Sparsity in LLMs Workshop at ICLR 2025

@sparseLLMs

Workshop on Sparsity in LLMs: Deep Dive into Mixture of Experts, Quantization, Hardware, and Inference @iclr_conf 2025.

Singapore

sparsellm.org

Joined December 2024

36Posts 202Followers 20Following

Pinned

Sparsity in LLMs Workshop at ICLR 2025

@sparseLLMs

Jan 6

We are happy to announce that the Workshop on Sparsity in LLMs will take place @iclr_conf in Singapore! For details: sparsellm.org Organizers: @TianlongChen4, @utkuevci, @yanii, @BerivanISIK, @Shiwei_Liu66, @adnan_ahmad1306, @alexinowak

sparseLLMs's tweet image. We are happy to announce that the Workshop on Sparsity in LLMs will take place
@iclr_conf in Singapore! For details: sparsellm.org

Organizers:
@TianlongChen4, @utkuevci, @yanii, @BerivanISIK, @Shiwei_Liu66, @adnan_ahmad1306, @alexinowak

Sparsity in LLMs Workshop at ICLR 2025 reposted

Yani Ioannou

@yanii

Apr 27

@AggieInCA giving the first Oral talk at #ICLR2025 @sparseLLMs workshop

Sparsity in LLMs Workshop at ICLR 2025 reposted

Presenting in short! 👉🏼 Mol-MoE: leveraging model merging and RLHF for test-time steering of molecular properties. 📆 today, 11:15am to 12:15pm 📍 Poster session #1, GEM Bio Workshop @gembioworkshop @sparseLLMs #ICLR #ICLR2025

Diego Calanzone @ COLM 2025 🔠

@diegocalanzone

Apr 23

In Mol-MoE, we propose a framework to train router networks to reuse property-specific molecule generators. This allows to personalize drug generation at test time by following property preferences! We discuss some challenges. @proceduralia @pierrelux arxiv.org/abs/2502.05633

Sparsity in LLMs Workshop at ICLR 2025 reposted

Yani Ioannou

@yanii

Apr 27

@black_samorez giving his oral talk at the #ICLR2025 @sparseLLMs workshop

Sparsity in LLMs Workshop at ICLR 2025 reposted

Ayush Noori

@ayushnoori

Apr 27

We are presenting “Prefix and output length-aware scheduling for efficient online LLM inference” at the ICLR 2025 (@iclr_conf) Sparsity in LLMs workshop (@sparseLLMs). 🪫 Challenge: LLM inference in data centers benefits from data parallelism. How can we exploit patterns in…

ayushnoori's tweet image. We are presenting “Prefix and output length-aware scheduling for efficient online LLM inference” at the ICLR 2025 (@iclr_conf) Sparsity in LLMs workshop (@sparseLLMs).

🪫 Challenge: LLM inference in data centers benefits from data parallelism. How can we exploit patterns in…

Sparsity in LLMs Workshop at ICLR 2025 reposted

Yani Ioannou

@yanii

Apr 27

@tydsh giving his invited talk at the #ICLR2025 @sparseLLMs workshop!

Sparsity in LLMs Workshop at ICLR 2025 reposted

Ashwinee Panda

@PandaAshwinee

Apr 27

our workshop on sparsity in LLMs is starting soon in Hall 4.7! we’re starting strong with an invited talk from @DAlistarh and an exciting oral on scaling laws for MoEs!

PandaAshwinee's tweet image. our workshop on sparsity in LLMs is starting soon in Hall 4.7! we’re starting strong with an invited talk from @DAlistarh and an exciting oral on scaling laws for MoEs!

Sparsity in LLMs Workshop at ICLR 2025 reposted

Yani Ioannou

@yanii

Apr 27

@DAlistarh giving his invited talk at the #ICLR2025 @sparseLLMs workshop

Sparsity in LLMs Workshop at ICLR 2025 reposted

Shiwei Liu

@Shiwei_Liu66

Apr 27

Our ICLR 2025 Workshop on Sparsity in LLMs (@sparseLLMs) kicks off with a talk by @DAlistarh on lossless (~1% perf drop) LLM compression using quantization across various benchmarks.

