activity
20242026
collaborators

12 papers

cs.IR2026

LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBay

Soumik Dey, Benjamin Braun, Naveen Ravipati +2

E-commerce sellers are advised to bid on keyphrases to boost their advertising campaigns. These keyphrases must be relevant to prevent irrelevant items from cluttering Search syste…

cs.CL2026

Batch Speculative Decoding Done Right

Ranran Haoran Zhang, Soumik Dey, Ashirbad Mishra +3

Speculative decoding must produce outputs distribution identical to standard autoregressive generation-this output equivalence is not an optimization target but the defining criter…

cs.CV2026

ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation

Mingyang Wu, Ashirbad Mishra, Soumik Dey +5

Image-to-Video generation (I2V) animates a static image into a temporally coherent video sequence following textual instructions, yet preserving fine-grained object identity under…

cs.IR2025

BroadGen: A Framework for Generating Effective and Efficient Advertiser Broad Match Keyphrase Recommendations

Ashirbad Mishra, Jinyu Zhao, Soumik Dey +3

In the domain of sponsored search advertising, the focus of Keyphrase recommendation has largely been on exact match types, which pose issues such as high management expenses, limi…

cs.CV2025

Q-Router: Agentic Video Quality Assessment with Expert Model Routing and Artifact Localization

Shuo Xing, Soumik Dey, Mingyang Wu +5

Video quality assessment (VQA) is a fundamental computer vision task that aims to predict the perceptual quality of a given video in alignment with human judgments. Existing perfor…

cs.CL2025

Performance and competence intertwined: A computational model of the Null Subject stage in English-speaking children

Soumik Dey, William Gregory Sakas

The empirically established null subject (NS) stage, lasting until about 4 years of age, involves frequent omission of subjects by children. Orfitelli and Hyams (2012) observe that…