Archive

2024  49

June  6

Damai Dai Deepseekmoe 2024

<span title='2024-06-22 11:13:50 +1000 AEST'>June 22, 2024</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;582 words&nbsp;·&nbsp;Sukai Huang

Posts

<span title='2024-06-22 11:13:50 +1000 AEST'>June 22, 2024</span>&nbsp;·&nbsp;0 min&nbsp;·&nbsp;Sukai Huang

Jessy Lin Learning to Model the World With Language 2024

<span title='2024-06-21 11:47:25 +1000 AEST'>June 21, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;381 words&nbsp;·&nbsp;Sukai Huang

Verification in Llm Topic 2024

<span title='2024-06-20 20:19:12 +1000 AEST'>June 20, 2024</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;110 words&nbsp;·&nbsp;Sukai Huang

Jiuzhou Reward Engineering for Generating Semi Structured Explan 2023

<span title='2024-06-20 14:11:32 +1000 AEST'>June 20, 2024</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;162 words&nbsp;·&nbsp;Sukai Huang

Jiuzhou Towards Uncertainty Aware Lang Agent 2024

<span title='2024-06-20 11:15:18 +1000 AEST'>June 20, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;295 words&nbsp;·&nbsp;Sukai Huang

May  6

Silviu Pitis Failure Modes of Learning Reward Models for Sequence Model 2023

<span title='2024-05-10 22:23:31 +1000 AEST'>May 10, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;312 words&nbsp;·&nbsp;Sukai Huang

Gaurav Ghosal the Effect of Modeling Human Rationality Level 2023

<span title='2024-05-10 19:35:03 +1000 AEST'>May 10, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;312 words&nbsp;·&nbsp;Sukai Huang

Nate Rahn Policy Optimization in Noisy Neighbourhood 2023

<span title='2024-05-10 14:16:56 +1000 AEST'>May 10, 2024</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;510 words&nbsp;·&nbsp;Sukai Huang

Ademi Adeniji Language Reward Modulation for Pretraining Rl 2023

<span title='2024-05-09 21:18:00 +1000 AEST'>May 9, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;338 words&nbsp;·&nbsp;Sukai Huang

Thomas Coste Reward Model Ensembles Help Mitigate Overoptimization 2024

<span title='2024-05-09 14:06:33 +1000 AEST'>May 9, 2024</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;205 words&nbsp;·&nbsp;Sukai Huang

Mengdi Li Internally Rewarded Rl 2023

<span title='2024-05-08 14:59:15 +1000 AEST'>May 8, 2024</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;682 words&nbsp;·&nbsp;Sukai Huang

April  8

Xuran Pan on the Integration of Self Attention and Convolution 2022

<span title='2024-04-25 17:53:46 +1000 AEST'>April 25, 2024</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;147 words&nbsp;·&nbsp;Sukai Huang

Recent Language Model Technique 2024

<span title='2024-04-25 12:49:03 +1000 AEST'>April 25, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;332 words&nbsp;·&nbsp;Sukai Huang

Thomas Carta Grounding Llms in Rl 2023

<span title='2024-04-23 13:20:22 +1000 AEST'>April 23, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;242 words&nbsp;·&nbsp;Sukai Huang

Daniel Hierarchies of Reward Machines 2023

<span title='2024-04-12 15:12:54 +1000 AEST'>April 12, 2024</span>&nbsp;·&nbsp;5 min&nbsp;·&nbsp;965 words&nbsp;·&nbsp;Sukai Huang

Shanchuan Efficient N Robust Exploration Through Discriminative Ir 2023

<span title='2024-04-12 15:07:58 +1000 AEST'>April 12, 2024</span>&nbsp;·&nbsp;9 min&nbsp;·&nbsp;1795 words&nbsp;·&nbsp;Sukai Huang

How to Autostart Apps on Your Server

<span title='2024-04-12 12:23:29 +1000 AEST'>April 12, 2024</span>&nbsp;·&nbsp;6 min&nbsp;·&nbsp;1109 words&nbsp;·&nbsp;Sukai Huang

Programming-Notes

<span title='2024-04-12 12:23:29 +1000 AEST'>April 12, 2024</span>&nbsp;·&nbsp;0 min&nbsp;·&nbsp;Sukai Huang

Discover Hierarchical Achieve in Rl via Cl 2023

<span title='2024-04-02 21:02:37 +1100 AEDT'>April 2, 2024</span>&nbsp;·&nbsp;5 min&nbsp;·&nbsp;1047 words&nbsp;·&nbsp;Sukai Huang

March  1

Using Kedro And Optuna for Your Project

<span title='2024-03-27 21:50:10 +1100 AEDT'>March 27, 2024</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;641 words&nbsp;·&nbsp;Sukai Huang

February  5

Jia Li Structured Cot Prompting for Code Generation 2023

<span title='2024-02-28 19:59:38 +1100 AEDT'>February 28, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;381 words&nbsp;·&nbsp;Sukai Huang

Stephanie Teaching Models to Express Their Uncertainty in Words 2022

<span title='2024-02-28 16:12:53 +1100 AEDT'>February 28, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;327 words&nbsp;·&nbsp;Sukai Huang

Gwenyth Estimating Confidence of Llm by Prompt Agreement 2023

<span title='2024-02-27 15:44:06 +1100 AEDT'>February 27, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;393 words&nbsp;·&nbsp;Sukai Huang

Sudhir Agarwal Translate Infer Compile for Accurate Text to Plan 2024

<span title='2024-02-17 12:56:25 +1100 AEDT'>February 17, 2024</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;639 words&nbsp;·&nbsp;Sukai Huang

How to Design Your Research Project Structure

<span title='2024-02-02 19:50:31 +1100 AEDT'>February 2, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;237 words&nbsp;·&nbsp;Sukai Huang

January  23

Philip Cohen Intention Is Choice With Commitment 1990

<span title='2024-01-30 23:17:51 +1100 AEDT'>January 30, 2024</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;752 words&nbsp;·&nbsp;Sukai Huang

Christian Muise Planning for Goal Oriented Dialgue Systems 2019

<span title='2024-01-30 16:58:06 +1100 AEDT'>January 30, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;416 words&nbsp;·&nbsp;Sukai Huang

Vishal Pallagani Llm N Planning Survey 2024

<span title='2024-01-29 23:02:47 +1100 AEDT'>January 29, 2024</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;546 words&nbsp;·&nbsp;Sukai Huang

Ishika Singh Progprompt Program Generation for Robot Task Planning 2023

<span title='2024-01-29 20:45:59 +1100 AEDT'>January 29, 2024</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;101 words&nbsp;·&nbsp;Sukai Huang

Avichai Levy Understanding Natural Language in Context 2023

<span title='2024-01-29 20:25:43 +1100 AEDT'>January 29, 2024</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;477 words&nbsp;·&nbsp;Sukai Huang

Mingyu Jin the Impact of Reasoning Steps Length on Llm 2024

<span title='2024-01-29 17:44:10 +1100 AEDT'>January 29, 2024</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;568 words&nbsp;·&nbsp;Sukai Huang

Weak-To-Strong-Generalization: Eliciting Strong Capabilities with Weak Supervision

