Ayush Mangal
  • About
  • Publications
  • Projects
  • Videos
  • Blog
  • Blog
    • Do it for the plot
    • ADHD on a train ride
    • A long walk to work
    • Book Notes : Foundation By Issac Asimov
    • Book Notes: Anxious Generation
    • Clarity
    • Wake up to reality
    • Being the human behind an AI
    • Occupational Hazards
    • Stuck
    • Ye shalt shut up and doth ye work
    • Fluid/Self
    • Smart enough?
    • FLARE — “Advanced” RAG implemented from scratch
    • A hacky minimal Tree of Thoughts implementation
    • Keeping up with ML
    • Creating an AMA bot for my personal website using LLMs
    • Leap of Faith
    • On being alone
    • RL with diffusion — I
    • Consuming Vs Creating
    • Trusting the process OR asking the control freak inside you to STFU
    • Life’s a Blur
    • Context switching like my brain is a fucking CPU
    • Living on Curiosity
    • Why I don’t want to let go of being “a child”
    • WORK, WORk, WOrk, Work, work…..why?
    • So….what are your hobbies?
    • The Man with(out) a Plan
    • How the law of diminishing marginal utility messes with our happiness
    • The DFS vs BFS way of living your life
    • The one due to my insomnia
    • How often do we try to actually understand stuff?
    • An honest review of (metaphorically) living under a rock
    • How brittle is your happiness?
    • Let’s talk about randomness
    • Why do we ( I )find doing nothing, harder than doing something?
    • How I would like to experience music in the future?
    • What doing research as an undergrad can teach you
    • The Exploration Vs Exploitation Dilemma in RL
    • Cool products that I would love (someone) to make if they don’t exist yet :P
    • Please don’t let them find out I am just an imposter!
    • Why the Hell do Companies even Hire an Intern?
    • The Side Effects of Being Studious
    • What I learnt from my love-hate relationship with Social Media
    • Ah Shit, Here We Go Again!
    • Some shit I randomly thought up :P
  • Projects
  • Projects
    • Advanced RAG - FLARE
    • Tree of Thoughts
    • DDPM Jax
    • DDPM Pytorch
    • Kandinsky 2.1, Diffusers
    • BLIP-Diffusion, Diffusers
    • Consistency Models, Diffusers
    • ADDA
    • Genzoo - VAE
    • Papers We Read
  • Videos
    • On the Expressivity of Markov Rewards
    • Evolving RL Algorithms
    • RL Using Diffusion Models
    • Textual Inversion
    • Dreambooth
    • Flash Attention
    • FrugalGPT
    • StreamingLLM
    • Prompt2prompt
    • InstaFlow
    • IntstructPix2Pix
  • Publications
    • Modeling Financial Uncertainty with Multivariate Temporal Entropy‐based Curriculums (UAI 2021)
    • Track, Check, Repeat: An EM Approach to Unsupervised Tracking (CVPR 2021)
    • Multimodal Multi‐Task Financial Risk Forecasting (ACM MM 2020 - Oral)
    • DEAP Cache: Deep Eviction Admission and Prefetching for Cache (Submitted to AAAI 2021)
    • Visual Relationship Detection using Scene Graphs: A Survey (Submitted to ACM CSUR 2020

RL Using Diffusion Models

Jul 15, 2023 · 0 min read
Go to Project Site
Last updated on Jul 15, 2023
Rl
Ayush Mangal
Authors
Ayush Mangal
First year MSR
← Evolving RL Algorithms Jul 15, 2023
Textual Inversion Jul 15, 2023 →

© 2026 Ayush Mangal

RSS · Source · Built with Hugo & Hugo Blox