Search Results for author:
Found 5 papers, 2 papers with code
Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference
This approach effectively reduces both the KV cache size and memory bandwidth usage without compromising model accuracy.
Kepler: Robust Learning for Faster Parametric Query Optimization
We propose Kepler, an end-to-end learning-based approach to PQO that demonstrates significant speedups in query latency over a traditional query optimizer.
Cinderella's shoe won't fit Soundarya: An audit of facial processing tools on Indian faces
The tools display varying error rates in the face detection and gender and age classification functions.
GUIDED MCMC FOR SPARSE BAYESIAN MODELS TO DETECT RARE EVENTS IN IMAGES SANS LABELED DATA
After the steady-state is obtained for the underlying Markov chain, it is possible to compute the posterior probability of the presence of the rare event in a given image.
Urban Delay Tolerant Network Simulator (UDTNSim v0.1)
The major reasons for high delay include partial connectivity of networks as can be seen in many types of ad hoc wireless networks with frequent network partitions, long propagation time as experienced in inter-planetary and deep space networks, and frequent link disruptions due to the mobility of nodes as observed in terrestrial wireless network environments.
Networking and Internet Architecture
