Search Results for author:
Found 12 papers, 1 papers with code
SudokuSens: Enhancing Deep Learning Robustness for IoT Sensing Applications using a Generative Approach
To incorporate sufficient diversity into the IoT training data, one therefore needs to consider a combinatorial explosion of training cases that are multiplicative in the number of objects considered and the possible environmental conditions in which such objects may be encountered.
TP-Aware Dequantization
In this paper, we present a novel method that reduces model inference latency during distributed deployment of Large Language Models (LLMs).
Accelerating a Triton Fused Kernel for W4A16 Quantized Inference with SplitK work decomposition
Our implementation shows improvement for the type of skinny matrix-matrix multiplications found in foundation model inference workloads.
State Action Separable Reinforcement Learning
We observe that although actions directly define the agents' behaviors, for many problems the next state after a state transition matters more than the action taken, in determining the return of such a state transition.
Neural Network Tomography
Network tomography, a classic research problem in the realm of network monitoring, refers to the methodology of inferring unmeasured network attributes using selected end-to-end path measurements.
SENSE: Semantically Enhanced Node Sequence Embedding
Effectively capturing graph node sequences in the form of vector embeddings is critical to many applications.
neuralRank: Searching and ranking ANN-based model repositories
The key idea behind this algorithm is to base model suitability on the discriminating power of a model, using a novel metric to measure it.
Actor Conditioned Attention Maps for Video Action Detection
While observing complex events with multiple actors, humans do not assess each actor separately, but infer from the context.
Object Localization and Size Estimation from RGB-D Images
However, the addition of a depth image can be further used to segment images that might otherwise have identical color information.
Beyond Spatial Auto-Regressive Models: Predicting Housing Prices with Satellite Imagery
Spatial Auto-Regression (SAR) is a common tool used to model such data, where the spatial contiguity matrix (W) encodes the spatial correlations.