<span title='2024-01-29 15:32:21 +1100 AEDT'>January 29, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;377 words&nbsp;·&nbsp;Sukai Huang

Ziwei Xu Hallucination Is Inevitable an Innate Limitation Llm 2024

<span title='2024-01-28 23:11:28 +1100 AEDT'>January 28, 2024</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;543 words&nbsp;·&nbsp;Sukai Huang

Zhiwei He Improving Machine Translation Use Quality Estimation as a Reward Model 2024

<span title='2024-01-28 22:53:41 +1100 AEDT'>January 28, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;285 words&nbsp;·&nbsp;Sukai Huang

Krishan Rana Sayplan Grounding Llm for Scalable Task Planning 2023

<span title='2024-01-28 21:37:21 +1100 AEDT'>January 28, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;388 words&nbsp;·&nbsp;Sukai Huang

Luigi Bonassi Planning With Qualitative Constraints Pddl3 2022

<span title='2024-01-28 21:28:51 +1100 AEDT'>January 28, 2024</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;125 words&nbsp;·&nbsp;Sukai Huang

Parsa Mahmoudieh Zero Shot Reward Specification via Grounded Natural Language 2022

<span title='2024-01-28 09:31:05 +1100 AEDT'>January 28, 2024</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;538 words&nbsp;·&nbsp;Sukai Huang

Allen Z Ren Robots That Ask for Help Uncertainty Alignment 2023

<span title='2024-01-26 17:29:29 +1100 AEDT'>January 26, 2024</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;510 words&nbsp;·&nbsp;Sukai Huang

Marta Skreta Replan Robotic Replanning 2024

<span title='2024-01-25 00:55:05 +1100 AEDT'>January 25, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;261 words&nbsp;·&nbsp;Sukai Huang

Binghai Wang Secrets of Rlhf Reward Modelling 2024

<span title='2024-01-24 23:31:28 +1100 AEDT'>January 24, 2024</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;144 words&nbsp;·&nbsp;Sukai Huang

Rui Zheng Secrets of Rlhf in Llm Part Ppo 2023

<span title='2024-01-22 20:26:18 +1100 AEDT'>January 22, 2024</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;465 words&nbsp;·&nbsp;Sukai Huang

Zhiting Hu Language Agent and World Models 2023

<span title='2024-01-22 16:01:20 +1100 AEDT'>January 22, 2024</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;749 words&nbsp;·&nbsp;Sukai Huang

React Js Development 2024

<span title='2024-01-21 17:40:43 +1100 AEDT'>January 21, 2024</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;140 words&nbsp;·&nbsp;Sukai Huang

Gautier Dagan Dynamic Planning With a Llm 2023

<span title='2024-01-21 01:42:23 +1100 AEDT'>January 21, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;384 words&nbsp;·&nbsp;Sukai Huang

Jun Wang Conformal Temporal Logic Planning Using Llm 2023

<span title='2024-01-21 00:34:56 +1100 AEDT'>January 21, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;357 words&nbsp;·&nbsp;Sukai Huang

Python and Os Utils 2024

<span title='2024-01-18 18:51:51 +1100 AEDT'>January 18, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;325 words&nbsp;·&nbsp;Sukai Huang

Gerevini Plan Constraints and Preferences in Pddl3 2005

<span title='2024-01-11 19:54:29 +1100 AEDT'>January 11, 2024</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;122 words&nbsp;·&nbsp;Sukai Huang

Nir Lipo Planning With Perspectives Using Functional Strips 2022

<span title='2024-01-11 19:41:55 +1100 AEDT'>January 11, 2024</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;267 words&nbsp;·&nbsp;Sukai Huang

2023  89

December  1

Python Logger

<span title='2023-12-04 20:25:12 +1100 AEDT'>December 4, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;496 words&nbsp;·&nbsp;Sukai Huang

November  2

Alex_coulter Theory Alignment via a Classical Encoding of Regular Bismulation 2022

<span title='2023-11-29 17:24:08 +1100 AEDT'>November 29, 2023</span>&nbsp;·&nbsp;6 min&nbsp;·&nbsp;1083 words&nbsp;·&nbsp;Sukai Huang

Pascal Bercher Detecting Ai Planning Modelling Mistakes Potential Errors and Benchmark Domains 2023

<span title='2023-11-13 22:33:14 +1100 AEDT'>November 13, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;408 words&nbsp;·&nbsp;Sukai Huang

October  5

Yecheng Jason Ma Eureka Human Level Reward Design via Coding Large Language Models 2023

<span title='2023-10-27 16:44:22 +1100 AEDT'>October 27, 2023</span>&nbsp;·&nbsp;6 min&nbsp;·&nbsp;1163 words&nbsp;·&nbsp;Sukai Huang

Mark Chen Evaluating Large Language Models Trained on Code 2021

<span title='2023-10-16 07:24:26 +1100 AEDT'>October 16, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;298 words&nbsp;·&nbsp;Sukai Huang

Baptiste Roziere Code Llama Open Foundation Model for Code 2023

<span title='2023-10-16 02:58:20 +1100 AEDT'>October 16, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;284 words&nbsp;·&nbsp;Sukai Huang

Haotian Liu Improved Baselines With Visual Instruction Tuning 2023

<span title='2023-10-08 10:37:37 +1100 AEDT'>October 8, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;240 words&nbsp;·&nbsp;Sukai Huang

Christabel Wayllace Goal Recognition Design With Stochastic Agent Action Outcomes 2016

<span title='2023-10-06 18:16:28 +1100 AEDT'>October 6, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;191 words&nbsp;·&nbsp;Sukai Huang

September  4

Alba Gragera Pddl Domain Repair Fixing Domains With Incomplete Action Effects 2023

<span title='2023-09-20 23:17:51 +1000 AEST'>September 20, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;153 words&nbsp;·&nbsp;Sukai Huang

Alba Gragera Exploring the Limitations of Using LLMs to Fix Planning Tasks 2023

<span title='2023-09-20 20:22:32 +1000 AEST'>September 20, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;403 words&nbsp;·&nbsp;Sukai Huang

Tathagata Chakraborti Plan Explanations as Model Reconciliation 2017

<span title='2023-09-19 22:04:06 +1000 AEST'>September 19, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;630 words&nbsp;·&nbsp;Sukai Huang

Vishal Pallagani Plansformer Tool Demonstrating Generation of Symbolic Plans Using Transformers 2023

<span title='2023-09-16 00:46:56 +1000 AEST'>September 16, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;105 words&nbsp;·&nbsp;Sukai Huang

August  5

Junnan_li Blip2 Boostrapping Language Image Pretraining 2023

<span title='2023-08-28 18:48:08 +1000 AEST'>August 28, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;327 words&nbsp;·&nbsp;Sukai Huang

Peng_gao Llama Adapter V2 2023

<span title='2023-08-28 18:47:05 +1000 AEST'>August 28, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;246 words&nbsp;·&nbsp;Sukai Huang

Langchain Use Cases 2023

<span title='2023-08-26 17:36:47 +1000 AEST'>August 26, 2023</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;700 words&nbsp;·&nbsp;Sukai Huang

