10 papers
One Empty Locker and Two Inspections: An Exact Optimal Team Strategy
Igor Kleiner, David Perry
We study a cooperative search game with lockers, labelled objects, one empty locker, and players. Player seeks object and may inspect at most two lockers; t…
FastFlow: Accelerating The Generative Flow Matching Models with Bandit Inference
Divya Jyoti Bajpai, Dhruv Bhardwaj, Soumya Roy +4
Flow-matching models deliver state-of-the-art fidelity in image and video generation, but the inherent sequential denoising process renders them slower. Existing acceleration metho…
FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow Matching
Divya Jyoti Bajpai, Shubham Agarwal, Apoorv Saxena +3
Flow Matching (FM) has recently emerged as a powerful approach for high-quality visual generation. However, their prohibitively slow inference due to a large number of denoising st…
FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference
Divya Jyoti Bajpai, Manjesh Kumar Hanawal
Vision-language Models (VLMs) have made significant strides in visual understanding and query response generation, but often face challenges of high computational cost and inferenc…
Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability
Divya Jyoti Bajpai, Manjesh Kumar Hanawal
Early-Exit Deep Neural Networks enable adaptive inference by allowing prediction at intermediary layers, significantly reducing computational costs and latency. Most of the early e…
Know What You Don't Know: Selective Prediction for Early Exit DNNs
Divya Jyoti Bajpai, Manjesh Kumar Hanawal
Inference latency and trustworthiness of Deep Neural Networks (DNNs) are the bottlenecks in deploying them in critical applications like sensitive tasks. Early Exit (EE) DNNs overc…