GLEE: A Unified Framework and Benchmark for Language-based Economic Environments Paper • 2410.05254 • Published Oct 7 • 80
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations Paper • 2410.02707 • Published Oct 3 • 47
Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs Paper • 2406.20086 • Published Jun 28 • 5
NNsight and NDIF: Democratizing Access to Foundation Model Internals Paper • 2407.14561 • Published Jul 18 • 33
Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models Paper • 2311.12092 • Published Nov 20, 2023 • 21
Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines Paper • 2403.05846 • Published Mar 9 • 1
Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model Paper • 2408.11039 • Published Aug 20 • 58
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding Paper • 2406.19389 • Published Jun 27 • 52
MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data Paper • 2406.18790 • Published Jun 26 • 33
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Paper • 2406.18629 • Published Jun 26 • 41
Make It Count: Text-to-Image Generation with an Accurate Number of Objects Paper • 2406.10210 • Published Jun 14 • 76