Rodrigo Reward Machines Exploiting Reward Function Structure in Rl 2022

<span title='2023-08-17 16:32:09 +1000 AEST'>August 17, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;321 words&nbsp;·&nbsp;Sukai Huang

Rodrigo Using Reward Machines for High Level Task Specification and Decomposition in Rl 2018

<span title='2023-08-17 11:13:24 +1000 AEST'>August 17, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;360 words&nbsp;·&nbsp;Sukai Huang

July  7

Pytorch Multiprocessing 2023

<span title='2023-07-18 16:48:13 +1000 AEST'>July 18, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;93 words&nbsp;·&nbsp;Sukai Huang

Remote Server, Tmux and Joshuto 2023

<span title='2023-07-16 18:45:57 +1000 AEST'>July 16, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;557 words&nbsp;·&nbsp;Sukai Huang

05 Jul – 31 Jul, 2023

<span title='2023-07-05 00:35:22 +1000 AEST'>July 5, 2023</span>&nbsp;·&nbsp;7 min&nbsp;·&nbsp;Sukai Huang

Weekly-Reports

<span title='2023-07-05 00:35:22 +1000 AEST'>July 5, 2023</span>&nbsp;·&nbsp;0 min&nbsp;·&nbsp;Sukai Huang

William_berrios Towards Language Models That Can See 2023

<span title='2023-07-03 19:33:22 +1000 AEST'>July 3, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;152 words&nbsp;·&nbsp;Sukai Huang

Lionel_wong From Word Models to World Models 2023

<span title='2023-07-02 21:24:50 +1000 AEST'>July 2, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;460 words&nbsp;·&nbsp;Sukai Huang

Jianning_wang Boosting Language Models Reasoning With Chain of Knowledge Prompting 2023

<span title='2023-07-02 16:09:58 +1000 AEST'>July 2, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;264 words&nbsp;·&nbsp;Sukai Huang

June  6

26 Jun – 30 Jun, 2023

<span title='2023-06-26 13:14:16 +1000 AEST'>June 26, 2023</span>&nbsp;·&nbsp;20 min&nbsp;·&nbsp;Sukai Huang

Undetected Chromedriver Use Case

<span title='2023-06-22 22:38:28 +1000 AEST'>June 22, 2023</span>&nbsp;·&nbsp;10 min&nbsp;·&nbsp;2086 words&nbsp;·&nbsp;Sukai Huang

Web Scrawler Using Selenium 2023

<span title='2023-06-22 22:38:28 +1000 AEST'>June 22, 2023</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;813 words&nbsp;·&nbsp;Sukai Huang

Xpath-cheatsheet

<span title='2023-06-22 22:38:28 +1000 AEST'>June 22, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;7 words&nbsp;·&nbsp;Sukai Huang

07 Jun – 14 Jun, 2023

<span title='2023-06-07 22:49:20 +1000 AEST'>June 7, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

Lin_guan Leveraging Pretrained Llm to Construct and Utilise World Models for Model Based Task Planning 2023

<span title='2023-06-04 12:01:46 +1000 AEST'>June 4, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;499 words&nbsp;·&nbsp;Sukai Huang

May  16

01 Jun – 06 Jun, 2023

<span title='2023-05-29 17:07:51 +1000 AEST'>May 29, 2023</span>&nbsp;·&nbsp;10 min&nbsp;·&nbsp;Sukai Huang

Python Module and Package Management 2023

<span title='2023-05-28 11:56:47 +1000 AEST'>May 28, 2023</span>&nbsp;·&nbsp;5 min&nbsp;·&nbsp;1024 words&nbsp;·&nbsp;Sukai Huang

Dharma_kc Neural Machine Translation for Code Generation 2023

<span title='2023-05-28 09:52:32 +1000 AEST'>May 28, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;181 words&nbsp;·&nbsp;Sukai Huang

Jiannan_xiang Language Models Meet World Models 2023

<span title='2023-05-26 01:00:02 +1000 AEST'>May 26, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;357 words&nbsp;·&nbsp;Sukai Huang

Ryan_yang PG3 Policy Guided Planning for Generalised Policy Generation 2022

<span title='2023-05-24 19:57:16 +1000 AEST'>May 24, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;304 words&nbsp;·&nbsp;Sukai Huang

Shunyu_yao Tree of Thoughts 2023

<span title='2023-05-24 16:35:10 +1000 AEST'>May 24, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;104 words&nbsp;·&nbsp;Sukai Huang

Tom_silver Generalised Planning in PDDL Domains With Pretrained Large Language Models 2023

<span title='2023-05-23 21:27:15 +1000 AEST'>May 23, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;551 words&nbsp;·&nbsp;Sukai Huang

Yongliang Hugginggpt 2023

<span title='2023-05-23 11:57:02 +1000 AEST'>May 23, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;288 words&nbsp;·&nbsp;Sukai Huang

Yaqi_xie Translating Natural Language to Planning Goals With Llm 2023

<span title='2023-05-22 12:30:25 +1000 AEST'>May 22, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;142 words&nbsp;·&nbsp;Sukai Huang

Bo_liu Llmp Empowering Large Language Models With Optimal Planning Proficiency 2023

<span title='2023-05-22 11:56:15 +1000 AEST'>May 22, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;251 words&nbsp;·&nbsp;Sukai Huang

Siyu_yuan Distilling Script Knowledge From Large Language Models for Constrainted Language Planning 2023

<span title='2023-05-22 11:31:39 +1000 AEST'>May 22, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;304 words&nbsp;·&nbsp;Sukai Huang

Junnan_li BLIP Bootstrapping Language Image Pre Training for Unified Vision Language Understanding and Generation 2022

<span title='2023-05-22 11:17:28 +1000 AEST'>May 22, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;240 words&nbsp;·&nbsp;Sukai Huang

Harsh_jhamtani Natural Language Decomposition and Interpretation of Complex Utterances 2023

<span title='2023-05-22 09:54:04 +1000 AEST'>May 22, 2023</span>&nbsp;·&nbsp;10 min&nbsp;·&nbsp;2088 words&nbsp;·&nbsp;Sukai Huang

Alexander_kirillov Segment Anything 2023

<span title='2023-05-21 11:56:54 +1000 AEST'>May 21, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;356 words&nbsp;·&nbsp;Sukai Huang

Rohit_gridhar Imagebind One Embedding Space to Bind Them All 2023

<span title='2023-05-15 15:06:48 +1000 AEST'>May 15, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;235 words&nbsp;·&nbsp;Sukai Huang

15 May – 21 May, 2023

<span title='2023-05-15 10:56:05 +1000 AEST'>May 15, 2023</span>&nbsp;·&nbsp;14 min&nbsp;·&nbsp;Sukai Huang

April  6

10 Apr – 16 Apr, 2023

<span title='2023-04-12 10:24:37 +0800 +0800'>April 12, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

Qinghao_hitea Hierarchical Temporal Aware Video Language Pre Training 2022

<span title='2023-04-06 10:02:22 +0800 +0800'>April 6, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;411 words&nbsp;·&nbsp;Sukai Huang

Jacob_andreas Guiding Pretraining in Reinforcement Learning With Llms 2023

<span title='2023-04-05 10:02:24 +0800 +0800'>April 5, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;298 words&nbsp;·&nbsp;Sukai Huang

