Picture

Anirudh Goyal @anirudhg9119

Thinking about thinking. Gemini ♊. Spent time at @Berkeley_EECS, @MPI_IS, @GoogleDeepMind. anirudh9119.github.io London, UK Joined October 2014
  • Tweets
    902
  • Followers
    5K
  • Following
    538
  • Likes
    6K
Anirudh Goyal retweeted
michaelqshieh Profile Picture

Michael Qizhe Shieh @michaelqshieh

4 weeks ago

To me, diffusion LMs work because they remove unnecessary inductive biases. The left-to-right inductive bias is natural for human but is unlikely to be natural for AI. This gives more capacity to our models like Transformer having a bigger capacity than LSTM. Our experiment…

NiJinjie Profile Picture

Jinjie Ni @NiJinjie

4 weeks ago

To me, diffusion LMs work because they remove unnecessary inductive biases. The left-to-right inductive bias is natural for human but is unlikely to be natural for AI. This gives more capacity to our models like Transformer having a bigger capacity than LSTM. Our experiment…

Anirudh Goyal retweeted
rosemary_ke Profile Picture

Nan Rosemary Ke @rosemary_ke

a year ago

Boosting LLM Performance with Dynamic Skill Selection! 1/ 🚀 What if LLMs could get better at solving math problems by understanding the skills they need? We explored this idea by having LLMs identify and label the skills required for each problem. arxiv.org/abs/2405.12205

prfsanjeevarora Profile Picture

Sanjeev Arora @prfsanjeevarora

a year ago

Boosting LLM Performance with Dynamic Skill Selection! 1/ 🚀 What if LLMs could get better at solving math problems by understanding the skills they need? We explored this idea by having LLMs identify and label the skills required for each problem. arxiv.org/abs/2405.12205

anirudhg9119 Profile Picture

Anirudh Goyal @anirudhg9119

a year ago

Interesting progress from @rm_rafailov and @DivGarg9 et. al following our work (applied to mathematical and commonsense reasoning): Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning arxiv.org/abs/2405.00451 (Also discussed in Llama-3 paper, @AIatMeta )

rm_rafailov Profile Picture

Rafael Rafailov @ NeurIPS @rm_rafailov

a year ago

Interesting progress from @rm_rafailov and @DivGarg9 et. al following our work (applied to mathematical and commonsense reasoning): Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning arxiv.org/abs/2405.00451 (Also discussed in Llama-3 paper, @AIatMeta ) https://t.co/aq7Icjkpql

anirudhg9119 Profile Picture

Anirudh Goyal @anirudhg9119

a year ago

Work from @DaniloJRezende, Shakir Mohamed and Daan Weistra. proceedings.mlr.press/v32/rezende14.… Credit assignment is difficult.

anirudhg9119 Profile Picture

Anirudh Goyal @anirudhg9119

3 years ago

Discrete Key-Value Bottleneck (Updated) Compresses the information of a pre-trained model in learnable "key-value" codebook such that knowledge can be quickly adapted in a continual learning fashion. arxiv.org/abs/2207.11240

anirudhg9119 Profile Picture

Anirudh Goyal @anirudhg9119

3 years ago

Temporal Latent Bottleneck combines recurrence and self-attention in an unified way. Recurrence integrates information over time, and self-attention models local dependencies in "short" context. arxiv.org/abs/2205.14794

arankomatsuzaki Profile Picture

Aran Komatsuzaki @arankomatsuzaki

3 years ago

Temporal Latent Bottleneck combines recurrence and self-attention in an unified way. Recurrence integrates information over time, and self-attention models local dependencies in "short" context. arxiv.org/abs/2205.14794 https://t.co/RtUdzw8tYO

Trends for United States

#CashAppFriday
#2KDay
7.228 posts
#2kgiveaway
7.057 posts
Hyundai
41,6 B posts
Cetus 100x
GiveRep V1
#FanCashDropPromotion
#FursuitFriday
12,5 B posts
Double
210 B posts
GAME DAY
36,3 B posts
Gates
177 B posts
Spielberg
7.247 posts
$TRAVEL
2.853 posts
Good Friday
58,1 B posts
Carter
176 B posts
Happy Friyay
2.061 posts
LINGORM ONLY YOU EP8
657 B posts
Bureau of Labor Statistics
6.177 posts
Blueprint
11,8 B posts
$TSLA
43,9 B posts

You might like

Professor of Computer Science at Oxford. Senior Staff Research Scientist at Waymo.
Shimon Whiteson
@shimon8282
18K Followers
Co-Founder & CEO @SkildAI, Faculty @CarnegieMellon. PhD @UCBerkeley. I study topics in AI (machine learning, robotics & computer vision).
Deepak Pathak
@pathak2206
23K Followers
CSO & co-founder, Reliant AI. Ex RL research lead at Google Brain, DeepMind. Known for Atari 2600 RL benchmark, Distributional RL (MIT Press 2023).
Marc G. Bellemare
@marcgbellemare
16K Followers
Co-founder & Chief Scientist @yutori_ai. Prev: Senior Director leading FAIR Embodied AI @MetaAI and Professor @GeorgiaTech.
Dhruv Batra
@DhruvBatraDB
19K Followers
Post-trainologer at FAIR. Into codegen, RL, equivariance, generative models. Spent time at Qualcomm, Scyfer (acquired), UvA, Deepmind, OpenAI.
Taco Cohen
@TacoCohen
27K Followers
Assoc Prof in ML @UniofOxford @StAnnesCollege @FLAIR_Ox/ RS @MetaAI, 2x dad. Ex: (A)PM @Google, DivStrat @GS, ex intern: @GoogleDeepmind, @GoogleBrain, @OpenAI
Jakob Foerster
@j_foerst
21K Followers
Research @AnthropicAI (Co-lead Discovery team) 💼 Past: Gemini @GoogleDeepMind (Co-led Blueshift team) 🧠 LLM Reasoning / AI Scientist 🎒Traveling & Backpacking
Behnam Neyshabur
@bneyshabur
29K Followers
Research Scientist @Google_Deepmind. PhD at @MILA.
Nan Rosemary Ke
@rosemary_ke
5K Followers
Research Scientist at Google DeepMind, PhD from MIT. Make machines empower people.
Been Kim
@_beenkim
26K Followers
Professor and Head of Machine Learning Department at @CarnegieMellon. Board member @OpenAI and @Qualcomm. Chief Technical Advisor @GraySwanAI.
Zico Kolter
@zicokolter
23K Followers
Assistant Professor @uwcse and Staff Research Scientist at @GoogleAI. Let's get off this app: https://t.co/jbH2oAjbPN
Natasha Jaques
@natashajaques
30K Followers
Director, @PrincetonPLI and Professor @PrincetonCS. Seeks math/conceptual understanding of deep learning and large AI models. Also on the
Sanjeev Arora
@prfsanjeevarora
25K Followers
AI Prof @Stanford | CEO & Cofounder @InceptionAILabs | Co-inventor of DDIM, FlashAttention, DPO, GAIL, and score-based/diffusion models
Stefano Ermon
@StefanoErmon
20K Followers
Research Scientist @OpenAI Previously: PhD @MIT @MSFTResearch @UberATG @SCSatCMU @AUB_Lebanon
Hadi Salman
@hadisalmanX
6K Followers
Reinforcement Learner, Adjunct Prof at McGill. Ex MSL Meta, DeepMind, Brain, Mila, IIT Bombay. NeurIPS Best Paper
Rishabh Agarwal
@agarwl_
17K Followers