4 papers
Rethinking CD: A Reproducibility Study and Extension on the Ineffectiveness of Contrastive Decoding at Mitigating Object Hallucinations in MLLMs
Arnav Bendre, Guneesh Gupta, Kavish Grover +2
Contrastive decoding (CD) has been proposed as a training-free strategy for mitigating object hallucinations in multimodal large language models (MLLMs), with reported gains on ben…
How Many Counterfactuals Does It Take? Probing VLM Hallucinations Through Circuits and Causal Effects
Abhivansh Gupta, Simardeep Singh, Advika Sinha +2
Visual Language Models (VLMs) are known to produce hallucinated predictions that are not grounded in visual evidence, yet existing approaches lack a principled understanding of how…
Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models
Shreyansh Modi, Akshat Tomar, Aarush Aggarwal
Unconditional diffusion models offer powerful generative priors, yet steering them toward aesthetically enhanced outputs remains largely unexplored. We show that h-space patching,…
Statistical Guarantees in Synthetic Data through Conformal Adversarial Generation
Rahul Vishwakarma, Shrey Dharmendra Modi, Vishwanath Seshagiri
The generation of high-quality synthetic data presents significant challenges in machine learning research, particularly regarding statistical fidelity and uncertainty quantificati…