Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation Paper • 2603.21884 • Published 17 days ago • 5
Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation Paper • 2603.21884 • Published 17 days ago • 5
BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data Paper • 2510.10159 • Published Oct 11, 2025 • 3
Measuring what Matters: Construct Validity in Large Language Model Benchmarks Paper • 2511.04703 • Published Nov 3, 2025 • 8
Learning Human-Human Interactions in Images from Weak Textual Supervision Paper • 2304.14104 • Published Apr 27, 2023
MOCHa: Multi-Objective Reinforcement Mitigating Caption Hallucinations Paper • 2312.03631 • Published Dec 6, 2023
ICC: Quantifying Image Caption Concreteness for Multimodal Dataset Curation Paper • 2403.01306 • Published Mar 2, 2024
Emergent Visual-Semantic Hierarchies in Image-Text Representations Paper • 2407.08521 • Published Jul 11, 2024
ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline Paper • 2508.06094 • Published Aug 8, 2025
Phonikud: Hebrew Grapheme-to-Phoneme Conversion for Real-Time Text-to-Speech Paper • 2506.12311 • Published Jun 14, 2025
Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding Paper • 2303.12513 • Published Mar 21, 2023
Kiki or Bouba? Sound Symbolism in Vision-and-Language Models Paper • 2310.16781 • Published Oct 25, 2023
MedicoSAM: Towards foundation models for medical image segmentation Paper • 2501.11734 • Published Jan 20, 2025 • 1
Generating (Factual?) Narrative Summaries of RCTs: Experiments with Neural Multi-Document Summarization Paper • 2008.11293 • Published Aug 25, 2020
Bayesian Deep Learning for Exoplanet Atmospheric Retrieval Paper • 1811.03390 • Published Nov 8, 2018
3rd Place Report of LSVOS 2025 MeViS Track: Sa2VA-i: Improving Sa2VA Results with Consistent Training and Inference Paper • 2509.19082 • Published Sep 23, 2025 • 1
view post Post 1596 New blog post analyzing the top 50 entities with the most downloaded models on @huggingface 🤗!https://huggingface.co/blog/lbourdois/huggingface-models-stats The purpose here is to get an idea of the profile of the models with the greatest impact in open source (we are not interested in closed models here!). 32 figures + dataEnjoy 🤗 See translation 👀 2 2 + Reply