Luke_zettlemoyer Scaling Expert Language Models With Unsupervised Domain Discovery 2023

<span title='2023-04-03 15:25:01 +0800 +0800'>April 3, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;161 words&nbsp;·&nbsp;Sukai Huang

Xuanting_chen How Robust Is GPT 3.5 to Predecessors a Comprehensive Study on Language Understanding Tasks

<span title='2023-04-03 15:00:57 +0800 +0800'>April 3, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;409 words&nbsp;·&nbsp;Sukai Huang

Anthony_liu a Picture Is Worth a Thousand Words Language Models Plan From Pixels 2023

<span title='2023-04-03 11:28:43 +0800 +0800'>April 3, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;359 words&nbsp;·&nbsp;Sukai Huang

March  19

Wenlong_huang Grounded Decoding Guiding Text Generation With Grounded Models for Robot Control 2023

<span title='2023-03-30 23:45:18 +0800 +0800'>March 30, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;229 words&nbsp;·&nbsp;Sukai Huang

Mariana_learning Generative Models With Goal Conditioned Reinforcement Learning 2023

<span title='2023-03-30 21:20:31 +0800 +0800'>March 30, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;325 words&nbsp;·&nbsp;Sukai Huang

Itsugun_cho Deep Rl With Hierarchical Action Exploration for Dialogue Generation 2023

<span title='2023-03-30 15:01:16 +0800 +0800'>March 30, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;358 words&nbsp;·&nbsp;Sukai Huang

Theodore_r_sumers How to Talk So Ai Will Learn 2022

<span title='2023-03-15 21:09:32 +0800 +0800'>March 15, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;591 words&nbsp;·&nbsp;Sukai Huang

12 Mar – 18 Mar, 2023

<span title='2023-03-10 18:12:42 +1100 AEDT'>March 10, 2023</span>&nbsp;·&nbsp;6 min&nbsp;·&nbsp;Sukai Huang

Cheng_chi Diffusion Policy Visuomotor Policy Learning via Action Diffusion 2023

<span title='2023-03-09 19:36:17 +1100 AEDT'>March 9, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;205 words&nbsp;·&nbsp;Sukai Huang

Alan_lindsay Framer Planning Models From Natural Language Action Descriptions 2017

<span title='2023-03-09 19:28:47 +1100 AEDT'>March 9, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;482 words&nbsp;·&nbsp;Sukai Huang

01 Mar – 11 Mar, 2023

<span title='2023-03-06 14:43:14 +1100 AEDT'>March 6, 2023</span>&nbsp;·&nbsp;8 min&nbsp;·&nbsp;Sukai Huang

Siddharth_karamcheti Language Driven Representation Learning for Robotics 2023

<span title='2023-03-03 16:16:19 +1100 AEDT'>March 3, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;463 words&nbsp;·&nbsp;Sukai Huang

Tatsuki_kuribayashi Does Vision Accelerate Hierarchical Generalisation of Neural Language Learners 2023

<span title='2023-03-03 15:26:55 +1100 AEDT'>March 3, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;111 words&nbsp;·&nbsp;Sukai Huang

Jing_cheng_pang Natural Language Conditioned Reinforcement Learning With Inside Out Task Language Development and Translation 2023

<span title='2023-03-03 15:19:43 +1100 AEDT'>March 3, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;173 words&nbsp;·&nbsp;Sukai Huang

Suvaansh_bhambri Multi Level Compositional Reasoning for Interactive Instruction Following 2023

<span title='2023-03-03 11:17:01 +1100 AEDT'>March 3, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;144 words&nbsp;·&nbsp;Sukai Huang

Tianjun_zhang the Wisdom of Hindsight Makes Language Models Better Instruction Followers 2023

<span title='2023-03-02 19:06:35 +1100 AEDT'>March 2, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;427 words&nbsp;·&nbsp;Sukai Huang

Ying_shen Learning by Asking for Embodied Visual Navigation and Task Completion 2023

<span title='2023-03-02 17:51:02 +1100 AEDT'>March 2, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;411 words&nbsp;·&nbsp;Sukai Huang

Ernest_davis Benchmarks for Automated Commonsense Reasoning a Survey 2023

<span title='2023-03-02 15:22:51 +1100 AEDT'>March 2, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;573 words&nbsp;·&nbsp;Sukai Huang

Alexander_nikulin Anti Exploration by Random Network Distillation 2023

<span title='2023-03-01 22:14:11 +1100 AEDT'>March 1, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;359 words&nbsp;·&nbsp;Sukai Huang

Edoardo_cetin Learning Pessimism for Reinforcement Learning 2023

<span title='2023-03-01 21:02:25 +1100 AEDT'>March 1, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;222 words&nbsp;·&nbsp;Sukai Huang

Timo_schick Toolformer Language Models Can Teach Themselves to Use Tools 2023

<span title='2023-03-01 19:57:49 +1100 AEDT'>March 1, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;486 words&nbsp;·&nbsp;Sukai Huang

Almog_gueta Knowledge Is a Region in Weight Space for Fine Tuned Language Model 2023

<span title='2023-03-01 12:45:54 +1100 AEDT'>March 1, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;548 words&nbsp;·&nbsp;Sukai Huang

February  13

12 Feb – 28 Feb, 2023

<span title='2023-02-12 09:53:46 +1100 AEDT'>February 12, 2023</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;Sukai Huang

Xiwen_liang Contrastive Instruction Trajectory Learning for Vision Language Navigation 2022

<span title='2023-02-10 02:51:23 +1100 AEDT'>February 10, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;360 words&nbsp;·&nbsp;Sukai Huang

Jacob_andreas Lammp Language Models as Probabilistic Priors for Perception and Action 2023

<span title='2023-02-10 00:46:15 +1100 AEDT'>February 10, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;267 words&nbsp;·&nbsp;Sukai Huang

Zhuosheng_zhang Multimodal Chain of Thought Reasoning in Language Models 2023

<span title='2023-02-08 22:23:45 +1100 AEDT'>February 8, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;548 words&nbsp;·&nbsp;Sukai Huang

Siyuan_wang Unifying Structure Reasoning and Language Model Pre Training for Complex Reasoning 2023

<span title='2023-02-08 22:17:31 +1100 AEDT'>February 8, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;281 words&nbsp;·&nbsp;Sukai Huang

Ekin_akyurek Towards Tracing Factual Knowledge in Language Models Back to the Training Data 2022

<span title='2023-02-08 22:16:28 +1100 AEDT'>February 8, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;363 words&nbsp;·&nbsp;Sukai Huang

Danijar_hafner Mastering Diverse Domains Through World Models 2023

<span title='2023-02-07 18:18:37 +1100 AEDT'>February 7, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;291 words&nbsp;·&nbsp;Sukai Huang

Yuanhan_zhang What Makes Good Examples for Visual in Context Learning 2023

<span title='2023-02-06 22:38:35 +1100 AEDT'>February 6, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;427 words&nbsp;·&nbsp;Sukai Huang

