Picture for Mohit Bansal

Mohit Bansal

Shammie

Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?

Add code
Jun 27, 2024
Viaarxiv icon

See It from My Perspective: Diagnosing the Western Cultural Bias of Large Vision-Language Models in Image Understanding

Add code
Jun 17, 2024
Viaarxiv icon

REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy

Add code
Jun 11, 2024
Viaarxiv icon

Are language models rational? The case of coherence norms and belief revision

Add code
Jun 05, 2024
Viaarxiv icon

The Power of Summary-Source Alignments

Add code
Jun 02, 2024
Viaarxiv icon

LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models

Add code
May 31, 2024
Viaarxiv icon

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos

Add code
May 29, 2024
Figure 1 for VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
Figure 2 for VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
Figure 3 for VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
Figure 4 for VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
Viaarxiv icon

RACCooN: Remove, Add, and Change Video Content with Auto-Generated Narratives

Add code
May 28, 2024
Viaarxiv icon

FlexEControl: Flexible and Efficient Multimodal Control for Text-to-Image Generation

Add code
May 08, 2024
Figure 1 for FlexEControl: Flexible and Efficient Multimodal Control for Text-to-Image Generation
Figure 2 for FlexEControl: Flexible and Efficient Multimodal Control for Text-to-Image Generation
Figure 3 for FlexEControl: Flexible and Efficient Multimodal Control for Text-to-Image Generation
Figure 4 for FlexEControl: Flexible and Efficient Multimodal Control for Text-to-Image Generation
Viaarxiv icon

Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model

Add code
Apr 15, 2024
Viaarxiv icon