Tag: Multimodality
All the articles with the tag "Multimodality".
-
Activation Space Interventions Can Be Transferred Between Large Language Models
Published: at 06:19 PM
85.65 🤔This paper demonstrates that activation space interventions for AI safety, such as backdoor removal and refusal behavior, can be transferred between large language models using autoencoder mappings, enabling smaller models to align larger ones, though challenges remain in cross-architecture transfers and complex tasks like corrupted capabilities.
-
Chain-of-Model Learning for Language Model
Published: at 11:24 AM 85.56 🤔本文提出 Chain-of-Model (CoM) 学习范式，通过在 Transformer 架构中引入因果依赖的多尺度表示（Chain-of-Representation），实现高效模型扩展和弹性推理，实验表明 CoLM 系列在性能上与标准 Transformer 相当，同时在预填充速度和灵活性上具有优势。
-
Improving Multilingual Language Models by Aligning Representations through Steering
Published: at 11:22 AM 85.45 🤔本文提出了一种通过表示引导调整大型语言模型层级表示的方法，以提升多语言任务性能，实验显示其在多种任务中优于基本提示并接近翻译基线，但对英语任务有负面影响且对低资源语言改进有限。
-
The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants
Published: at 11:43 AM 85.27 🤔本文提出*Avengers*框架，通过无训练的嵌入、聚类、评分和投票操作，整合多个小型开源语言模型的集体智能，在15个多样化数据集上平均性能超越GPT-4.1，展现了开源模型挑战专有巨头的潜力。
-
Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis
Published: at 11:51 AM 85.09 🤔本文通过提出 PTQ-Bench 基准测试框架，系统评估了大型语言模型后训练量化（PTQ）策略的跨位宽、跨结构和跨模态鲁棒性，发现旋转型和补偿型策略在低位量化中表现优异，并提出极低位量化需重新审视及补偿型策略结合其他方法可显著提升鲁棒性的关键见解。