Profiles2020-2026
Jimmy Lin
University of Waterloo
20Papers
12Last author
46Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers20
- Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search AgentsAuthor 2 of 3ACL Findings 2026 · 1 citation
- Nearest Neighbor Speculative Decoding for LLM Generation and AttributionAuthor 5 of 10NeurIPS 2024 · 29 citations
- Unifying Multimodal Retrieval via Document Screenshot EmbeddingAuthor 5 of 5EMNLP 2024 · 13 citations
- Words Worth a Thousand Pictures: Measuring and Understanding Perceptual Variability in Text-to-Image GenerationAuthor 7 of 8EMNLP 2024
- Precise Zero-Shot Dense Retrieval without Relevance LabelsAuthor 3 of 4ACL 2023 · 211 citations
- What the DAAM: Interpreting Stable Diffusion Using Cross AttentionAuthor 8 of 10ACL 2023 · 93 citations
- "Low-Resource" Text Classification: A Parameter-Free Classification Method with CompressorsAuthor 6 of 6ACL Findings 2023 · 78 citations
- How to Train Your Dragon: Diverse Augmentation Towards Generalizable Dense RetrievalAuthor 5 of 8EMNLP Findings 2023 · 49 citations
- CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector RetrievalAuthor 5 of 9ACL 2023 · 10 citations
- Operator Selection and Ordering in a Pipeline Approach to Efficiency Optimizations for TransformersAuthor 5 of 5ACL Findings 2023
- XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic ParsingAuthor 3 of 3EMNLP Findings 2022 · 29 citations
- Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information RetrievalAuthor 4 of 4EMNLP Findings 2022 · 14 citations
- Few-Shot Non-Parametric Learning with Deep Latent Variable ModelAuthor 5 of 5NeurIPS 2022 · 6 citations
- Certified Error Control of Candidate Set Pruning for Two-Stage Relevance RankingAuthor 5 of 5EMNLP 2022 · 3 citations
- Multi-Task Dense Retrieval via Model Uncertainty Fusion for Open-Domain Question AnsweringAuthor 3 of 3EMNLP Findings 2021 · 10 citations
- Unsupervised Chunking as Syntactic Structure Induction with a Knowledge-Transfer ApproachAuthor 4 of 5EMNLP Findings 2021 · 2 citations
- The Art of Abstention: Selective Prediction and Error Regularization for Natural Language ProcessingAuthor 4 of 4ACL 2021
- Document Ranking with a Pretrained Sequence-to-Sequence ModelAuthor 4 of 4EMNLP Findings 2020 · 469 citations
- Cross-Lingual Training of Neural Models for Document RankingAuthor 3 of 3EMNLP Findings 2020 · 19 citations
- Inserting Information Bottleneck for Attribution in TransformersAuthor 4 of 4EMNLP Findings 2020 · 9 citations
