugging Face models to solve complex multi-modal AI tasks.
MiniGPT-v2 adds unique task identifiers to a large language model so one system can perform image description, visual question answering, and visual grounding after three-stage training.
citing papers explorer
-
LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops
LingoLoop traps MLLMs into generating up to 367 times more tokens by applying POS-aware attention adjustments to postpone EOS tokens and pruning generative paths to sustain repetitive loops.
-
InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
InternVid supplies 7M videos and LLM captions to train ViCLIP, which reaches leading zero-shot action recognition and competitive retrieval performance.
-
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
GPT-4 as an LLM judge achieves over 80% agreement with human preferences on MT-Bench and Chatbot Arena, matching human agreement levels and providing a scalable evaluation method.
-
PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
PMC-VQA dataset and MedVInT model achieve better generative performance on medical VQA benchmarks by visual instruction tuning on a newly constructed large-scale dataset.
-
CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
CAMEL proposes a role-playing framework with inception prompting that enables autonomous multi-agent cooperation among LLMs and generates conversational data for studying their behaviors.
-
HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
HuggingGPT is an agent system where ChatGPT plans and orchestrates calls to Hugging Face models to solve complex multi-modal AI tasks.
-
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
MiniGPT-v2 adds unique task identifiers to a large language model so one system can perform image description, visual question answering, and visual grounding after three-stage training.