9 papers
Training-Free Speech-Centric Omni Understanding with Frozen VLMs
Ankan Deria, Hanoona Rasheed, Xilin He +2
Audio-visual understanding remains challenging because models must jointly interpret spoken content, visual events, and their temporal relationships. Existing omni models typically…
SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-Training
Komal Kumar, Ankan Deria, Abhishek Basu +3
Diffusion models have been widely studied for removing unsafe content learned during pre-training. Existing methods require expensive supervised data, either unsafe-text paired wit…
TriALS: Triphasic-Aided Liver Lesion Segmentation Benchmark in Non-Contrast CT
Marawan Elbatel, Mohamed Ghonim, Jiaji Mao +62
Automated segmentation of liver lesions on non-contrast computed tomography (NCCT) is clinically important but fundamentally challenging, particularly in low-resource settings acro…
See Fair, Speak Truth: Equitable Attention Improves Grounding and Reduces Hallucination in Vision-Language Alignment
Mohammad Anas Azeez, Ankan Deria, Zohaib Hasan Siddiqui +5
Multimodal large language models (MLLMs) frequently hallucinate objects that are absent from the visual input, often because attention during decoding is disproportionately drawn t…
CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning
Ankan Deria, Komal Kumar, Xilin He +4
Recent vision-language models (VLMs) typically rely on a single vision encoder trained with contrastive image-text objectives, such as CLIP-style pretraining. While contrastive enc…
MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images
Ankan Deria, Komal Kumar, Adinath Madhavrao Dukre +3
Multimodal large language models have advanced rapidly, but their adoption in medicine is constrained by limited domain coverage, imperfect modality alignment, and insufficient gro…
Robust Atypical Mitosis Classification with DenseNet121: Stain-Aware Augmentation and Hybrid Loss for Domain Generalization
Adinath Dukre, Ankan Deria, Yutong Xie +1
Atypical mitotic figures are important biomarkers of tumor aggressiveness in histopathology, yet reliable recognition remains challenging due to severe class imbalance and variabil…
MuGa-VTON: Multi-Garment Virtual Try-On via Diffusion Transformers with Prompt Customization
Ankan Deria, Dwarikanath Mahapatra, Behzad Bozorgtabar +3
Virtual try-on seeks to generate photorealistic images of individuals in desired garments, a task that must simultaneously preserve personal identity and garment fidelity for pract…
Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning
Ankan Deria, Adinath Madhavrao Dukre, Feilong Tang +5
Despite significant advances in inference-time search for vision-language models (VLMs), existing approaches remain both computationally expensive and prone to unpenalized, low-con…