Jaehong Yoon lists you as their postdoctoral advisor. Claim this profile to confirm it and keep the rest of your record right.
Claim this profileAcademic lineage
View as a treeStudents and postdocs1
Works411 from public data
- LXMERT: Learning Cross-Modality Encoder Representations from Transformers3,068
The LXMERT (Learning Cross-Modality Encoder Representations from Transformers) framework, a large-scale Transformer model that consists of three encoders, achieves the state-of-the-art results on two visual question answering datasets and shows the generalizability of the pre-trained cross-modality model.
- End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures1,320
A novel end-to-end neural model to extract entities and relations between them and compares favorably to the state-of-the-art CNN based model (in F1-score) on nominal relation classification (SemEval-2010 Task 8).
- Adversarial NLI: A New Benchmark for Natural Language Understanding1,300
This work introduces a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure, and shows that non-expert annotators are successful at finding their weaknesses.
- MAttNet: Modular Attention Network for Referring Expression Comprehension1,003
This work proposes to decompose expressions into three modular components related to subject appearance, location, and relationship to other objects, which allows for flexibly adapt to expressions containing different types of information in an end-to-end framework.
- Less is More: CLIPBERT for Video-and-Language Learning via Sparse Sampling836
Experiments on text-to-video retrieval and video question answering on six datasets demonstrate that CLIPBERT outperforms (or is on par with) existing methods that exploit full-length videos, suggesting that end- to-end learning with just a few sparsely sampled clips is often more accurate than using densely extracted offline features from full- length videos, proving the proverbial less-is-more principle.
- TVQA: Localized, Compositional Video Question Answering821
This paper presents TVQA, a large-scale video QA dataset based on 6 popular TV shows, and provides analyses of this new dataset as well as several baselines and a multi-stream end-to-end trainable neural network framework for the TVZA task.
- Dynabench: Rethinking Benchmarking in NLP654
It is argued that Dynabench addresses a critical need in the community: contemporary models quickly achieve outstanding performance on benchmark tasks but nonetheless fail on simple challenge examples and falter in real-world scenarios.
- Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting618
An accurate and fast summarization model that first selects salient sentences and then rewrites them abstractively to generate a concise overall summary is proposed, which achieves the new state-of-the-art on all metrics on the CNN/Daily Mail dataset, as well as significantly higher abstractiveness scores.
- 544
- VL-ADAPTER: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks521
The results demonstrate that training the adapter with the weight-sharing technique can match the performance of fine-tuning the entire model, and enhance the efficiency and performance of adapters by sharing their weights to attain knowledge across tasks.
- Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout422
This paper presents a generalizable navigational agent, trained in two stages via mixed imitation and reinforcement learning, outperforming the state-of-art approaches by a large margin on the private unseen test set of the Room-to-Room task, and achieving the top rank on the leaderboard.
- TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval388
The proposed XML model uses a late fusion design with a novel Convolutional Start-End detector (ConvSE), surpassing baselines by a large margin and with better efficiency, providing a strong starting point for future work.
- Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?386
Human subject tests are carried out that are the first of their kind to isolate the effect of algorithmic explanations on a key aspect of model interpretability, simulatability, while avoiding important confounding experimental factors.
- Analyzing and Mitigating Object Hallucination in Large Vision-Language Models381
This work proposes a simple yet powerful algorithm, LVLM Hallucination Revisor (LURE), to post-hoc rectify object hallucination in LVLMs by reconstructing less hallucinatory descriptions and consistently ranks at the top in both GPT and human evaluations.
- Rethinking machine unlearning for large language models364
An effective assessment framework for LLM unlearning is outlined and its applications in copyright and privacy safeguards and sociotechnical harm reduction are explored and revisiting methodologies and overlooked principles for future improvements are revisited.
- Combining Fact Extraction and Verification with Neural Semantic Matching Networks361
This paper presents a connected system consisting of three homogeneous neural semantic matching models that conduct document retrieval, sentence selection, and claim verification jointly for fact extraction and verification.
- DALL-EVAL: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models323
It is demonstrated that recent text-to-image generation models learn specific biases about gender and skin tone from web image-text pairs, which will help guide future progress in improving text-to-image generation models on visual reasoning skills and learning socially unbiased representations.
- VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos319
VideoTree is proposed, a training-free framework which builds a query-adaptive and hierarchical video representation for LLM reasoning over long-form videos that outperforms existing training-free approaches on EgoSchema and NExT-QA with less inference time.
- Tailoring Continuous Word Representations for Dependency Parsing313
It is found that all embeddings yield significant parsing gains, including some recent ones that can be trained in a fraction of the time of others, suggesting their complementarity.
- A Joint Speaker-Listener-Reinforcer Model for Referring Expressions295
A unified framework for the tasks of referring expression comprehension and generation is proposed, composed of three modules: speaker, listener, and reinforcer, which achieves state-of-the-art results for both comprehension andgeneration on three referring expression datasets.
- What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment295
An end-to-end, domain-independent neural encoder-aligner-decoder model for selective generation, i.e., the joint task of content selection and surface realization, achieves the best selection and generation results reported to-date on the benchmark WeatherGov dataset, despite using no specialized features or linguistic resources.
- TVQA+: Spatio-Temporal Grounding for Video Question Answering293
By performing this joint task, the proposed Spatio-Temporal Answerer with Grounded Evidence with STAGE model is able to produce insightful and interpretable spatio-temporal attention visualizations.
- From Paraphrase Database to Compositional Paraphrase Model and Back291
This work proposes models to leverage the phrase pairs from the Paraphrase Database to build parametric paraphrase models that score paraphrase pairs more accurately than the PPDB’s internal scores while simultaneously improving its coverage.
- HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification282
It is shown that the performance of an existing state-of-the-art semantic-matching model degrades significantly on this dataset as the number of reasoning hops increases, hence demonstrating the necessity of many-hop reasoning to achieve strong results.
- An Empirical Survey of Data Augmentation for Limited Data Learning in NLP264
An empirical survey of recent progress on data augmentation for NLP in the limited labeled data setting is provided, summarizing the landscape of methods and carrying out experiments on 11 datasets covering topics/news classification, inference tasks, paraphrasing tasks, and single-sentence tasks.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.