Muhammad Awais

Associate Professor@University of Surrey·英国·OpenReview

研究方向

self-supervised learning · multimodal analysis · vision language pretraining · parameter efficient finetuning of large vision language models · medical imaging · computer vision

Muhammad Awais

Object-Centric Refinement for Enhanced Zero-Shot Segmentation

PAL: Probing Audio Encoders via LLMs - Audio Information Transfer into LLMs

Encoding the LLM Vocabulary Bottleneck

MADGen:Minority Attribute Discovery in Text-to-Image Generative Models

Consistent Region-Informed Self-supervised Pretraining

C3R: Channel Conditioned Cell Representations for unified evaluation in microscopy imaging

Can Models Learn From Arbitrary Pairs?

Diff-ID: Identity-Consistent Facial Image Generation and Morphing via Diffusion Models

RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation

CG-SSL: Concept-Guided Self-Supervised Learning

SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning

A PATCH LEVEL PERSPECTIVE OF PROMPT TUNING

Concept Denoising Score Matching for Responsible Text-to-Image Generation