10 papers
Mitigating Diffusion Model Hallucinations with Dynamic Guidance
Kostas Triaridis, Alexandros Graikos, Aggelina Chatziagapi +2
Hallucinations in diffusion models are samples with structural inconsistencies that can emerge due to the excessive smoothing of the learned score function, which in turn leads to…
Why DDIM Hallucinates More Than DDPM: A Theoretical Analysis of Reverse Dynamics
Muhammad H. Ashiq, Samanyu Arora, Abhinav N. Harish +3
We theoretically study the hallucination phenomena in two canonical diffusion samplers: the stochastic Denoising Diffusion Probabilistic Model (DDPM) and the deterministic Denoisin…
Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Models
Jeffrey Wang, Jonathan Gregory, Grigorios G. Chrysos
Modern vision backbones treat pointwise activations (e.g., ReLU, GELU) and exponential softmax as essential sources of nonlinearity, but we demonstrate they are not required within…
LJ-Bench: Ontology-Based Benchmark for U.S. Crime
Hung Yun Tseng, Wuzhen Li, Blerina Gkotse +1
The potential of Large Language Models (LLMs) to provide harmful information remains a significant concern due to the vast breadth of illegal queries they may encounter. Unfortunat…
Corrective Diffusion Language Models
Shuibai Zhang, Fred Zhangzhi Peng, Yiheng Zhang +2
While Diffusion Language Models (DLMs) are theoretically well-suited for iterative refinement due to their non-causal structure, they often fail to reliably revise incorrect tokens…
Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
James Oldfield, Shawn Im, Sharon Li +3
Multilayer perceptrons (MLPs) are an integral part of large language models, yet their dense representations render them difficult to understand, edit, and steer. Recent methods le…