Papers by Muhammad Haris Khan
microCLIP: Unsupervised CLIP Adaptation via Coarse-Fine Token Fusion for Fine-Grained Image Classification (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing UA methods for fine-grained image classification rely on coarse-grain visual tokens, which misses fine spatial details. |
| Approach: | They propose a label-free self-training framework that adapts visual features and LLMderived text prototypes using fine-grained cues. |
| Outcome: | The proposed framework improves alignment between finegrained visual regions and rich textual descriptions while updating only layer norms and a tiny head. |
GCA Framework: A GCC Countries–Grounded Dataset and Agentic Pipeline for Climate Decision Support (2026.acl-long)
Copied to clipboard
| Challenge: | Climate decision support systems are weak in region-specific climate knowledge and interaction with geospatial and forecasting tools. |
| Approach: | They propose a framework that unifies a curated multimodal dataset and a tool-augmented agent for climate analysis. |
| Outcome: | The proposed framework improves reliability over general-purpose models on climate tasks in the Gulf region. |
BioVLM: Routing Prompts, Not Parameters, for Cross-Modality Generalization in Biomedical VLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Pretrained biomedical vision–language models perform well on average but often degrade on challenging modalities. |
| Approach: | They propose a prompt-learning framework that improves cross-domain generalization without extensive backbone fine-tuning. |
| Outcome: | BioVLM learns a diverse prompt bank and introduces dynamic prompt selection . it can combine sparse few-shot evidence with rich LLM semantic priors . bioVLM achieves state-of-the-art on 11 MedMNIST+ 2D datasets based on the proposed framework . |
DAMASHA: Detecting AI in Mixed Adversarial Texts via Segmentation with Human-interpretable Attribution (2026.findings-eacl)
Copied to clipboard
| Challenge: | a new framework for mixed authorship detection addresses the challenge of segmenting mixed-authorship text . mixed-authored text detection is a growing concern in the age of advanced large language models . a recent survey highlighted the greater challenges of detecting AI content in realworld settings . |
| Approach: | They propose a framework for mixed authorship detection that integrates stylometric cues, perplexity-driven signals, and structured boundary modeling to accurately segment collaborative human-AI content. |
| Outcome: | The proposed framework improves robustness against adversarial perturbations while revealing limitations. |