24 papers
UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations
Dvir Samuel, Guy Bar-Shalom, Fabrizio Frasca +4
Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by the visual input. Effective mi…
SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
Yewei Liu, Xiyuan Wang, Yansheng Mao +3
We propose SHINE (Scalable Hyper In-context NEtwork), a scalable hypernetwork that can map diverse meaningful contexts into high-quality LoRA adapters for large language models (LL…
Spanning the Visual Analogy Space with a Weight Basis of LoRAs
Hila Manor, Rinon Gal, Haggai Maron +2
Visual analogy learning enables image editing via demonstration rather than textual description, allowing users to specify complex transformations difficult to articulate in words.…
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aaron Blakeman +571
We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 t…
On the Expressive Power of Permutation-Equivariant Weight-Space Networks
Adir Dayan, Yam Eitan, Haggai Maron
Weight-space learning studies neural architectures that operate directly on the parameters of other neural networks. Motivated by the growing availability of pretrained models, rec…
Learning from Historical Activations in Graph Neural Networks
Yaniv Galron, Hadar Sinai, Haggai Maron +1
Graph Neural Networks (GNNs) have demonstrated remarkable success in various domains such as social networks, molecular chemistry, and more. A crucial component of GNNs is the pool…