DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion Paper • 2510.15264 • Published 13 days ago • 1
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs Paper • 2510.11288 • Published 17 days ago • 45
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA Paper • 2510.04849 • Published 24 days ago • 108
The Rogue Scalpel: Activation Steering Compromises LLM Safety Paper • 2509.22067 • Published Sep 26 • 27
SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens Paper • 2508.05305 • Published Aug 7 • 46
T-LoRA: Single Image Diffusion Model Customization Without Overfitting Paper • 2507.05964 • Published Jul 8 • 118
Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models Paper • 2506.06751 • Published Jun 7 • 71
SpatialLM: Training Large Language Models for Structured Indoor Modeling Paper • 2506.07491 • Published Jun 9 • 50
Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning Paper • 2506.07044 • Published Jun 8 • 113
Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA Paper • 2505.21115 • Published May 27 • 139
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders Paper • 2503.18878 • Published Mar 24 • 119
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers Paper • 2502.15007 • Published Feb 20 • 174
What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective Paper • 2410.23743 • Published Oct 31, 2024 • 63
CLEAR: Character Unlearning in Textual and Visual Modalities Paper • 2410.18057 • Published Oct 23, 2024 • 209