Papers by Pradyumna Narayana

8 papers
CPL: Counterfactual Prompt Learning for Vision and Language Models (2022.emnlp-main)

Copied to clipboard

Challenge: Existing prompt tuning methods tend to learn spurious or entangled representations, leading to poor generalization to unseen concepts.
Approach: They propose a prompt tuning technique that tunes the learnable prompt for pre-trained vision and language models.
Outcome: The proposed method improves few-shot performance on vision and language tasks over existing prompt tuning methods.
Seeing Beyond: Enhancing Visual Question Answering with Multi-Modal Retrieval (2025.coling-industry)

Copied to clipboard

Challenge: Multi-modal Large language models still suffer from model hallucination and lack of specific knowledge when answering challenging questions.
Approach: They propose to use a multi-modal retrieval augmented generation method to integrate knowledge from all modalities into a model to enable alignment between query and knowledge.
Outcome: The proposed method achieves significant performance improvement on the VQA dataset.
Enhancing User Safety: Context-Aware Detection of Offensive Query-Ad Pairs in Multimodal Search Advertising (2026.eacl-industry)

Copied to clipboard

Challenge: Multi-modal online advertisements require robust content moderation to ensure user safety . key challenges include nuanced, multi-modal nature of ads, severe data scarcity and class imbalance due to the rarity of offensive content .
Approach: They propose a framework that detects offensive content only when a user's search query is paired with a specific ad .
Outcome: The proposed framework reduces the serving of offensive query-ad pairs by more than 80% while maintaining the efficiency required for real-time advertising systems.
KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models (2023.acl-industry)

Copied to clipboard

Challenge: Image ad understanding is a crucial task with wide real-world applications, but is under-explored in the machine learning community due to the lack of foundational vision-language models (VLMs) .
Approach: They propose a simple feature adaptation strategy to fuse multimodal information for image ads and further empower it with knowledge of real-world entities.
Outcome: The proposed strategy fuses multimodal information for image ads and empowers it with knowledge of real-world entities.
Diagnosing Vision-and-Language Navigation: What Really Matters (2022.naacl-main)

Copied to clipboard

Challenge: Existing models claim to be able to align object tokens with specific visual targets, but there are non-negligible gaps between the two.
Approach: They conduct diagnostic experiments to examine how the agents perceive multimodal input by ablation diagnostics input data.
Outcome: The results show that indoor and outdoor navigation agents refer to object and direction tokens when making decisions.
Towards Understanding Sample Variance in Visually Grounded Language Generation: Evaluations and Observations (2020.emnlp-main)

Copied to clipboard

Challenge: A major challenge in visually grounded language generation is to build robust benchmark datasets and models that can generalize well in real-world settings.
Approach: They propose to use visual attention to build robust benchmark datasets and models that can generalize well in real-world settings.
Outcome: The proposed models show that human-generated references vary drastically in different datasets/tasks, revealing the nature of each task.
PRISM: A New Lens for Improved Color Understanding (2024.emnlp-industry)

Copied to clipboard

Challenge: PRISM is a visual representation learner that can grasp the nuances of precise colors without compromising CLIP’s performance on established benchmarks.
Approach: They propose a method that extends CLIP's ability to grasp the nuances of precise colors by utilizing a curated dataset of 100 image-text pairs that can be effortlessly repurposed for fine-tuning.
Outcome: The proposed method improves CLIP's ability to grasp the nuances of precise colors without compromising CLIP’s performance on established benchmarks.
Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation (2021.eacl-main)

Copied to clipboard

Challenge: Outdoor vision-and-language navigation (VLN) tasks require visual grounding to generate correct actions.
Approach: They propose a multimodal text style transfer learning approach to mitigate data scarcity in outdoor vision-and-language navigation tasks.
Outcome: The proposed approach outperforms baseline models on the outdoor vision-and-language navigation task, improving task completion rate by 8.7% relative to the baseline models.

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