Multiverse Computing

company

Verified

https://multiversecomputing.com/

AI & ML interests

None defined yet.

Recent Activity

AntonioTN submitted a paper about 1 hour ago

When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill

Htijero published a model about 20 hours ago

MultiverseComputingCAI/Comet_60B_A12B_NVFP4

Htijero published a model about 20 hours ago

MultiverseComputingCAI/Comet_60B_A12B_FP8

View all activity

Papers

When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill

Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal

View all Papers

Articles

Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents

Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem

Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

Making Knowledge Distillation Cheap Enough to Run at Scale

View all articles

submitted a paper to Daily Papers about 1 hour ago

When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill

Paper • 2610.21500 • Published 1 day ago

published 3 models about 20 hours ago

MultiverseComputingCAI/Comet_60B_A12B_NVFP4

Image-Text-to-Text • 35B • Updated 1 day ago • 25 • 6

MultiverseComputingCAI/Comet_60B_A12B_FP8

Image-Text-to-Text • 62B • Updated 1 day ago • 8 • 1

MultiverseComputingCAI/Comet_60B_A12B_BF16

Image-Text-to-Text • 61B • Updated 1 day ago • 17 • 8

carlosmoralrubio

updated 3 models 1 day ago

MultiverseComputingCAI/Comet_60B_A12B_NVFP4

Image-Text-to-Text • 35B • Updated 1 day ago • 25 • 6

MultiverseComputingCAI/Comet_60B_A12B_FP8

Image-Text-to-Text • 62B • Updated 1 day ago • 8 • 1

MultiverseComputingCAI/Comet_60B_A12B_BF16

Image-Text-to-Text • 61B • Updated 1 day ago • 17 • 8

authored a paper 16 days ago

Scaling Laws for Energy Efficiency of Local LLMs

Paper • 2512.16531 • Published Dec 29, 2025 • 2

authored a paper 17 days ago

ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents

Paper • 2606.18037 • Published Aug 27 • 2

published an article 17 days ago

Article

Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents

MultiverseComputingCAI

•

17 days ago

• 23

published an article 25 days ago

Article

Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem

MultiverseComputingCAI

•

25 days ago

• 34

authored a paper about 1 month ago

Scaling Laws for Energy Efficiency of Local LLMs

Paper • 2512.16531 • Published Dec 29, 2025 • 2

authored 3 papers about 1 month ago

Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs

Paper • 2608.20953 • Published Aug 21 • 15

LLM Compression by Block Removal with Constrained Binary Optimization

Paper • 2602.00161 • Published Jun 17 • 9

Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss

Paper • 2608.03796 • Published Aug 4 • 21

published an article about 1 month ago

Article

Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic

MultiverseComputingCAI

•

Sep 8

• 31

submitted a paper to Daily Papers about 1 month ago

Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal

Paper • 2609.04482 • Published Sep 3 • 12

authored a paper about 1 month ago

Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal

Paper • 2609.04482 • Published Sep 3 • 12

authored 2 papers about 2 months ago

Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs

Paper • 2608.20953 • Published Aug 21 • 15

LLM Compression by Block Removal with Constrained Binary Optimization

Paper • 2602.00161 • Published Jun 17 • 9