Presentations
Lab Meeting
2024
[Sep 24, 2024] HIRE: Leveraging LLMs to Highlight and Reference Information(Research Project)[Sep 10, 2024] Faith and Fate: Transformers as fuzzy pattern matchers[Aug 13, 2024] Faithful CoT[Jul 22, 2024] The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in LLMs[Jul 10, 2024] Why are Visually-Grounded Language Models Bad at Image Classification[May 16, 2024] Hierarchical Open-vocabulary Universal Image Segmentation[Apr 16, 2024] GLaMM: Pixel Grounding Large Multimodal Model[Mar 12, 2024] Improved Zero-shot Classification by Adapting VLMs with Text Descriptions[Jan 30, 2024] Classification based on Boxes and Phrases (Research Project)2023
[Nov 21, 2023] What does CLIP know about a red circle? Visual prompt engineering for VLMs[Oct 3, 2023] CLIP-Event: Connecting Text and Images with Event Structures[Aug 25, 2023] How does “habitat” help fine-grained bird identification? (Research Project)[Apr 25, 2023] Zero-Shot Classification by Logical Reasoning on Natural Language Explanations[Mar 21, 2023] Open-Vocabulary Semantic Segmentation With Mask-Adapted CLIP[Feb 14, 2023] STAIR: Learning Sparse Text and Image Representation in Grounded Tokens2022
[Nov 22, 2022] Re-labeling ImageNet - from Single to Multi-Labels, from Global to Localized Labels[Oct 18, 2022] Class Activation Latent Mapping - Keep CALM and Improve Visual Feature Attribution[Sep 20, 2022] Mask2Former: Masked-attention Mask Transformer for Universal Image SegmentationPosts in this series