Akhil Bhimaraju
YOU?
Author Swipe
View article: Skip-It? Theoretical Conditions for Layer Skipping in Vision-Language Models
Skip-It? Theoretical Conditions for Layer Skipping in Vision-Language Models Open
Vision-language models (VLMs) achieve incredible performance across a wide range of tasks, but their large size makes inference costly. Recent work shows that selectively skipping VLM layers can improve efficiency with minimal performance …
View article: Dynamic batching of online arrivals to leverage economies of scale
Dynamic batching of online arrivals to leverage economies of scale Open
View article: DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding
DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding Open
The hyperscaling of data and parameter count in transformer models is yielding diminishing performance improvement, especially when weighed against training costs. Such plateauing underlines a growing need for more efficient finetuning and…
View article: Review of: "Poisson Network SIR Epidemic Model"
Review of: "Poisson Network SIR Epidemic Model" Open
View article: Fractional Budget Allocation for Influence Maximization under General Marketing Strategies
Fractional Budget Allocation for Influence Maximization under General Marketing Strategies Open
We consider the fractional influence maximization problem, i.e., identifying users on a social network to be incentivized with potentially partial discounts to maximize the influence on the network. The larger the discount given to a user,…
View article: Dynamic Resource Allocation to Minimize Concave Costs of Shortfalls
Dynamic Resource Allocation to Minimize Concave Costs of Shortfalls Open
We study a resource allocation problem over time, where a finite (random) resource needs to be distributed among a set of users at each time instant. Shortfalls in the resource allocated result in user dissatisfaction, which we model as an…
View article: Dynamic Batching of Online Arrivals to Leverage Economies of Scale
Dynamic Batching of Online Arrivals to Leverage Economies of Scale Open
Many settings, such as matching riders to drivers in ride-hailing platforms or in-stream video advertising, require handling arrivals over time. In such applications, it is often beneficial to group the arriving orders or requests into bat…
View article: Multi-channel Resource Allocation for Smooth Streaming: Non-convexity and Bandits
Multi-channel Resource Allocation for Smooth Streaming: Non-convexity and Bandits Open
User dissatisfaction due to buffering pauses during streaming is a significant cost to the system, which we model as a non-decreasing function of the frequency of buffering pause. Minimization of total user dissatisfaction in a multi-chann…
View article: Resource Allocation for Smooth Streaming: Non-convexity and Bandits.
Resource Allocation for Smooth Streaming: Non-convexity and Bandits. Open
User dissatisfaction due to buffering pauses during streaming is a significant cost to the system, which we model as a non-decreasing function of the frequency of buffering pause. Minimization of total user dissatisfaction in a multi-chann…
View article: Mean Extinction Times of Epidemics with State-Dependent Infectiousness
Mean Extinction Times of Epidemics with State-Dependent Infectiousness Open
We model an epidemic where the per-person infectiousness in a network of geographic localities changes with the total number of active cases. This would happen as people adopt more stringent non-pharmaceutical precautions when the populati…
View article: Non-clairvoyant Scheduling of Coflows
Non-clairvoyant Scheduling of Coflows Open
The coflow scheduling problem is considered: given an input/output switch with each port having a fixed capacity, find a scheduling algorithm that minimizes the weighted sum of the coflow completion times respecting the port capacities, wh…