Jing_yu_koh Grounding Language Models to Images for Multimodal Generation 2023

<span title='2023-02-06 22:37:53 +1100 AEDT'>February 6, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;239 words&nbsp;·&nbsp;Sukai Huang

Zhenfang_chen See Think Confirm Interactive Prompting Between Vision and Language Models for Knowledge Based Visual Reasoning 2023

<span title='2023-02-06 22:36:41 +1100 AEDT'>February 6, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;405 words&nbsp;·&nbsp;Sukai Huang

Xiaotian_liu a Planning Based Neural Symbolic Approach for Embodied Instruction Following 2022

<span title='2023-02-02 13:28:19 +1100 AEDT'>February 2, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;226 words&nbsp;·&nbsp;Sukai Huang

So_yeon_min Film Following Instructions in Language With Modular Methods 2022

<span title='2023-02-01 18:32:24 +1100 AEDT'>February 1, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;430 words&nbsp;·&nbsp;Sukai Huang

Yuki_inoue Prompter Utilizing Large Language Model Prompting for a Data Efficient Embodied Instruction Following 2022

<span title='2023-02-01 17:22:35 +1100 AEDT'>February 1, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;526 words&nbsp;·&nbsp;Sukai Huang

January  5

Kyle_mahowald Dissociating Language and Thought in Large Language Models a Cognitive Perspective 2023

<span title='2023-01-31 18:47:45 +1100 AEDT'>January 31, 2023</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;776 words&nbsp;·&nbsp;Sukai Huang

Michael_janner Planning With Diffusion for Flexible Behaviour Synthesis 2022

<span title='2023-01-30 13:43:20 +1100 AEDT'>January 30, 2023</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;317 words&nbsp;·&nbsp;Sukai Huang

01 Feb – 11 Feb, 2023

<span title='2023-01-29 23:15:54 +1100 AEDT'>January 29, 2023</span>&nbsp;·&nbsp;7 min&nbsp;·&nbsp;Sukai Huang

Shailaja_keyur_sampat Reasoning About Actions Over Visual and Linguistic Modalities a Survey 2022

<span title='2023-01-20 13:59:00 +1100 AEDT'>January 20, 2023</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;524 words&nbsp;·&nbsp;Sukai Huang

Xin_wang Reinforced Cross Modal Matching and Self Supervised Imitation Learning for Vision Language Navigation 2019

<span title='2023-01-18 09:48:14 +1100 AEDT'>January 18, 2023</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;195 words&nbsp;·&nbsp;Sukai Huang

2022  104

December  26

Alekh_agarwal PC-PG Policy Cover Directed Exploration for Provable Policy Gradient Learning 2020

<span title='2022-12-28 14:39:25 +1100 AEDT'>December 28, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;271 words&nbsp;·&nbsp;Sukai Huang

Alekh_agarwal on the Theory of Policy Gradient Methods Optimality Approximation and Distribution Shift 2020

<span title='2022-12-28 14:36:20 +1100 AEDT'>December 28, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;557 words&nbsp;·&nbsp;Sukai Huang

Chloe_ching_yun_hsu Revisiting Design Choices in Proximal Policy Optimisation 2020

<span title='2022-12-28 14:32:15 +1100 AEDT'>December 28, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;467 words&nbsp;·&nbsp;Sukai Huang

James_queeney Generalized Proximal Policy Optimisation With Sample Reuse 2021

<span title='2022-12-28 14:00:32 +1100 AEDT'>December 28, 2022</span>&nbsp;·&nbsp;5 min&nbsp;·&nbsp;1033 words&nbsp;·&nbsp;Sukai Huang

Lun_wang Backdoorl Backdoor Attack Against Competitive Reinforcement Learning 2021

<span title='2022-12-28 03:57:59 +1100 AEDT'>December 28, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;202 words&nbsp;·&nbsp;Sukai Huang

Sandy_huang Adversarial Attacks on Neural Network Policies 2017

<span title='2022-12-28 00:08:22 +1100 AEDT'>December 28, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;346 words&nbsp;·&nbsp;Sukai Huang

Yinglun_xu Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning 2022

<span title='2022-12-27 23:14:19 +1100 AEDT'>December 27, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;302 words&nbsp;·&nbsp;Sukai Huang

Young_wu Reward Poisoning Attacks on Offline Multi Agent Reinforcement Learning 2022

<span title='2022-12-27 22:50:14 +1100 AEDT'>December 27, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;146 words&nbsp;·&nbsp;Sukai Huang

Xuezhou_zhang Robust Policy Gradient Against Strong Data Corruption 2021

<span title='2022-12-27 20:35:10 +1100 AEDT'>December 27, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;317 words&nbsp;·&nbsp;Sukai Huang

Kiarash_banihashem Defense Against Reward Poisoning Attacks in Reinforcement Learning 2021

<span title='2022-12-27 18:27:17 +1100 AEDT'>December 27, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;303 words&nbsp;·&nbsp;Sukai Huang

Amin_rakhsha Reward Poisoning in Reinforcement Learning Attacks Against Unknown Learners in Unknown Environments 2021

<span title='2022-12-27 15:50:22 +1100 AEDT'>December 27, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;233 words&nbsp;·&nbsp;Sukai Huang

Xuezhou_zhang Adaptive Reward Poisoning Attacks Against Reinforcement Learning 2020

<span title='2022-12-27 00:21:15 +1100 AEDT'>December 27, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;283 words&nbsp;·&nbsp;Sukai Huang

Anindya_sarkar Reward Delay Attacks on Deep Reinforcement Learning 2022

<span title='2022-12-26 21:07:03 +1100 AEDT'>December 26, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;374 words&nbsp;·&nbsp;Sukai Huang

Proximal Policy Optimisation Explained Blog

<span title='2022-12-26 19:50:35 +1100 AEDT'>December 26, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;196 words&nbsp;·&nbsp;Sukai Huang

Tom_everitt Reinforcement Learning With a Corrupted Reward Channel 2017

<span title='2022-12-26 01:11:23 +1100 AEDT'>December 26, 2022</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;757 words&nbsp;·&nbsp;Sukai Huang

Yunhan_huang Manipulating Reinforcement Learning Stealthy Attacks on Cost Signals 2020

<span title='2022-12-25 19:12:17 +1100 AEDT'>December 25, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;336 words&nbsp;·&nbsp;Sukai Huang

Vincent_zhuang No Regret Reinforcement Learning With Heavy Tailed Rewards 2021

<span title='2022-12-25 18:15:53 +1100 AEDT'>December 25, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;225 words&nbsp;·&nbsp;Sukai Huang

Wenshuai_zhao Towards Closing the Sim to Real Gap in Collaborative Multi Robot Deep Reinforcement Learning 2020

<span title='2022-12-25 16:54:11 +1100 AEDT'>December 25, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;365 words&nbsp;·&nbsp;Sukai Huang

Jan_corazza Reinforcement Learning With Stochastic Reward Machines 2022

<span title='2022-12-24 22:36:07 +1100 AEDT'>December 24, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;465 words&nbsp;·&nbsp;Sukai Huang

Oguzhan_dogru Reinforcement Learning With Constrained Uncertain Reward Function Through Particle Filtering 2022

