English
English Indonesia Türkçe Deutsch Español Português Pусский Français Italiano Nederlands Polski العربية ไทย Tiếng Việt 繁體中文 简体中文 日本語 한국어
yiwu5cs's profile picture. PhD Student @PurdueCS | #LLM #Robotics #AI

Yi Wu

@yiwu5cs

PhD Student @PurdueCS | #LLM #Robotics #AI

14Posts 218Followers 427Following
You might like
Yi Wu reposted
Lin0Tan's profile picture.
Lin Tan
 @Lin0Tan
Apr 25

Our SELP paper is an #ICRA25 Best Paper Award Finalist, among a selected few from 4,153 submissions! 🏆 Proud of my PhD student @yiwu5cs & the team! cs.purdue.edu/homes/lintan/p… #robotics #LLM #ConstrainedDecoding #Agent #LLMPlanner @PurdueCS @anikbera @ieee_ras_icra

Lin0Tan's profile picture. Elmore New Frontiers Professor @PurdueCS, Amazon Scholar @awscloud | Ex @Meta @UWaterloo @IllinoisCS @MSFTResearch @IBMResearch | #SE #LLM4Code #AI #Security
Lin Tan
 @Lin0Tan
Feb 5

Introducing our first #ICRA2025 paper, SELP (Safe Efficient LLM Planner), a method for generating plans for robot agents that adhere to user constraints while optimizing for time-efficient execution. 🔗 Preprint: arxiv.org/pdf/2409.19471 #LLMs #Robotics #Agent

Lin0Tan's tweet image. Introducing our first #ICRA2025 paper, SELP (Safe Efficient LLM Planner), a method for generating plans for robot agents that adhere to user constraints while optimizing for time-efficient execution. 🔗 Preprint: arxiv.org/pdf/2409.19471 #LLMs #Robotics #Agent
Lin0Tan's tweet image. Introducing our first #ICRA2025 paper, SELP (Safe Efficient LLM Planner), a method for generating plans for robot agents that adhere to user constraints while optimizing for time-efficient execution. 🔗 Preprint: arxiv.org/pdf/2409.19471 #LLMs #Robotics #Agent
Lin0Tan's tweet image. Introducing our first #ICRA2025 paper, SELP (Safe Efficient LLM Planner), a method for generating plans for robot agents that adhere to user constraints while optimizing for time-efficient execution. 🔗 Preprint: arxiv.org/pdf/2409.19471 #LLMs #Robotics #Agent
4
5
34
5
8K
8
2
41
0
7K
Yi Wu reposted
Lin0Tan's profile picture.
Lin Tan
 @Lin0Tan
Feb 5

Introducing our first #ICRA2025 paper, SELP (Safe Efficient LLM Planner), a method for generating plans for robot agents that adhere to user constraints while optimizing for time-efficient execution. 🔗 Preprint: arxiv.org/pdf/2409.19471 #LLMs #Robotics #Agent

Lin0Tan's tweet image. Introducing our first #ICRA2025 paper, SELP (Safe Efficient LLM Planner), a method for generating plans for robot agents that adhere to user constraints while optimizing for time-efficient execution. 🔗 Preprint: arxiv.org/pdf/2409.19471 #LLMs #Robotics #Agent
Lin0Tan's tweet image. Introducing our first #ICRA2025 paper, SELP (Safe Efficient LLM Planner), a method for generating plans for robot agents that adhere to user constraints while optimizing for time-efficient execution. 🔗 Preprint: arxiv.org/pdf/2409.19471 #LLMs #Robotics #Agent
Lin0Tan's tweet image. Introducing our first #ICRA2025 paper, SELP (Safe Efficient LLM Planner), a method for generating plans for robot agents that adhere to user constraints while optimizing for time-efficient execution. 🔗 Preprint: arxiv.org/pdf/2409.19471 #LLMs #Robotics #Agent
4
5
34
5
8K
Yi Wu reposted
Lin0Tan's profile picture.
Lin Tan
 @Lin0Tan
Nov 8, 2024

All LLMs including GPT-4o achieve < 30% pass@1 on real-world code completion: Check out 🐟REPOCOD, a real-world code generation benchmark: - Repository-level context - Whole function generation - Validation with test cases - 980 instances from 11 Python projects #LLM #LLM4Code

Lin0Tan's tweet image. All LLMs including GPT-4o achieve &amp;lt; 30% pass@1 on real-world code completion: Check out 🐟REPOCOD, a real-world code generation benchmark: - Repository-level context - Whole function generation - Validation with test cases - 980 instances from 11 Python projects #LLM #LLM4Code
Lin0Tan's tweet image. All LLMs including GPT-4o achieve &amp;lt; 30% pass@1 on real-world code completion: Check out 🐟REPOCOD, a real-world code generation benchmark: - Repository-level context - Whole function generation - Validation with test cases - 980 instances from 11 Python projects #LLM #LLM4Code
Lin0Tan's tweet image. All LLMs including GPT-4o achieve &amp;lt; 30% pass@1 on real-world code completion: Check out 🐟REPOCOD, a real-world code generation benchmark: - Repository-level context - Whole function generation - Validation with test cases - 980 instances from 11 Python projects #LLM #LLM4Code
3
11
59
19
7K
Yi Wu reposted
Lin0Tan's profile picture.
Lin Tan
 @Lin0Tan
Nov 1, 2024

