most citedUnderstanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference

3 citations · 4 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2024

Prompt-Guided Mask Proposal for Two-Stage Open-Vocabulary Segmentation

Yu-Jhe Li, Xinyang Zhang, Kun Wan +3

We tackle the challenge of open-vocabulary segmentation, where we need to identify objects from a wide range of categories in different environments, using text prompts as our inpu…

cs.CV2024

Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See

Zeliang Zhang, Phu Pham, Wentian Zhao +6

By treating visual tokens from visual encoders as text tokens, Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse visual understanding tasks,…