<span title='2022-12-24 19:32:25 +1100 AEDT'>December 24, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;297 words&nbsp;·&nbsp;Sukai Huang

Inaam_ilahi Challenges and Countermeasures for Adversarial Attacks on Reinforcement Learning 2022

<span title='2022-12-24 17:06:12 +1100 AEDT'>December 24, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;517 words&nbsp;·&nbsp;Sukai Huang

Zuxin_liu on the Robustness of Safe Reinforcement Learning Under Observational Perturbations 2022

<span title='2022-12-22 22:38:13 +1100 AEDT'>December 22, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;532 words&nbsp;·&nbsp;Sukai Huang

Ruben_majadas Disturbing Reinforcement Learning Agents With Corrupted Rewards 2021

<span title='2022-12-17 00:38:35 +1100 AEDT'>December 17, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;383 words&nbsp;·&nbsp;Sukai Huang

Jingkang_wang Reinforcement Learning With Perturbed Rewards 2020

<span title='2022-12-16 20:48:51 +1100 AEDT'>December 16, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;402 words&nbsp;·&nbsp;Sukai Huang

1 Dec – 31 Dec, 2022

<span title='2022-12-16 19:25:59 +1100 AEDT'>December 16, 2022</span>&nbsp;·&nbsp;7 min&nbsp;·&nbsp;Sukai Huang

Jacob_andreas Language Models as Agent Models 2022

<span title='2022-12-10 00:47:33 +1100 AEDT'>December 10, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;639 words&nbsp;·&nbsp;Sukai Huang

November  7

Charlie_snell Context Aware Language Modeling for Goal Oriented Dialogue Systems 2022

<span title='2022-11-20 16:29:59 +1100 AEDT'>November 20, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;489 words&nbsp;·&nbsp;Sukai Huang

Sanchit_agarwal Building Goal Oriented Dialogue Systems With Situated Visual Context 2021

<span title='2022-11-20 16:29:14 +1100 AEDT'>November 20, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;211 words&nbsp;·&nbsp;Sukai Huang

Yichi_zhang Danli Deliberative Agent for Following Natural Language Instructions 2022

<span title='2022-11-20 16:28:23 +1100 AEDT'>November 20, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;343 words&nbsp;·&nbsp;Sukai Huang

Xiang_li Diffusion-LM Improves Controllable Text Generation 2022

<span title='2022-11-14 16:32:31 +1100 AEDT'>November 14, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;104 words&nbsp;·&nbsp;Sukai Huang

Consider incremental publication of results Nov, 2022

<span title='2022-11-13 15:59:12 +1100 AEDT'>November 13, 2022</span>&nbsp;·&nbsp;7 min&nbsp;·&nbsp;Sukai Huang

Jie_huang Can Language Models Be Specific How 2022

<span title='2022-11-08 20:41:04 +1100 AEDT'>November 8, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;429 words&nbsp;·&nbsp;Sukai Huang

01 Nov – 30 Nov, 2022

<span title='2022-11-02 20:08:39 +1100 AEDT'>November 2, 2022</span>&nbsp;·&nbsp;12 min&nbsp;·&nbsp;Sukai Huang

October  7

Yizhou_zhao Semantic Aligned Fusion Transformer for One Shot Object Detection 2022

<span title='2022-10-24 19:14:34 +1100 AEDT'>October 24, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;67 words&nbsp;·&nbsp;Sukai Huang

Ting_i_hsieh One Shot Object Detection With Co Attention and Co Excitation 2019

<span title='2022-10-24 19:13:10 +1100 AEDT'>October 24, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;158 words&nbsp;·&nbsp;Sukai Huang

Ayan_kumar_bhunia a Deep One Shot Network for Query Based Logo Retrieval 2019

<span title='2022-10-24 19:12:22 +1100 AEDT'>October 24, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;258 words&nbsp;·&nbsp;Sukai Huang

Yuetian_weng an Efficient Spatio Temporal Pyramid Transformer for Action Detection 2022

<span title='2022-10-20 19:06:41 +1100 AEDT'>October 20, 2022</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;649 words&nbsp;·&nbsp;Sukai Huang

Steven_kapturowski Human Level Atari 200x Faster 2022

<span title='2022-10-05 23:22:01 +1100 AEDT'>October 5, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;357 words&nbsp;·&nbsp;Sukai Huang

Andrea_banino Coberl Contrastive Bert for Reinforcement Learning 2022

<span title='2022-10-05 23:04:49 +1100 AEDT'>October 5, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;258 words&nbsp;·&nbsp;Sukai Huang

01 Oct – 31 Oct, 2022

<span title='2022-10-05 19:25:25 +1100 AEDT'>October 5, 2022</span>&nbsp;·&nbsp;8 min&nbsp;·&nbsp;Sukai Huang

September  7

Alex_petrekno Sample Factory Asynchronous Rl at Very High Fps 2020

<span title='2022-09-25 16:34:09 +1000 AEST'>September 25, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;154 words&nbsp;·&nbsp;Sukai Huang

Jonathan_ho Video Diffusion Models 2022

<span title='2022-09-22 20:40:21 +1000 AEST'>September 22, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;471 words&nbsp;·&nbsp;Sukai Huang

Dongwon Fire Burns Sword Cuts Commonsense Inductive Bias for Exploration in Text Based Games 2022

<span title='2022-09-22 19:38:56 +1000 AEST'>September 22, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;276 words&nbsp;·&nbsp;Sukai Huang

Wenlong_huang Language Models as Zero Shot Planners Extracting Actionable Knowledge for Embodied Agents 2022

<span title='2022-09-19 21:55:13 +1000 AEST'>September 19, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;253 words&nbsp;·&nbsp;Sukai Huang

Pengchuan_zhang Vinvl Revisiting Visual Representations in Vision Language Models 2021

<span title='2022-09-03 17:17:47 +1000 AEST'>September 3, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;332 words&nbsp;·&nbsp;Sukai Huang

Xiujun_li Oscar Object Semantic Aligned Pro Training for Vision Language Tasks 2020

<span title='2022-09-03 17:12:54 +1000 AEST'>September 3, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;462 words&nbsp;·&nbsp;Sukai Huang

01 Sep – 30 Sep, 2022

<span title='2022-09-03 16:26:36 +1000 AEST'>September 3, 2022</span>&nbsp;·&nbsp;6 min&nbsp;·&nbsp;Sukai Huang

August  8

Yung_sung_chuang Diffcse Difference Based Contrastive Learning for Sentence Embeddings 2022

<span title='2022-08-27 16:03:42 +1000 AEST'>August 27, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;351 words&nbsp;·&nbsp;Sukai Huang

Gregor_geigle Retrieve Fast Rerank Smart Cooperative and Joint Approaches for Improved Cross Modal Retrieval 2022

<span title='2022-08-27 00:31:38 +1000 AEST'>August 27, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;453 words&nbsp;·&nbsp;Sukai Huang

Kaitao_song Mpnet Masked and Permuted Retrain for Language Understanding 2020

<span title='2022-08-25 12:24:55 +1000 AEST'>August 25, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;378 words&nbsp;·&nbsp;Sukai Huang

Sergios_karagiannakos Vision Language Models Towards Multimodal Dl 2022

<span title='2022-08-09 07:37:30 +1000 AEST'>August 9, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;24 words&nbsp;·&nbsp;Sukai Huang

Jiali_duan Multimodal Alignment Using Representation Codebook 2022

<span title='2022-08-09 07:26:46 +1000 AEST'>August 9, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;513 words&nbsp;·&nbsp;Sukai Huang

07 Aug – 31 Aug, 2022

<span title='2022-08-08 17:40:55 +1000 AEST'>August 8, 2022</span>&nbsp;·&nbsp;5 min&nbsp;·&nbsp;Sukai Huang

A preliminary idea about using instruction following as a intermediate training step towards a general learning-based agent

<span title='2022-08-07 17:17:07 +1000 AEST'>August 7, 2022</span>&nbsp;·&nbsp;5 min&nbsp;·&nbsp;Sukai Huang

Supplementary explanations for proposed methods and PhD thesis structure

<span title='2022-08-04 12:59:17 +1000 AEST'>August 4, 2022</span>&nbsp;·&nbsp;11 min&nbsp;·&nbsp;Sukai Huang

July  1

Younggyo_seo Masked World Models for Visual Control 2022

<span title='2022-07-01 12:03:57 +1000 AEST'>July 1, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;227 words&nbsp;·&nbsp;Sukai Huang

June  4

19 Jun – 25 Jun, 2022

<span title='2022-06-19 23:28:00 +1000 AEST'>June 19, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

12 Jun – 18 Jun, 2022

<span title='2022-06-09 12:39:31 +1000 AEST'>June 9, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

05 Jun – 11 Jun, 2022

<span title='2022-06-02 13:41:59 +1000 AEST'>June 2, 2022</span>&nbsp;·&nbsp;13 min&nbsp;·&nbsp;Sukai Huang

A Brief Overview of Rank Based Prioritized Experience Replay 2016

<span title='2022-06-02 11:47:17 +1000 AEST'>June 2, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;365 words&nbsp;·&nbsp;Sukai Huang

May  4

29 May – 04 Jun, 2022

<span title='2022-05-30 14:47:30 +1000 AEST'>May 30, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

22 May – 28 May, 2022

<span title='2022-05-25 20:15:27 +1000 AEST'>May 25, 2022</span>&nbsp;·&nbsp;6 min&nbsp;·&nbsp;Sukai Huang

15 May – 21 May, 2022

<span title='2022-05-18 15:52:30 +1000 AEST'>May 18, 2022</span>&nbsp;·&nbsp;8 min&nbsp;·&nbsp;Sukai Huang

Deepmind Flamingo a Visual Language Model for Few Shot Learning 2022

<span title='2022-05-11 16:35:03 +1000 AEST'>May 11, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

April  4

Angela_fan Augmenting Transformer With Knn Composite Memory for Dialog 2021

<span title='2022-04-21 11:01:14 +1000 AEST'>April 21, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

17 April – 23 April, 2022

<span title='2022-04-18 18:05:46 +1000 AEST'>April 18, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

Hao_hu Generalisable Episodic Memory for Drl 2021

<span title='2022-04-07 12:12:20 +1000 AEST'>April 7, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

03 April – 09 April, 2022

<span title='2022-04-05 11:43:54 +1000 AEST'>April 5, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

March  17

Ilya_kostrikov Offline Rl With Implicit Q Learning 2021

<span title='2022-03-22 19:01:49 +1100 AEDT'>March 22, 2022</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;Sukai Huang

Qinqing_zheng Online Decision Transformer 2022

<span title='2022-03-21 21:56:45 +1100 AEDT'>March 21, 2022</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;Sukai Huang

Sebastian_borgeaud Improving Language Models by Retrieving From Trillions of Tokens 2022

<span title='2022-03-21 19:07:36 +1100 AEDT'>March 21, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

20 March – 2 April, 2022

<span title='2022-03-21 14:29:31 +1100 AEDT'>March 21, 2022</span>&nbsp;·&nbsp;8 min&nbsp;·&nbsp;Sukai Huang

Machel_reid Can Wikipedia Help Offline Rl 2022

<span title='2022-03-16 21:18:24 +1100 AEDT'>March 16, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

Stephen_cresswell Generalised Domain Model Acquisition From Action Traces 2013

<span title='2022-03-15 16:34:45 +1100 AEDT'>March 15, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

Wenfeng_feng Extracting Action Sequences From Texts by Rl

<span title='2022-03-15 14:40:38 +1100 AEDT'>March 15, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

Shivam_miglani Nltopddl Learning From Nlp Manuals 2020

<span title='2022-03-14 15:08:45 +1100 AEDT'>March 14, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

13 March – 19 March, 2022

<span title='2022-03-14 14:29:03 +1100 AEDT'>March 14, 2022</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;Sukai Huang

Linear Temporal Logic

<span title='2022-03-10 12:36:26 +1100 AEDT'>March 10, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

Giuseppe_de_giacomo Foundations for Retraining Bolts Rl With Ltl 2019

<span title='2022-03-04 12:12:57 +1100 AEDT'>March 4, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

Joseph_kim Collaborative Planning With Encoding of High Level Strategies 2017

<span title='2022-03-04 12:12:27 +1100 AEDT'>March 4, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

Mikayel_samvelyan Minihack the Planet a Sandbox for Open Ended Rl Research 2021

<span title='2022-03-04 12:11:55 +1100 AEDT'>March 4, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

06 March – 12 March 2022

<span title='2022-03-04 11:32:45 +1100 AEDT'>March 4, 2022</span>&nbsp;·&nbsp;5 min&nbsp;·&nbsp;Sukai Huang

Richard_shin Constrained Language Models Yield Few Shot Semantic Parsers 2021

<span title='2022-03-02 00:19:18 +1100 AEDT'>March 2, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

Heinrich_kuttler the Nethack Learning Environment 2020

<span title='2022-03-02 00:18:35 +1100 AEDT'>March 2, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

Pashootan_vaezipoor Ltl2action Generalising Ltl Instructions for Multi Task Rl 2021

<span title='2022-03-01 20:53:10 +1100 AEDT'>March 1, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

February  8

Roma_patel Learning to Ground Language Temporal Logical Form 2019

<span title='2022-02-28 21:40:53 +1100 AEDT'>February 28, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

Thang_m_pham Out of Order How Important Is the Sequential Order of Words in a Sentence in Natural Language Understanding Tasks 2021

<span title='2022-02-28 18:58:52 +1100 AEDT'>February 28, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

Anton_belyy Guided K Best Selection for Semantic Parsing Annotation 2021

<span title='2022-02-23 19:42:39 +1100 AEDT'>February 23, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

20 February – 5 March, 2022

<span title='2022-02-18 14:52:59 +1100 AEDT'>February 18, 2022</span>&nbsp;·&nbsp;8 min&nbsp;·&nbsp;Sukai Huang

13 February – 19 February, 2022

<span title='2022-02-16 15:27:05 +1100 AEDT'>February 16, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

S_teufel Argumentative Zoning 2000

<span title='2022-02-16 14:40:57 +1100 AEDT'>February 16, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

Jacob_andreas Compositionality as Lexical Symmetry 2022

<span title='2022-02-08 14:20:19 +1100 AEDT'>February 8, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

