Search Results for author:
Found 14 papers, 3 papers with code
State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models
At every timestep, our method directly affects the state at the current step, leading to more effective adaptation.
LoL-PIM: Long-Context LLM Decoding with Scalable DRAM-PIM System
Processing-in-Memory (PIM) maximizes memory bandwidth by moving compute to the data and can address the memory bandwidth challenges; however, PIM is not necessarily scalable to accelerate long-context LLM because of limited per-module memory capacity and the inflexibility of fixed-functional unit PIM architecture and static memory management.
Selectively Dilated Convolution for Accuracy-Preserving Sparse Pillar-based Embedded 3D Object Detection
To facilitate actual acceleration with this novel convolution approach, we designed SPADE+ as a cost-efficient augmentation to existing embedded sparse convolution accelerators.
Learning Equi-angular Representations for Online Continual Learning
Online continual learning suffers from an underfitted solution due to insufficient training for prompt model update (e. g., single-epoch training).
Just Say the Name: Online Continual Learning with Category Names Only via Data Generation
Requiring extensive human supervision is often impractical for continual learning due to its cost, leading to the emergence of 'name-only continual learning' that only provides the name of new concepts (e. g., classes) without providing supervised samples.
Rethinking Session Variability: Leveraging Session Embeddings for Session Robustness in Speaker Verification
In the field of speaker verification, session or channel variability poses a significant challenge.
Selective Generation for Controllable Language Models
$\texttt{SGen}^{\texttt{Sup}}$, a direct modification of the selective prediction, is a supervised learning algorithm which exploits entailment-labeled data, annotated by humans.
Leveraging Skill-to-Skill Supervision for Knowledge Tracing
To do so, knowledge tracing systems should trace the knowledge state of the students by utilizing their problem-solving history and knowledge about the problems.
Encoder-decoder multimodal speaker change detection
The task of speaker change detection (SCD), which detects points where speakers change in an input, is essential for several applications.
SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving
3D object detection using point cloud (PC) data is essential for perception pipelines of autonomous driving, where efficient encoding is key to meeting stringent resource and latency requirements.
NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networks
We introduce NeuralVDB, which improves on an existing industry standard for efficient storage of sparse volumetric data, denoted VDB [Museth 2013], by leveraging recent advancements in machine learning.
SVD-Softmax: Fast Softmax Approximation on Large Vocabulary Neural Networks
The approximate probability of each word can be estimated with only a small part of the weight matrix by using a few large singular values and the corresponding elements for most of the words.
FPGA-Based Low-Power Speech Recognition with Recurrent Neural Networks
The weights are quantized to 6 bits to store all of them in the on-chip memory of an FPGA.
Online Keyword Spotting with a Character-Level Recurrent Neural Network
In this paper, we propose a context-aware keyword spotting model employing a character-level recurrent neural network (RNN) for spoken term detection in continuous speech.
