25 papers
GlucoPRISM: Protocol-Supervised Pretraining for Cross-Cohort Glucose Transfer
Adinath Madhavrao Dukre, Abdullah Mohammad, Yifan Lu +3
Continuous glucose monitoring (CGM) foundation models encode each day as one vector that mixes who the person is, what happened that day and how the sensor measured it, so measurem…
What Makes Recurrence Effective in Looped Language Models?
Xinlin Zhuang, Siyuan Wang, Imran Razzak +1
Looped language models (LoopLMs) increase computational depth through parameter sharing, offering a path to scale inference computation without adding parameters. However, it remai…
DoAtlas-2: A Foundation for Self-Evolving Causal Biomedical Discovery
Yulong Li, Rong Xia, Yuxuan Zhang +12
We introduce DoAtlas-2, a foundation for self-evolving causal biomedical discovery that organizes knowledge around causal mechanisms and advances through external evidence from hum…
MedRoundsQA: A Persona and Difficulty Aware Evaluation for Multi-Turn Medical Consultations
Youssef Mohamed, Ahmed Heakl, Qinrong Cui +13
Medical benchmarks are dominated by single-turn, multiple-choice clinical cases that poorly reflect real consultations. Practically, clinicians elicit evidence interactively and pa…
Grounding Isn't Knowing: Do VLMs Need Object Localization for Spatial Reasoning?
Xiwei Liu, Yulong Li, Xinlin Zhuang +5
Vision-language models (VLMs) can answer spatial questions, yet the mechanisms connecting object grounding to spatial reasoning remain poorly understood. It is underexplored whethe…
AsyTO: Asymmetric Temporal Operator for Parameter-Efficient Multivariate Time Series Forecasting
Xiachong Lin, Du Yin, Hao Xue +5
Multivariate time-series forecasting faces a structural dilemma: sharing one temporal predictor across variables is parameter-efficient but forces heterogeneous variables through a…
On the Robustness of Temporal Vision-Language Models for Surgical Endoscopy Videos
Darakshan Rashid, Raza Imam, Ufaq Khan +9
Temporal vision-language models (TVLMs) offer a reusable, prompt-based interface for surgical video understanding, yet, their robustness under clinically realistic acquisition arti…
Evaluating LLM Personalization via Semantic Constraint Verification
Xuran Li, Guanqin Zhang, Imran Razzak +4
Current evaluation paradigms for Large Language Model (LLM) personalization rely heavily on brittle surface-matching metrics or computationally expensive LLM-as-a-judge protocols,…
Knowledge Graph Enhanced Memory-Augmented Retrieval for Long Context Modeling
Ghadir Alselwi, Basem Suleiman, Hao Xue +4
Long-context language modeling requires not only extending context windows but maintaining coherent understanding of entity states and relationships across thousands of tokens -- a…
DocAtlas: Multilingual Document Understanding Across 80+ Languages
Ahmed Heakl, Youssef Mohamed, Abdullah Sohail +6
Multilingual document understanding remains limited for low-resource languages due to scarce training data and model-based annotation pipelines that perpetuate existing biases. We…
AMO: Operator-level Adaptive Muon Orthogonalization
Xinlin Zhuang, Panyi Ouyang, Yichen Li +7
Muon has recently emerged as a competitive alternative to AdamW for large-scale pre-training, with orthogonalization via Newton-Schulz (NS) iteration as its core operation. Standar…
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…
MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs
Ruiyi Yang, Zechen Li, Hao Xue +2
Self-evolving language-model agents must decide what to learn next and how to preserve what they have learned across iterations. Existing systems typically carry this cross-iterati…
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…
SAGE: Sustainable Agent-Guided Expert-tuning for Culturally Attuned Translation in Low-Resource Southeast Asia
Zhixiang Lu, Chong Zhang, Yulong Li +5
The vision of an inclusive World Wide Web is impeded by a severe linguistic divide, particularly for communities in low-resource regions of Southeast Asia. While large language mod…
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…
DeLo: Dual Decomposed Low-Rank Experts Collaboration for Continual Missing Modality Learning
Xiwei Liu, Yulong Li, Feilong Tang +1
Adapting Large Multimodal Models (LMMs) to real-world scenarios poses the dual challenges of learning from sequential data streams while handling frequent modality incompleteness,…
ClinCoT: Clinical-Aware Visual Chain-of-Thought for Medical Vision Language Models
Xiwei Liu, Yulong Li, Xinlin Zhuang +5
Medical Vision-Language Models have shown promising potential in clinical decision support, yet they remain prone to factual hallucinations due to insufficient grounding in localiz…
CMSA-Net: Causal Multi-scale Aggregation with Adaptive Multi-source Reference for Video Polyp Segmentation
Tong Wang, Yaolei Qi, Siwen Wang +3
Video polyp segmentation (VPS) is an important task in computer-aided colonoscopy, as it helps doctors accurately locate and track polyps during examinations. However, VPS remains…
Mitigating Preference Leakage via Strict Estimator Separation for Normative Generative Ranking
Dalia Nahhas, Xiaohao Cai, Imran Razzak +1
In Generative Information Retrieval (GenIR), the bottleneck has shifted from generation to the selection of candidates, particularly for normative criteria such as cultural relevan…
DoAtlas-1: A Causal Compilation Paradigm for Clinical AI
Yulong Li, Jianxu Chen, Xiwei Liu +9
Medical foundation models generate narrative explanations but cannot quantify intervention effects, detect evidence conflicts, or validate literature claims, limiting clinical audi…
LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs
Behzad Bozorgtabar, Dwarikanath Mahapatra, Sudipta Roy +3
Medical vision-language models (VLMs) are strong zero-shot recognizers for medical imaging, but their reliability under domain shift hinges on calibrated uncertainty with guarantee…
Attention-Driven Framework for Non-Rigid Medical Image Registration
Muhammad Zafar Iqbal, Ghazanfar Farooq Siddiqui, Anwar Ul Haq +1
Deformable medical image registration is a fundamental task in medical image analysis with applications in disease diagnosis, treatment planning, and image-guided interventions. De…