06 February – 12 February, 2022

<span title='2022-02-06 18:40:28 +1100 AEDT'>February 6, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

January  11

23 January – 29 January, 2022

<span title='2022-01-25 12:36:30 +1100 AEDT'>January 25, 2022</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;Sukai Huang

Pytorch Notes

<span title='2022-01-19 21:01:49 +1100 AEDT'>January 19, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

16 January – 22 January, 2022

<span title='2022-01-19 21:01:40 +1100 AEDT'>January 19, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

Tao_lei When Attention Meets Fast Recurrence Training Language Models With Reduced Compute 2021

<span title='2022-01-14 00:26:37 +1100 AEDT'>January 14, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

Alex_nichol Glide Towards Photorealistic Image Generation and Editing With Text Guided Diffusion Models 2021

<span title='2022-01-12 16:54:01 +1100 AEDT'>January 12, 2022</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

Junyang_lin M6 a Chinese Multimodal Pretrainer 2021

<span title='2022-01-12 13:38:14 +1100 AEDT'>January 12, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

Swin Transformer

<span title='2022-01-08 20:34:41 +1100 AEDT'>January 8, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

09 January – 15 January, 2022

<span title='2022-01-07 22:20:48 +1100 AEDT'>January 7, 2022</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

Tianshi_cao Babyai Plus Plus Towards Grounded Language Learning Beyond Memorization 2020

<span title='2022-01-03 22:38:40 +1100 AEDT'>January 3, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

Federico_bianchi Language in a Search Box Grounding Language Learning in Real World Human Machine Interaction 2021

<span title='2022-01-03 16:51:39 +1100 AEDT'>January 3, 2022</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

02 January – 08 January, 2022

<span title='2022-01-01 17:07:59 +1100 AEDT'>January 1, 2022</span>&nbsp;·&nbsp;5 min&nbsp;·&nbsp;Sukai Huang

2021  26

December  20

Modular Reinforcement Learning Details

<span title='2021-12-26 17:11:34 +1100 AEDT'>December 26, 2021</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;Sukai Huang

Lili_chen Decision Transformer Reinforcement Learning via Sequence Modeling 2021

<span title='2021-12-24 23:29:49 +1100 AEDT'>December 24, 2021</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

Jiayuan_mao Grammar Based Grounded Lexicon Learning 2021

<span title='2021-12-22 17:22:15 +1100 AEDT'>December 22, 2021</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

Julia_kiseleva Interactive Grounded Language Understanding in a Collaborative Environment 2021

<span title='2021-12-22 15:10:56 +1100 AEDT'>December 22, 2021</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

19 December – 31 December, 2021

<span title='2021-12-20 19:26:40 +1100 AEDT'>December 20, 2021</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;Sukai Huang

Dominik_drexler Expressing and Exploiting the Common Subgoal Structure of Classical Planning Domains Using Sketches 2021

<span title='2021-12-17 13:07:53 +1100 AEDT'>December 17, 2021</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

12 DECEMBER – 18 DECEMBER, 2021 Supplementary Notes

<span title='2021-12-16 18:07:25 +1100 AEDT'>December 16, 2021</span>&nbsp;·&nbsp;5 min&nbsp;·&nbsp;Sukai Huang

Yiding_jiang Language as Abstraction for Hierarchical Deep Reinforcement Learning

<span title='2021-12-15 19:49:28 +1100 AEDT'>December 15, 2021</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

Hengyuan_hu Hierarchical Decision Making by Generating and Following Natural Language Instructions 2019

<span title='2021-12-15 13:11:05 +1100 AEDT'>December 15, 2021</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

David_ding Attention Over Learned Object Embeddings Enables Complex Visual Reasoning 2021

<span title='2021-12-15 12:59:07 +1100 AEDT'>December 15, 2021</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

Jacob_andreas Modular Multitask Reinforcement Learning With Policy Sketches 2017

<span title='2021-12-13 17:23:12 +1100 AEDT'>December 13, 2021</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

Research Guides

<span title='2021-12-12 14:06:19 +1100 AEDT'>December 12, 2021</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

12 December – 18 December, 2021

<span title='2021-12-10 13:59:41 +1100 AEDT'>December 10, 2021</span>&nbsp;·&nbsp;12 min&nbsp;·&nbsp;Sukai Huang

Iglu Neurips 2021 Workshop

<span title='2021-12-10 06:18:31 +1100 AEDT'>December 10, 2021</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

Interesting Tutorial Slides in Neurips 2021

<span title='2021-12-08 17:14:57 +1100 AEDT'>December 8, 2021</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

Environment deployment Notes

<span title='2021-12-06 20:13:12 +1100 AEDT'>December 6, 2021</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;Sukai Huang

Docker Notes

<span title='2021-12-05 20:40:59 +1100 AEDT'>December 5, 2021</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

David_abel on the Expressivity of Markov Reward 2021

<span title='2021-12-05 12:02:23 +1100 AEDT'>December 5, 2021</span>&nbsp;·&nbsp;5 min&nbsp;·&nbsp;Sukai Huang

05 December – 11 December, 2021

<span title='2021-12-05 10:48:45 +1100 AEDT'>December 5, 2021</span>&nbsp;·&nbsp;6 min&nbsp;·&nbsp;Sukai Huang

Rishabh_agarwal Deep Reinforcement Learning at the Edge of the Stats Precipice 2021

<span title='2021-12-03 19:50:10 +1100 AEDT'>December 3, 2021</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang

November  6

Borja_ibarz Reward Learning From Human Preferences and Demonstrations in Atari 2018

<span title='2021-11-27 19:14:04 +1100 AEDT'>November 27, 2021</span>&nbsp;·&nbsp;2 min&nbsp;·&nbsp;Sukai Huang

Adrien_ecoffet Go Explore a New Approach for Hard Exploration Problems 2021 Paper Review

<span title='2021-11-27 18:58:32 +1100 AEDT'>November 27, 2021</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;Sukai Huang

Tuomas_haarnoja Soft Actor Critic Off Policy Maximum Entropy Deep Reinforcement Learning With a Stochastic Actor 2018 Paper Review

<span title='2021-11-18 12:08:53 +1100 AEDT'>November 18, 2021</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;Sukai Huang

Adria Badia Agent57 Outperforming the Atari Human Benchmark 2020 Paper Review

<span title='2021-11-18 12:05:47 +1100 AEDT'>November 18, 2021</span>&nbsp;·&nbsp;5 min&nbsp;·&nbsp;Sukai Huang

Stefan O Toole Width Based Lookaheads With Learnt Base Policies and Heuristics Over the Atari 2600 Benchmark 2021 Paper Reivew

<span title='2021-11-16 17:40:10 +1100 AEDT'>November 16, 2021</span>&nbsp;·&nbsp;4 min&nbsp;·&nbsp;Sukai Huang

Cristian Paul Bara Mindcraft Theory of Mind Modelling 2021 Paper Review

<span title='2021-11-12 12:56:24 +1100 AEDT'>November 12, 2021</span>&nbsp;·&nbsp;3 min&nbsp;·&nbsp;Sukai Huang