Papers with InternVL

4 papers
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track (2025.emnlp-industry)

Copied to clipboard

Challenge: EMNLP 2025 Industry Track highlights key insights, novel research trends and challenges encountered in practical language technology applications.
Approach: Kai Chen will present the technical advances behind the open-source Intern-series large models . he will highlight how models acquire expert-level skills in specialized domains .
Outcome: This talk will highlight the technical advances behind the open-source Intern-series models . it will highlight how models acquire expert-level skills in specialized domains while retaining broad generalization ability.
\mathsf{Con Instruction}: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities (2025.acl-long)

Copied to clipboard

Challenge: Existing attacks communicate instruction through text, accompanied by a toxic image or audio . a novel gray-box attack method generates adversarial images or audio to convey harmful instructions to MLLMs .
Approach: They propose a gray-box attack method that generates adversarial images or audio to convey specific harmful instructions to MLLMs by following non-textual instruction.
Outcome: The proposed method achieves highest success rates on visual and audio-language models . larger models are more susceptible toCon Instruction, compared to their underlying models - the results will be released .
TurkingBench: A Challenge Benchmark for Web Agents (2025.naacl-long)

Copied to clipboard

Challenge: TurkingBench is a benchmark consisting of tasks presented as web pages with textual instructions and multi-modal contexts.
Approach: They propose to use HTML pages to perform various annotation tasks on crowdsourcing platforms.
Outcome: The proposed model outperforms other models on the TurkingBench benchmark.
ClimateViz: A Benchmark for Statistical Reasoning and Fact Verification on Scientific Charts (2025.emnlp-main)

Copied to clipboard

Challenge: Scientific fact-checking has largely focused on textual and tabular sources, neglecting scientific charts.
Approach: They propose a benchmark for scientific fact-checking grounded in scientific charts . climateViz comprises 49,862 claims paired with 2,896 visualizations . results show current models struggle to perform fact- checking when statistical reasoning is required .
Outcome: The climateviz benchmark is the first large-scale benchmark for scientific fact-checking . it includes 49,862 claims paired with 2,896 visualizations labeled as support, refute, or not enough .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations