Explore tweets tagged as #ModelMerging
@swyx
swyx
4 months
whoa so @thinkymachines is doing model merging + customized RL quite a come-up for merging in the past couple weeks, with @arcee_ai mergekit also featuring heavily in AFM. credit due to @jeremyphoward for being the first to make me take modelmerging seriously
26
50
780
@LucaLumetti
Luca Lumetti
4 months
Paper accepted at #MICCAI2025: “U-Net Transplant: The Role of Pre-training for Model Merging in 3D Medical Segmentation” Our study is the first about #ModelMerging in the 3D medical image segmentation domain: 📄 Paper: https://t.co/S1BUoIE5jN 💻 Code: https://t.co/MlCBVqjFIt
0
0
3
@DonatoCrisosto1
Donato Crisostomi
3 months
Also check the poster👀 #ICML2025 @icmlconf #modelmerging
@tommaso_mncttn
tommaso mencattini
3 months
Want to merge multiple LLMs into a new SOTA model, using just a desktop GPU? 🧬 Meet MERGE3: an evolutionary merging framework that slashes fitness costs by 50×! A quick dive into our #ICML25 paper ⤵️
0
2
19
@LucaZh00
Luca Zhou
27 days
0
0
0
@andresvilarino
Andres Vilariño 🇪🇦
11 months
TIME Framework: A Novel #MachineLearning Unifying Framework Breaking Down Temporal #ModelMerging https://t.co/XBwbma4q5p
0
0
0
@TheBullrunMeme
Bull Run
1 year
Exploring Model Merging Techniques for Large Language Models (LLMs): Discover how model merging enhances the efficiency of large language models by repurposing resources and improving… https://t.co/64oINNVgyv #ModelMerging #LLMs #Efficiency #Resources #TaskPerformance
1
0
1
@vlruso
Vlad Ruso PhD
1 year
0
0
0
@vlruso
Vlad Ruso PhD
11 months
TIME Framework: A Novel Machine Learning Unifying Framework Breaking Down Temporal Model Merging https://t.co/dhss0YBL3Q #ModelMerging #TIMEFramework #MachineLearning #AIResearch #TemporalIntegration #ai #news #llm #ml #research #ainews #innovation #artificialintelligence #ma
0
1
1
@vlruso
Vlad Ruso PhD
8 months
Enhancing Reasoning Capabilities in Low-Resource Language Models through Efficient Model Merging #LowResourceLanguages #AIResearch #ModelMerging #LanguageModels #ReasoningCapabilities https://t.co/oZNnjPHoZf
0
1
3
@cindy2000_sh
Cindy Zeng
6 months
[1/N] #ML #LLM #ModelMerging Paper: https://t.co/l52QPhymxE We build theory to explain why task arithmetic works, and propose Task Vector Bases, a scalable model editing method grounded in it. With @heyifei99, @youweiqiu, Yifan, Hubert, @myamada0, @hanzhao_ml. 🧵 Dive in below:
2
5
14
@EngageProVideo
EngagePro Video For Business
2 years
Merge Large Language Models with mergekit. Create your own models easily, no GPU required! https://t.co/0YTNHgrD7h #MergeKit #LLMs #ModelMerging
0
0
1
@vlruso
Vlad Ruso PhD
1 year
0
0
0
@vlruso
Vlad Ruso PhD
1 year
Researchers from Georgia Tech and IBM Introduces KnOTS: A Gradient-Free AI Framework to Merge LoRA Models https://t.co/KZuNnjnkg6 #AIResearch #ModelMerging #KnOTS #MachineLearning #Innovation #ai #news #llm #ml #research #ainews #innovation #artificialintelligence #machinelea
0
0
0
@vlruso
Vlad Ruso PhD
1 year
Model Kinship: The Degree of Similarity or Relatedness between LLMs, Analogous to Biological Evolution https://t.co/s8ZWVjRxPV #ModelKinship #LargeLanguageModels #AIInnovation #ModelMerging #EfficiencyInAI #ai #news #llm #ml #research #ainews #innovation #artificialintelligen
0
0
0
@vlruso
Vlad Ruso PhD
1 year
This AI Research from Cohere for AI Compares Merging vs Data Mixing as a Recipe for Building High-Performant Aligned LLMs https://t.co/uY0uYaKqV2 #AIRevolution #LargeLanguageModels #ModelMerging #AISafety #CohereAI #ai #news #llm #ml #research #ainews #innovation #artificiali
0
0
0
@arcee_ai
Arcee.ai
1 year
... like writing style or "flavor" then Task Arithmetic with a model you like at weight 1 then a few others at much smaller weights (0.01-0.05) is a good way to explore what you can get. Sign up for the hackathon here: https://t.co/ohmghhpPZi (3/3) #nlp #modelmerging #LLM
0
0
1