most citedVerifiable Fine-Tuning for LLMs: Zero-Knowledge Training Proofs Bound to Data Provenance and Policy

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing eess.SPShow all

1 paper · 1 filter

eess.SP2025

RCMCL: A Unified Contrastive Learning Framework for Robust Multi-Modal (RGB-D, Skeleton, Point Cloud) Action Understanding

Hasan Akgul, Mari Eplik, Javier Rojas +3

Human action recognition (HAR) with multi-modal inputs (RGB-D, skeleton, point cloud) can achieve high accuracy but typically relies on large labeled datasets and degrades sharply…