Kaixiang (@linkaixi) profile picture

RL researcher. Opinions are my own.

Sunnyvale CA
Joined March 2017
Photo by Kaixiang (@linkaixi)Photo by Kaixiang (@linkaixi)Photo by Kaixiang (@linkaixi)Photo by Kaixiang (@linkaixi)Photo by Kaixiang (@linkaixi)Photo by Kaixiang (@linkaixi)Photo by Kaixiang (@linkaixi)Photo by Kaixiang (@linkaixi)Photo by Kaixiang (@linkaixi)Photo by Kaixiang (@linkaixi)
Attending #ICLR2025 from 4/23 to 4/28 & will present PrefEval (prefeval.github.io/) discussing the performance of SoTA LLMs on personalization. Catch our presentations on April 26th: 🔥Oral: 10:42-10:54am @ Hall 1 Apex 📊 Poster #558: 3:00-5:30pm @ Hall 3 + Hall 2B Beyond personalization, If you’d like to chat about RL, reasoning, & multimodal agents. DM for a coffee chat, let's connect! #ICLR2025 #RL #LLM #AmazonScience
3
18
1,239
What a comprehensive collection of simulation platforms for embodied AI and RL! Add two more: aihabitat.org/ and svl.stanford.edu/igibson/
Some simulation platforms that caught my eye this year 🧵
Embodied & Teachable AI team at Amazon Alexa AI is looking for multiple research interns starting summer 2021. Please feel free to contact me if you are interested in Human-robot interaction, VQA, VLN, etc. #internship #machinelearning #AI #Amazon
8
8
#SIAMSDM18 Markov Chain Monitoring by Harshal Chaudhari et al. Design efficient algorithm to reduce the variance of prediction of positions of items with limited monitoring resources
3
#SIAMSDM18 Co-Regularized Monotone Retargeting for Semi-Supervised Letor by Shalmali Joshi et al. Utilizing convex structures of isotonic vectors for a semi-supervised learning to rank problem under multi-view setting.
#SIAMSDM18 Learning Graph Representation Via Frequent Subgraphs by Dang Nguyen. Unsupervised learning for graph embedding.
3
#SIAMSDM18 Latitude: A Model for Mixed Linear–Tropical Matrix Factorization by Sanjar Karaev,et al. combing NFM and subtropical matrix facorization
CP16 3rd paper: Sparse Graphical Modeling Via Stochastic Complexity from the Kohei Miyaguchi, University of Tokyo, Japan #SIAMSDM17
#SIAMSDM17 1st paper in optimization session
H-FLIP Supervised hash-based feature learning framework for regression. #SIAMSDM17 nitter.cf/linkaixi/status/858060…
1
Propose new problem: Rank aggregation is possible under strong privacy with minimal impact on the cost. nitter.cf/linkaixi/status/858056…
1
Design a single score works on any kind of data and any type of dependency. #SIAMSDM17 nitter.cf/linkaixi/status/857986…
1
Unsupervised feature selection incorporates the knowledge of hierarchical structures nitter.cf/linkaixi/status/857977…
1