Institute of Foundation Models

community

https://ifm.ai/

institute-of-foundation-models

AI & ML interests

Foundation Models, Large Language Models (LLMs), Generative AI, Multilingual Models, Reasoning, AI Agents, Open-Source AI, AI Research

Recent Activity

hunterhector new activity about 1 hour ago

IFM/K2-Horizon-MoVA-36B-A4B:Independent testing shows the true capabilities of this model

zhou94539 updated a model about 1 hour ago

IFM/K2-Horizon-3.7B

zhou94539 updated a model about 1 hour ago

IFM/K2-Horizon-7B

View all activity

Papers

LOCI: Spatial Linear Memory for Streaming World Models

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

View all Papers

in IFM/K2-Horizon-MoVA-36B-A4B about 1 hour ago

Independent testing shows the true capabilities of this model

#9 opened 1 day ago by

updated 2 models about 1 hour ago

IFM/K2-Horizon-3.7B

Text Generation • 5B • Updated about 1 hour ago • 18.8k • • 84

IFM/K2-Horizon-7B

Text Generation • 9B • Updated about 1 hour ago • 27.6k • • 242

updated a model about 2 hours ago

IFM/K2-Type-0.9B

Text Generation • 1B • Updated about 1 hour ago • 720 • 1

updated 5 models about 7 hours ago

IFM/K2-Horizon-MoVA-36B-A4B-GGUF

Text Generation • 37B • Updated about 7 hours ago • 34.4k • 139

IFM/K2-Horizon-32B-GGUF

Text Generation • 35B • Updated about 7 hours ago • 2.29k • 13

IFM/K2-Horizon-7B-GGUF

Text Generation • 9B • Updated about 7 hours ago • 23.3k • 70

IFM/K2-Horizon-3.7B-GGUF

Text Generation • 5B • Updated about 7 hours ago • 13.3k • 37

IFM/K2-Horizon-0.9B-GGUF

Text Generation • 1B • Updated about 7 hours ago • 7.07k • 28

submitted a paper to Daily Papers about 10 hours ago

LOCI: Spatial Linear Memory for Streaming World Models

Paper • 2609.40222 • Published 2 days ago • 5

authored 2 papers about 12 hours ago

Memorizon: Training World Models Beyond Their Context Window

Paper • 2610.00544 • Published 3 days ago • 4

LOCI: Spatial Linear Memory for Streaming World Models

Paper • 2609.40222 • Published 2 days ago • 5

submitted a paper to Daily Papers about 14 hours ago

Memorizon: Training World Models Beyond Their Context Window

Paper • 2610.00544 • Published 3 days ago • 4

submitted a paper to Daily Papers 18 days ago

MInTRL: Off-policy Intervention can boost On-policy RL

Paper • 2609.12419 • Published 22 days ago • 14

authored 3 papers 18 days ago

Continuous Diffusion Scales Competitively with Discrete Diffusion for Language

Paper • 2605.18530 • Published May 18

Scaling Beyond Masked Diffusion Language Models

Paper • 2602.15014 • Published Feb 16 • 2

Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokens

Paper • 2509.20060 • Published Sep 24, 2025

authored a paper 24 days ago

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Paper • 2609.04010 • Published 30 days ago • 114

authored 2 papers 24 days ago

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Paper • 2609.04010 • Published 30 days ago • 114

ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning

Paper • 2607.02509 • Published Jul 2 • 2