Alert button
Picture for Hugo Latapie

Hugo Latapie

Alert button

TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection

Add code
Bookmark button
Alert button
Mar 12, 2024
Hanning Chen, Wenjun Huang, Yang Ni, Sanggeon Yun, Fei Wen, Hugo Latapie, Mohsen Imani

Figure 1 for TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection
Figure 2 for TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection
Figure 3 for TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection
Figure 4 for TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection
Viaarxiv icon

HDReason: Algorithm-Hardware Codesign for Hyperdimensional Knowledge Graph Reasoning

Add code
Bookmark button
Alert button
Mar 09, 2024
Hanning Chen, Yang Ni, Ali Zakeri, Zhuowen Zou, Sanggeon Yun, Fei Wen, Behnam Khaleghi, Narayan Srinivasa, Hugo Latapie, Mohsen Imani

Figure 1 for HDReason: Algorithm-Hardware Codesign for Hyperdimensional Knowledge Graph Reasoning
Figure 2 for HDReason: Algorithm-Hardware Codesign for Hyperdimensional Knowledge Graph Reasoning
Figure 3 for HDReason: Algorithm-Hardware Codesign for Hyperdimensional Knowledge Graph Reasoning
Figure 4 for HDReason: Algorithm-Hardware Codesign for Hyperdimensional Knowledge Graph Reasoning
Viaarxiv icon

Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments

Add code
Bookmark button
Alert button
Feb 22, 2024
Yu Gu, Yiheng Shu, Hao Yu, Xiao Liu, Yuxiao Dong, Jie Tang, Jayanth Srinivasa, Hugo Latapie, Yu Su

Viaarxiv icon

CenterRadarNet: Joint 3D Object Detection and Tracking Framework using 4D FMCW Radar

Add code
Bookmark button
Alert button
Nov 04, 2023
Jen-Hao Cheng, Sheng-Yao Kuan, Hugo Latapie, Gaowen Liu, Jenq-Neng Hwang

Viaarxiv icon

VQPy: An Object-Oriented Approach to Modern Video Analytics

Add code
Bookmark button
Alert button
Nov 03, 2023
Shan Yu, Zhenting Zhu, Yu Chen, Hanchen Xu, Pengzhan Zhao, Yang Wang, Arthi Padmanabhan, Hugo Latapie, Harry Xu

Figure 1 for VQPy: An Object-Oriented Approach to Modern Video Analytics
Figure 2 for VQPy: An Object-Oriented Approach to Modern Video Analytics
Figure 3 for VQPy: An Object-Oriented Approach to Modern Video Analytics
Figure 4 for VQPy: An Object-Oriented Approach to Modern Video Analytics
Viaarxiv icon

Ethosight: A Reasoning-Guided Iterative Learning System for Nuanced Perception based on Joint-Embedding & Contextual Label Affinity

Add code
Bookmark button
Alert button
Jul 21, 2023
Hugo Latapie, Kristinn R. Thorisson, Shan Yu, Vahagn Petrosyan, Patrick Hammer, Pei Wang, Brandon Kynoch, Hanning Chen, Tangrui Li

Viaarxiv icon

RecallM: An Architecture for Temporal Context Understanding and Question Answering

Add code
Bookmark button
Alert button
Jul 10, 2023
Brandon Kynoch, Hugo Latapie

Figure 1 for RecallM: An Architecture for Temporal Context Understanding and Question Answering
Figure 2 for RecallM: An Architecture for Temporal Context Understanding and Question Answering
Figure 3 for RecallM: An Architecture for Temporal Context Understanding and Question Answering
Figure 4 for RecallM: An Architecture for Temporal Context Understanding and Question Answering
Viaarxiv icon

EENet: Learning to Early Exit for Adaptive Inference

Add code
Bookmark button
Alert button
Jan 15, 2023
Fatih Ilhan, Ling Liu, Ka-Ho Chow, Wenqi Wei, Yanzhao Wu, Myungjin Lee, Ramana Kompella, Hugo Latapie, Gaowen Liu

Figure 1 for EENet: Learning to Early Exit for Adaptive Inference
Figure 2 for EENet: Learning to Early Exit for Adaptive Inference
Figure 3 for EENet: Learning to Early Exit for Adaptive Inference
Figure 4 for EENet: Learning to Early Exit for Adaptive Inference
Viaarxiv icon

A Retrieve-and-Read Framework for Knowledge Graph Link Prediction

Add code
Bookmark button
Alert button
Dec 19, 2022
Vardaan Pahuja, Boshi Wang, Hugo Latapie, Jayanth Srinivasa, Yu Su

Figure 1 for A Retrieve-and-Read Framework for Knowledge Graph Link Prediction
Figure 2 for A Retrieve-and-Read Framework for Knowledge Graph Link Prediction
Figure 3 for A Retrieve-and-Read Framework for Knowledge Graph Link Prediction
Figure 4 for A Retrieve-and-Read Framework for Knowledge Graph Link Prediction
Viaarxiv icon

Learning Omnidirectional Flow in 360-degree Video via Siamese Representation

Add code
Bookmark button
Alert button
Aug 07, 2022
Keshav Bhandari, Bin Duan, Gaowen Liu, Hugo Latapie, Ziliang Zong, Yan Yan

Figure 1 for Learning Omnidirectional Flow in 360-degree Video via Siamese Representation
Figure 2 for Learning Omnidirectional Flow in 360-degree Video via Siamese Representation
Figure 3 for Learning Omnidirectional Flow in 360-degree Video via Siamese Representation
Figure 4 for Learning Omnidirectional Flow in 360-degree Video via Siamese Representation
Viaarxiv icon