Shiwei_Liu66's tweet image. Our ICLR 2025 Workshop on Sparsity in LLMs (@sparseLLMs) kicks off with a talk by @DAlistarh on lossless (~1% perf drop) LLM compression using quantization across various benchmarks.

Sparsity in LLMs Workshop at ICLR 2025 reposted

Yani Ioannou

@yanii

Apr 27

First poster session at the #ICLR2025 @sparseLLMs workshop

Sparsity in LLMs Workshop at ICLR 2025 reposted

Ashwinee Panda

@PandaAshwinee

Apr 27

a PACKED hall for @tydsh‘s talk at our sparsity in LLMs workshop -not surprising! we have another oral right after this, and then we’ll have the first of 2 poster sessions before lunch! @iclr_conf

PandaAshwinee's tweet image. a PACKED hall for @tydsh‘s talk at our sparsity in LLMs workshop -not surprising! we have another oral right after this, and then we’ll have the first of 2 poster sessions before lunch! @iclr_conf

Sparsity in LLMs Workshop at ICLR 2025 reposted

Yani Ioannou

@yanii

Apr 27

@DAlistarh giving his invited talk at the #ICLR2025 @sparseLLMs workshop now!

Sparsity in LLMs Workshop at ICLR 2025 reposted

Yani Ioannou

@yanii

Apr 27

#ICLR2025 @sparseLLMs Workshop Panel with @PavloMolchanov @ayazdanb @DAlistarh @realDanFu @YangYou1991 and Olivia Hsu, moderated by @PandaAshwinee

yanii's tweet image. #ICLR2025 @sparseLLMs Workshop Panel with @PavloMolchanov @ayazdanb @DAlistarh @realDanFu @YangYou1991 and Olivia Hsu, moderated by @PandaAshwinee

Sparsity in LLMs Workshop at ICLR 2025 reposted

Harshay Shah

@harshays_

Apr 26

If you’re at #ICLR2025, go watch @AggieInCA give an oral presentation at the @SparseLLMs workshop on scaling laws for pretraining MoE LMs! Had a great time co-leading this project with @samira_abnar & @AggieInCA at Apple MLR last summer. When: Sun Apr 27, 9:30a Where: Hall 4-07

Samira Abnar

@samira_abnar

Jan 28

🚨 One question that has always intrigued me is the role of different ways to increase a model's capacity: parameters, parallelizable compute, or sequential compute? We explored this through the lens of MoEs:

samira_abnar's tweet image. 🚨 One question that has always intrigued me is the role of different ways to increase a model's capacity: parameters, parallelizable compute, or sequential compute?

We explored this through the lens of MoEs:

Sparsity in LLMs Workshop at ICLR 2025

@sparseLLMs

Apr 26

Sparse LLM workshop will run on Sunday with two poster sessions, a mentoring session, 4 spotlight talks, 4 invited talks and a panel session. We'll host an amazing lineup of researchers: @DAlistarh @vithursant19 @tydsh @ayazdanb @gkdziugaite Olivia Hsu @PavloMolchanov Yang Yu

sparseLLMs's tweet image. Sparse LLM workshop will run on Sunday with two poster sessions, a mentoring session, 4 spotlight talks, 4 invited talks and a panel session.

We'll host an amazing lineup of researchers: @DAlistarh @vithursant19 @tydsh @ayazdanb @gkdziugaite Olivia Hsu @PavloMolchanov Yang Yu

Sparsity in LLMs Workshop at ICLR 2025 reposted

Yani Ioannou

@yanii

Apr 22

I will travelling to Singapore 🇸🇬 this week for the ICLR 2025 Workshop on Sparsity in LLMs (SLLM) that I'm co-organizing! We have an exciting lineup of invited speakers and panelists including @DAlistarh, @gkdziugaite, @PavloMolchanov, @vithursant19, @tydsh and @ayazdanb.

