Zachary Pangan

D2 Student at Nara Institute of Science and Technology (NAIST)
Social Computing Lab

[Zachary Pangan @ZacharyPangan]

"We're fickle, stupid beings with poor memories and a great gift for self-destruction."
- Plutarch Heavensbee, Mockingjay

[Zachary Pangan @ZacharyPangan]

@summersnow_0826 It means that you're learning and growing!

[Nick Dobos @NickADobos]

A collection and survey of over 180 LLm based agents! This is gonna be a fun list to dig into. Very cool to see common patterns starting to emerge

[IC2S2 @IC2S2]

**Tutorials' day**
Room H 0900 - 1230: "Creating multiplayer, interactive online experiments with Empirica" with Mohammed Alsobay @malsobay, and James Houghton

[AK @_akhaliq]

Learning to Model the World with Language

paper page: https://t.co/jYjQnqEJAR

To interact with humans in the world, agents need to understand the diverse types of language that people use, relate them to the visual world, and act based on them. While current agents learn to execute simple language instructions from task rewards, we aim to build agents that leverage diverse language that conveys general knowledge, describes the state of the world, provides interactive feedback, and more. Our key idea is that language helps agents predict the future: what will be observed, how the world will behave, and which situations will be rewarded. This perspective unifies language understanding with future prediction as a powerful self-supervised learning objective. We present Dynalang, an agent that learns a multimodal world model that predicts future text and image representations and learns to act from imagined model rollouts. Unlike traditional agents that use language only to predict actions, Dynalang acquires rich language understanding by using past language also to predict future language, video, and rewards. In addition to learning from online interaction in an environment, Dynalang can be pretrained on datasets of text, video, or both without actions or rewards. From using language hints in grid worlds to navigating photorealistic scans of homes, Dynalang utilizes diverse types of language to improve task performance, including environment descriptions, game rules, and instructions.

[Zachary Pangan @ZacharyPangan]

So glad to have been able to present my current research in IC2S2 at Copenhagen, Denmark.

Presenting in my Slytherin necktie for confidence 🐍🙌

[Anders Giovanni Møller @AndersGiovanni]

Hacked together a little @IC2S2 #IC2S2 dashboard! 📊 Key metrics & infographics, straight from the crossroads of social and computational science, are now at your fingertips. 🌍✌🏼
https://t.co/SoLTkRf9s4

[Zachary Pangan @ZacharyPangan]

@summersnow_0826 kaso sa school ka nakatira 😅🫣

[Zachary Pangan @ZacharyPangan]

@fwjole Aabot sa paskuhan? Lakas 💪😅

[Zachary Pangan @ZacharyPangan]

@fwjole Awow

[Zachary Pangan @ZacharyPangan]

@johnmariomag @gareththeworld @imjohngo kailangan maglakad ng 20 minutes to get to a train station and 5 minutes to get to a bus station (and wait longer for the bus) here in japan, bud 🙃 the sidewalks are wide tho 👌

[Zachary Pangan @ZacharyPangan]

@fwjole parang di naman totoo hahaha

[Zachary Pangan @ZacharyPangan]

@HeavenCamacam I’ll bake one for you the next time we meet, Hevs!!!

[Zachary Pangan @ZacharyPangan]

@HeavenCamacam 5K Php dito ang full tank hevs 🙃

[Zachary Pangan @ZacharyPangan]

@viannedanielle wala ata sa vocab mo ang “SHY” 0.0 boooorj g na 👌💪

[Zachary Pangan @ZacharyPangan]

@viannedanielle congraaaaats! boooorj ang lakas 💪

[Zachary Pangan @ZacharyPangan]

@gablucero_ even doc tricia 😍💪👌

[Tricia Robredo @jpgrobredo]

Not a hot take. Just a Top Gun Maverick appreciation tweet. 🫣

[Zachary Pangan @ZacharyPangan]

@skylark13_ saaame haha! now entering: safe zone 😅

[Zachary Pangan @ZacharyPangan]

@HeavenCamacam wahahahaha don’t fall into that trap 😂 hohohoh go hevs 😅

[Zachary Pangan @ZacharyPangan]

@crstlluciano ipanalo na10 ang Pilipino 💪

[Zachary Pangan @ZacharyPangan]

@jariocampo deserb