Large Language Model
Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model
Despite its importance, the vision-language connector has been relatively less explored.
ESPACE: Dimensionality Reduction of Activations for Model Compression
ESP ACE projects activations onto a pre-calibrated set of principal components.
ORA: Towards Safety Alignment of T ext2Video Generation via a Human Preference Dataset
This dataset encompasses human preferences in text-to-video generation tasks along two primary dimensions: helpfulness and harmlessness.
Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models
There are two updating strategies: 1) mimicking strategy to generate similar samples based on original data, preserving stylistic and contextual essence, and 2) extending strategy that further expands existing samples at varying cognitive levels by adapting Bloom's taxonomy of educational objectives.
NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
However, are these models truly effective?
Loki: Low-rank Keys for Efficient Sparse Attention
In particular, the self-attention mechanism used in LLM inference contributes significantly to these costs, which has sparked an interest in approximating the self-attention computation to reduce such costs.