Wanna generate webpages automatically? Meet🧇WAFFLE: multimodal #LLMs for generating HTML from UI images! It uses structure-aware attention & contrastive learning. arxiv.org/abs/2410.18362 #LLM4Code #MLLM #FrontendDev #WebDev @LiangShanchao @NanJiang719 Shangshu Qian

Lin0Tan's tweet image. Wanna generate webpages automatically? Meet🧇WAFFLE: multimodal #LLMs for generating HTML from UI images! It uses structure-aware attention &amp;amp; contrastive learning. arxiv.org/abs/2410.18362 #LLM4Code #MLLM #FrontendDev #WebDev @LiangShanchao @NanJiang719 Shangshu Qian
Lin0Tan's tweet image. Wanna generate webpages automatically? Meet🧇WAFFLE: multimodal #LLMs for generating HTML from UI images! It uses structure-aware attention &amp;amp; contrastive learning. arxiv.org/abs/2410.18362 #LLM4Code #MLLM #FrontendDev #WebDev @LiangShanchao @NanJiang719 Shangshu Qian
Lin0Tan's tweet image. Wanna generate webpages automatically? Meet🧇WAFFLE: multimodal #LLMs for generating HTML from UI images! It uses structure-aware attention &amp;amp; contrastive learning. arxiv.org/abs/2410.18362 #LLM4Code #MLLM #FrontendDev #WebDev @LiangShanchao @NanJiang719 Shangshu Qian
1
3
24
11
3K
Yi Wu reposted
NanJiang719's profile picture.
Nan Jiang
 @NanJiang719
Oct 30, 2024

Excited to introduce our NeurIPS 2024 paper: Open-source models struggle with self-debugging! We introduce LeDex, an automated pipeline for gathering self-debug data, boosting LLMs' debugging skills through supervised fine-tuning and reinforcement learning. #NeurIPS2024 #LLM4Code

NanJiang719's tweet image. Excited to introduce our NeurIPS 2024 paper: Open-source models struggle with self-debugging! We introduce LeDex, an automated pipeline for gathering self-debug data, boosting LLMs&apos; debugging skills through supervised fine-tuning and reinforcement learning. #NeurIPS2024 #LLM4Code
NanJiang719's tweet image. Excited to introduce our NeurIPS 2024 paper: Open-source models struggle with self-debugging! We introduce LeDex, an automated pipeline for gathering self-debug data, boosting LLMs&apos; debugging skills through supervised fine-tuning and reinforcement learning. #NeurIPS2024 #LLM4Code
1
2
16
3
1K
Yi Wu reposted
Lin0Tan's profile picture.
Lin Tan
 @Lin0Tan
Oct 21, 2024

Introducing Nova, a series of foundation models for binary/assembly code. We have also released fine-tuned models for binary code decompilation. #LLM #LLM4Code #BinaryAnalysis #Security @NanJiang719, Chengxiao Wang, Kevin Liu, @XiangzheX, Xiangyu Zhang, Petr Babkin.

Lin0Tan's tweet image. Introducing Nova, a series of foundation models for binary/assembly code. We have also released fine-tuned models for binary code decompilation. #LLM #LLM4Code #BinaryAnalysis #Security @NanJiang719, Chengxiao Wang, Kevin Liu, @XiangzheX, Xiangyu Zhang, Petr Babkin.
Lin0Tan's tweet image. Introducing Nova, a series of foundation models for binary/assembly code. We have also released fine-tuned models for binary code decompilation. #LLM #LLM4Code #BinaryAnalysis #Security @NanJiang719, Chengxiao Wang, Kevin Liu, @XiangzheX, Xiangyu Zhang, Petr Babkin.
Lin0Tan's tweet image. Introducing Nova, a series of foundation models for binary/assembly code. We have also released fine-tuned models for binary code decompilation. #LLM #LLM4Code #BinaryAnalysis #Security @NanJiang719, Chengxiao Wang, Kevin Liu, @XiangzheX, Xiangyu Zhang, Petr Babkin.
3
31
118
53
19K
Yi Wu reposted
Lin0Tan's profile picture.
Lin Tan
 @Lin0Tan
Aug 20, 2024

Introducing ReSym (CCS'24): our binary analysis technique, an LLM+static analysis solution that recovers names, types, and layouts of variables and data structures from binaries tinyurl.com/resym24 @danning_x, @i2huer, @NanJiang719, @XiangzheX XiangyuZhang #LLM4code #CCS #LLM

Lin0Tan's tweet image. Introducing ReSym (CCS&apos;24): our binary analysis technique, an LLM+static analysis solution that recovers names, types, and layouts of variables and data structures from binaries tinyurl.com/resym24 @danning_x, @i2huer, @NanJiang719, @XiangzheX XiangyuZhang #LLM4code #CCS #LLM
Lin0Tan's tweet image. Introducing ReSym (CCS&apos;24): our binary analysis technique, an LLM+static analysis solution that recovers names, types, and layouts of variables and data structures from binaries tinyurl.com/resym24 @danning_x, @i2huer, @NanJiang719, @XiangzheX XiangyuZhang #LLM4code #CCS #LLM
6
48
200
83
35K
yiwu5cs's profile picture.
Yi Wu
 @yiwu5cs
Jul 21, 2023

My first in-person conference @issta23 @issta_conf ! So exited! Presented my first paper and met with great researchers! UW is such a beautiful place #ISSTA23

yiwu5cs's tweet image. My first in-person conference @issta23 @issta_conf ! So exited! Presented my first paper and met with great researchers! UW is such a beautiful place #ISSTA23
2
0
42
0
3K

United States Trends

You might like

Something went wrong.


Something went wrong.