Search Results for author:
Found 15 papers, 5 papers with code
The Eater and the Mover Game
This paper studies the idea of ``deception by motion'' through a two-player dynamic game played between a Mover who must retrieve resources at a goal location, and an Eater who can consume resources at two candidate goals.
Zero-Sum Games between Large-Population Teams: Reachability-based Analysis under Mean-Field Sharing
This work studies the behaviors of two large-population teams competing in a discrete environment.
On the Adversarial Convex Body Chasing Problem
In this work, we extend the convex bodies chasing problem (CBC) to an adversarial setting, where an agent (the Player) is tasked with chasing a sequence of convex bodies generated adversarially by another agent (the Opponent).
Transkimmer: Transformer Learns to Layer-wise Skim
To address the above limitations, we propose the Transkimmer architecture, which learns to identify hidden state tokens that are not required by each layer.
Dynamic Defender-Attacker Blotto Game
The game terminates with the attacker's win if any location has more attacker robots than defender robots at any time.
Block-Skim: Efficient Question Answering for Transformer
We further prune the hidden states corresponding to the unnecessary positions early in lower layers, achieving significant inference-time speedup.
Joint Optical Neuroimaging Denoising with Semantic Tasks
We use both the supervised and the self-supervised models for the denoising and introduce a new cost term for the joint denoising and the segmentation setup.
PointManifoldCut: Point-wise Augmentation in the Manifold for Point Clouds
This paper proposes a point cloud augmentation approach, PointManifoldCut(PMC), which replaces the neural network embedded points, rather than the Euclidean space coordinates.
Block Skim Transformer for Efficient Question Answering
Following this idea, we proposed Block Skim Transformer (BST) to improve and accelerate the processing of transformer QA models.
How Far Does BERT Look At: Distance-based Clustering and Analysis of BERT's Attention
Recent research on the multi-head attention mechanism, especially that in pre-trained models such as BERT, has shown us heuristics and clues in analyzing various aspects of the mechanism.
How Far Does BERT Look At:Distance-based Clustering and Analysis of BERT$'$s Attention
Recent research on the multi-head attention mechanism, especially that in pre-trained models such as BERT, has shown us heuristics and clues in analyzing various aspects of the mechanism.
Learning Nash Equilibria in Zero-Sum Stochastic Games via Entropy-Regularized Policy Approximation
We explore the use of policy approximations to reduce the computational cost of learning Nash equilibria in zero-sum stochastic games.
Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity
Network pruning can reduce the high computation cost of deep neural network (DNN) models.
Geometry Normalization Networks for Accurate Scene Text Detection
Large geometry (e. g., orientation) variances are the key challenges in the scene text detection.
Ranked #10 on
Scene Text Detection
on ICDAR 2017 MLT
