Moritz Boehle

mboehle's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 1 month ago

CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion

Paper • 2512.19535 • Published Dec 22, 2025 • 12

updated a model about 1 month ago

kyutai/CASA-Helium1-VL-2B

Image-Text-to-Text • 3B • Updated Dec 23, 2025 • 88 • 6

updated a model 10 months ago

kyutai/moshi-artifacts

Updated Mar 26, 2025

authored 3 papers 10 months ago

Using Explanations to Guide Models

Paper • 2303.11932 • Published Mar 21, 2023

Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery

Paper • 2407.14499 • Published Jul 19, 2024

Good Teachers Explain: Explanation-Enhanced Knowledge Distillation

Paper • 2402.03119 • Published Feb 5, 2024

updated a model 10 months ago

kyutai/moshika-vis-pytorch-bf16

Updated Jun 18, 2025 • 56

authored 2 papers 10 months ago

Better Understanding Differences in Attribution Methods via Systematic Evaluations

Paper • 2303.11884 • Published Mar 21, 2023

Towards Better Understanding Attribution Methods

Paper • 2205.10435 • Published May 20, 2022

updated a dataset 10 months ago

kyutai/Babillage

Viewer • Updated Mar 21, 2025 • 465k • 19 • 12

updated a model 10 months ago

kyutai/moshika-vis-mlx

Updated Mar 18, 2025 • 2

updated a model 11 months ago

kyutai/moshika-vis-candle-bf16

Updated Mar 18, 2025 • 1

updated a collection 11 months ago

MoshiVis v0.1

Collection

MoshiVis is a Vision Speech Model built as a perceptually-augmented version of Moshi v0.1 for conversing about image inputs • 9 items • Updated Dec 23, 2025 • 23

updated a model 12 months ago

kyutai/moshika-vis-pytorch-bf16

Updated Jun 18, 2025 • 56