Deep Learning
Unified Generative and Discriminative Training for Multi-modal Large Language Models Wei Chow
In recent times, Vision-Language Models (VLMs) have been trained under two predominant paradigms.
Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information
Current uncertainty quantification is memory and compute expensive, which hinders practical uptake.
Communication-Efficient Federated Group Distributionally Robust Optimization
In contrast to CV aR, KL is a softer regularizer to promote smoother and more stable learning.
A two-scale Complexity Measure for Deep Learning Models
We introduce a novel capacity measure 2sED for statistical models based on the effective dimension.
SnapKV: LLM Knows What You Are Looking for before Generation Y uhong Li1 Yingbing Huang 1 Bowen Y ang 2 Bharat V enkitesh
To validate the robustness, we design extensive experiments across diverse prompts in terms of length, format, and content.
ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs Irene Huang 1 Wei Lin
Compositional Reasoning (CR) entails grasping the significance of attributes, relations, and word order.
FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation
Recently, prompt learning has emerged as the state-of-the-art (SOT A) for fair text-to-image (T2I) generation.