Gerard de Melo

7

Papers

25

Total Citations

Papers (7)

NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning

Hierarchical Divide-and-Conquer for Fine-Grained Alignment in LLM-Based Medical Evaluation

MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models

Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision

Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification

Frozen CLIP Models Are Efficient Video Learners

Incorporating Pragmatic Reasoning Communication into Emergent Language