Sparsity in LLMs Workshop at ICLR 2025 reposted

Vimal Thilak🦉🐒

@AggieInCA

Apr 21

Check out this post that has information about research from Apple that will be presented at ICLR 2025 in 🇸🇬 this week. I will be at ICLR and will be presenting some of our work (led by @samira_abnar) at SLLM @sparseLLMs workshop. Happy to chat about JEPAs as well!

Peter Gray

@peteryugray

Apr 21

New post: "Apple Machine Learning Research at @iclr_conf 2025" - highlighting a selection of the many Apple #ML research papers to be presented at the conference this week: machinelearning.apple.com/research/iclr-…

Sparsity in LLMs Workshop at ICLR 2025 reposted

Dan Alistarh

@DAlistarh

Apr 7

Our QuEST paper was selected for Oral Presentation at ICLR @sparseLLMs workshop! QuEST is the first algorithm with Pareto-optimal LLM training for 4bit weights/activations, and can even train accurate 1-bit LLMs. Paper: arxiv.org/abs/2502.05003 Code: github.com/IST-DASLab/QuE…

github.com

GitHub - IST-DASLab/QuEST: Work in progress.

Work in progress. Contribute to IST-DASLab/QuEST development by creating an account on GitHub.

Source: github.com

Mohammad Areeb

@itsareebverse

rose lin

@roselin86992969

co_kole

@ilikecocole

Wenwu Tang

@WenwuT51451

Danish Ahmed

@DanxhAhmed

Moabyte_ 0C42

@mcy_0x0

Leonardo Leão

@Lleao1300

JieJyun Liu

@elevenyeast

prabhu

@Sameehanay

tejas krishna

@tejaskrshna

returnwellbeing

@returnwellbeing

RealNerd

@inaw_varuag

Arvada

@Arvada_A

Bala Pillai

@balapillai

Abhay shukla

@AbhayS1999

Quoc Anh Mai

@Vodkahn92

Egli Loiacono

@EgliLoiaco75579

Jinane Bazzi

@JinaneBazzi

TvT Zoey

@TvTZoey

aastha

@being__aastha

Christine Konopelski

@ChristineK47796

smile

@Smilex_P

PURANJAY DATTA

@puranjay1412

Vinci Yang

@WanqiYang1

Ziping Zhao

@ZipingZhao

jluite

@jluite2014

Anuj Dutt

@anujdutt92

Jiminator

@Jiminator31

Schuvic

@Schuvic

GDP

@bookwormengr

Ed Blyden

@EdBlyden

Taishi Nakamura

@Setuna7777_2

Miles Williams

@miles_wil

Weronika Ormaniec

@wormaniec

Ayush Noori

@ayushnoori

Samuel Horváth

@sam_hrvth

Lavoie Jacob

@jacoblav

Sabarish

@sabarish_sn

Andrew Stack

@drewstack

Huiqiang Jiang

@iofu728

William Hsu

@William02319778

Jeongwhan Choi

@jeongwhan_choi

Meenu Shekhawat

@PIlka2227

Huanjian Zhou

@shukanken

Tuấn Võ Anh

@VoAnh29397

NaB

@Mich0_0Mach

T Zhang

@madHamiltonian

Co ong

@cosmas_ochieng

Tim Lawson

@tslwn

Mohamed Hamed

@hamed_mo7amed

Vimal Thilak🦉🐒

@AggieInCA

Pavlo Molchanov

@PavloMolchanov

Amir Yazdan

@ayazdanb

Gintare Karolina Dziugaite

@gkdziugaite

Yuandong Tian

@tydsh

Aleksandra

@alexinowak

Fuzhao Xue (Frio)

@XueFz

Vithu Thangarasa

@vithursant19

Azalia Mirhoseini

@Azaliamirh

$sarahookr's profile picture. Adaptive Intelligence. Built @Cohere_Labs, @GoogleBrain, @GoogleDeepmind. ML Efficiency, Multimodal\lingual. Changing spaces where breakthroughs happen.$