Alert button
Picture for Mohit Bansal

Mohit Bansal

Alert button

Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models

Mar 28, 2023
Adyasha Maharana, Amita Kamath, Christopher Clark, Mohit Bansal, Aniruddha Kembhavi

Figure 1 for Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models
Figure 2 for Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models
Figure 3 for Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models
Figure 4 for Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models
Viaarxiv icon

Faithfulness-Aware Decoding Strategies for Abstractive Summarization

Mar 06, 2023
David Wan, Mengwen Liu, Kathleen McKeown, Markus Dreyer, Mohit Bansal

Figure 1 for Faithfulness-Aware Decoding Strategies for Abstractive Summarization
Figure 2 for Faithfulness-Aware Decoding Strategies for Abstractive Summarization
Figure 3 for Faithfulness-Aware Decoding Strategies for Abstractive Summarization
Figure 4 for Faithfulness-Aware Decoding Strategies for Abstractive Summarization
Viaarxiv icon

Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models

Jan 10, 2023
Peter Hase, Mohit Bansal, Been Kim, Asma Ghandeharioun

Figure 1 for Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
Figure 2 for Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
Figure 3 for Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
Figure 4 for Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
Viaarxiv icon

Unifying Vision, Text, and Layout for Universal Document Processing

Dec 20, 2022
Zineng Tang, Ziyi Yang, Guoxin Wang, Yuwei Fang, Yang Liu, Chenguang Zhu, Michael Zeng, Cha Zhang, Mohit Bansal

Figure 1 for Unifying Vision, Text, and Layout for Universal Document Processing
Figure 2 for Unifying Vision, Text, and Layout for Universal Document Processing
Figure 3 for Unifying Vision, Text, and Layout for Universal Document Processing
Figure 4 for Unifying Vision, Text, and Layout for Universal Document Processing
Viaarxiv icon

MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation

Dec 16, 2022
Swarnadeep Saha, Xinyan Velocity Yu, Mohit Bansal, Ramakanth Pasunuru, Asli Celikyilmaz

Figure 1 for MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation
Figure 2 for MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation
Figure 3 for MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation
Figure 4 for MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation
Viaarxiv icon

Vision Transformers are Parameter-Efficient Audio-Visual Learners

Dec 15, 2022
Yan-Bo Lin, Yi-Lin Sung, Jie Lei, Mohit Bansal, Gedas Bertasius

Figure 1 for Vision Transformers are Parameter-Efficient Audio-Visual Learners
Figure 2 for Vision Transformers are Parameter-Efficient Audio-Visual Learners
Figure 3 for Vision Transformers are Parameter-Efficient Audio-Visual Learners
Figure 4 for Vision Transformers are Parameter-Efficient Audio-Visual Learners
Viaarxiv icon

VindLU: A Recipe for Effective Video-and-Language Pretraining

Dec 09, 2022
Feng Cheng, Xizi Wang, Jie Lei, David Crandall, Mohit Bansal, Gedas Bertasius

Figure 1 for VindLU: A Recipe for Effective Video-and-Language Pretraining
Figure 2 for VindLU: A Recipe for Effective Video-and-Language Pretraining
Figure 3 for VindLU: A Recipe for Effective Video-and-Language Pretraining
Figure 4 for VindLU: A Recipe for Effective Video-and-Language Pretraining
Viaarxiv icon

Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality

Nov 28, 2022
Yichen Jiang, Xiang Zhou, Mohit Bansal

Figure 1 for Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality
Figure 2 for Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality
Figure 3 for Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality
Figure 4 for Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality
Viaarxiv icon

Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention

Nov 21, 2022
Zineng Tang, Jaemin Cho, Jie Lei, Mohit Bansal

Figure 1 for Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention
Figure 2 for Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention
Figure 3 for Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention
Figure 4 for Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention
Viaarxiv icon