Antonio Tiene

AntonioTN

MultiverseComputingCAI

·

antoniotiene

AI & ML interests

LLMs

Recent Activity

submitted a paper about 4 hours ago

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

upvoted a paper 17 days ago

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

upvoted an article 17 days ago

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

View all activity

Organizations

Articles 5

Article

23

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

Article

34

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

View all Articles

Papers 4

arxiv:2609.04482

arxiv:2608.20953

arxiv:2608.03796

arxiv:2512.16531

models 0

None public yet

datasets 0

None public yet