activity
20192023
most citedHybrid RL: Using Both Offline and Online Data Can Make RL Efficient

7 citations · 8 across the 6 of their papers we have counts for

collaborators
Showing 2022Show all

5 papers · 1 filter

cs.CL2022

Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQA

Elias Stengel-Eskin, Jimena Guallar-Blasco, Yi Zhou +1

Natural language is ambiguous. Resolving ambiguous questions is key to successfully answering them. Focusing on questions about images, we create a dataset of ambiguous examples. W…

cs.CV2022

: Backward-compatible Training with Basis Transformation

Yifei Zhou, Zilu Li, Abhinav Shrivastava +4

Modern retrieval system often requires recomputing the representation of every piece of data in the gallery when updating to a better representation model. This process is known as…

cs.CL2022

GAPX: Generalized Autoregressive Paraphrase-Identification X

Yifei Zhou, Renyu Li, Hayden Housen +1

Paraphrase Identification is a fundamental task in Natural Language Processing. While much progress has been made in the field, the performance of many state-of-the-art models ofte…

cs.LG2022★ 7 cited

Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient

Yuda Song, Yifei Zhou, Ayush Sekhari +3

We consider a hybrid reinforcement learning setting (Hybrid RL), in which an agent has access to an offline dataset and the ability to collect experience via real-world online inte…

cs.CL2022

Improve Discourse Dependency Parsing with Contextualized Representations

Yifei Zhou, Yansong Feng

Recent works show that discourse analysis benefits from modeling intra- and inter-sentential levels separately, where proper representations for text units of different granulariti…