InsightSee: Advancing Multi-agent Vision-Language Models for Enhanced Visual Understandingby Huaxiang Zhang, Yaojia Mu, Guo-Niu Zhu,…
Don’t Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Modelsby A. Bavaresco, A.…
The AI Alignment Paradoxby Robert West, Roland AydinFirst submitted to arxiv on: 31 May 2024CategoriesMain:…
clembench-2024: A Challenging, Dynamic, Complementary, Multilingual Benchmark and Underlying Flexible Framework for LLMs as Multi-Action…
Automatic Channel Pruning for Multi-Head Attentionby Eunho Lee, Youngbae HwangFirst submitted to arxiv on: 31…
MALT: Multi-scale Action Learning Transformer for Online Action Detectionby Zhipeng Yang, Ruoyu Wang, Yang Tan,…
Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Studyby…
Enhancing Vision Models for Text-Heavy Content Understanding and Interactionby Adithya TG, Adithya SK, Abhinav R…
Preemptive Answer “Attacks” on Chain-of-Thought Reasoningby Rongwu Xu, Zehan Qi, Wei XuFirst submitted to arxiv…
OR-Bench: An Over-Refusal Benchmark for Large Language Modelsby Justin Cui, Wei-Lin Chiang, Ion Stoica, Cho-Jui…