Search Results for author: Kaiqi Chen

Found 9 papers, 2 papers with code

DeFT: Flash Tree-attention with IO-Awareness for Efficient Tree-search-based LLM Inference

no code implementations30 Mar 2024 Jinwei Yao, Kaiqi Chen, Kexun Zhang, Jiaxuan You, Binhang Yuan, Zeke Wang, Tao Lin

Decoding using tree search can greatly enhance the inference quality for transformer-based Large Language Models (LLMs).

Behavioral Refinement via Interpolant-based Policy Diffusion

no code implementations25 Feb 2024 Kaiqi Chen, Eugene Lim, Kelvin Lin, Yiyang Chen, Harold Soh

However, the target policy to be learned is often significantly different from Gaussian and this mismatch can result in poor performance when using a small number of diffusion steps (to improve inference speed) and under limited data.

Imitation Learning

Latent Emission-Augmented Perspective-Taking (LEAPT) for Human-Robot Interaction

no code implementations12 Aug 2023 Kaiqi Chen, Jing Yu Lim, Kingsley Kuan, Harold Soh

Perspective-taking is the ability to perceive or understand a situation or concept from another individual's point of view, and is crucial in daily human interactions.

Semantic Visual Simultaneous Localization and Mapping: A Survey

no code implementations14 Sep 2022 Kaiqi Chen, Jianhua Zhang, Jialing Liu, Qiyi Tong, Ruyu Liu, ShengYong Chen

Numerous publications have reported that, by combining with the semantic information with vSLAM, the semantic vSLAM systems have the capability of solving the above problems in recent years.

Robot Navigation Simultaneous Localization and Mapping

MIRROR: Differentiable Deep Social Projection for Assistive Human-Robot Communication

1 code implementation6 Mar 2022 Kaiqi Chen, Jeffrey Fong, Harold Soh

In this work, we present MIRROR, an approach to (i) quickly learn human models from human demonstrations, and (ii) use the models for subsequent communication planning in assistive shared-control settings.

Imitation Learning

Collaborative Visual Inertial SLAM for Multiple Smart Phones

no code implementations23 Jun 2021 Jialing Liu, Ruyu Liu, Kaiqi Chen, Jianhua Zhang, Dongyan Guo

Each agent can independently explore the environment, run a visual-inertial odometry module online, and then send all the measurement information to a central server with higher computing resources.

Accurate Object Association and Pose Updating for Semantic SLAM

no code implementations21 Dec 2020 Kaiqi Chen, Jialing Liu, Jianhua Zhang, Zhenhua Wang

The key to solving this problem is to correctly associate multiple object measurements of one object landmark, and refine the pose of object landmark.

Multiple Object Tracking Object +1

Improving Layer-wise Adaptive Rate Methods using Trust Ratio Clipping

no code implementations27 Nov 2020 Jeffrey Fong, Siwei Chen, Kaiqi Chen

Training neural networks with large batch is of fundamental significance to deep learning.

Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.