Searcharxiv⌕ Search

arXiv subjects

Kai Jin

Publications and source records attributed to Kai Jin.

At least 19 recordsLinked to original sources
arXiv2026

From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities

Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence. However, most existing math benchmarks evaluate only final answers. This outcome-oriented evaluation provides limited diagnostic value for identifying process-level failures or rigorous logic, failing to guide the transformation of LLMs into robust agents. To bridge this gap, we present a process-level benchmark designed to evaluate the inherent agentic mathematical reasoning abilities of LLMs. Our framework aligns problem-solving agentic behaviors with a structured taxonomy of reusable mathematical atomic capabilities. We design a comprehensive suite of planning, action, and feedback tasks across both textual and multimodal contexts, supported by an automated pipeline that synthesizes high-quality trajectories and produces fine-grained annotations via controlled LLM rewriting. Experiments reveal that models with similar end-to-end accuracy can exhibit markedly different agentic capability profiles. This demonstrates that process-level evaluation is crucial for interpreting the true potential of LLMs and guiding the development of next-generation mathematical agents.

cs.AI↗
arXiv2026

RASLF: Representation-Aware State Space Model for Light Field Super-Resolution

Current SSM-based light field super-resolution (LFSR) methods often fail to fully leverage the complementarity among various LF representations, leading to the loss of fine textures and geometric misalignments across views. To address these issues, we propose RASLF, a representation-aware state-space framework that explicitly models structural correlations across multiple LF representations. Specifically, a Progressive Geometric Refinement (PGR) block is created that uses a panoramic epipolar representation to explicitly encode multi-view parallax differences, thereby enabling integration across different LF representations. Furthermore, we introduce a Representation Aware Asymmetric Scanning (RAAS) mechanism that dynamically adjusts scanning paths based on the physical properties of different representation spaces, optimizing the balance between performance and efficiency through path pruning. Additionally, a Dual-Anchor Aggregation (DAA) module improves hierarchical feature flow, reducing redundant deeplayer features and prioritizing important reconstruction information. