Skip to content
conftrace_

cross-model transfer

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) classifier-guided decoding (1) reward feedback learning (1) negative embedding learning (1) negative embedding (1) attention-transfer attack (1) reward guidance (1) clip text encoder (1) lookback ratio (1) contextual hallucination (1)

Papers

Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models AAAI 2026 Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts ACL 2025 ReNeg: Learning Negative Embedding with Reward Guidance CVPR 2025 Sparse Autoencoder Features for Classifications and Transferability EMNLP 2025 Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps EMNLP 2024