WaterMoE: A Low-Overhead Watermarking Method for Mixture-of-Experts LLMs
Large language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse, motivating the need for reliable watermarking techniques. However, these…
Read the full articleYou might also wanna read
Uncovering Hidden Truths: The Rise of Watermark Detection in AI Text
WISER, a new watermark detection tool, promises to revolutionize AI-generated text authenticity with unprecedented speed and accuracy.
StickyMoE: Cutting Edge in Expert Routing for Language Models
StickyMoE tackles the inefficiencies in Mixture-of-Experts by ensuring consistency in expert assignments across tokens. This results in fewe
Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing
arXiv:2607.08839v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are typically designed under the assumption that
Large Language Models Enable Effective Deanonymization of Pseudonymous Online Users
We show that large language models can be used to perform at-scale deanonymization. With full Internet access, our agent can re-identify Hac
arxiv.org·4mo ago
Nemotron-Labs-3-Puzzle-75B-A9B: A Compressed Hybrid MoE LLM for Efficient Interactive Deployment
We present Nemotron-Labs-3-Puzzle-75B-A9B, a compressed variant of Nemotron-3-Super optimized for interactive deployment. We designed the mo
arxiv.org·9d agoNemotron-Labs-3-Puzzle-75B-A9B: A Compressed Hybrid MoE LLM for Efficient Interactive Deployment
We present Nemotron-Labs-3-Puzzle-75B-A9B, a compressed variant of Nemotron-3-Super optimized for interactive deployment. We designed the mo
arxiv.org·9d agoPangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity
The surgence of Mixture of Experts (MoE) in Large Language Models promises a small price of execution cost for a much larger model parameter
arxiv.org·1y ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.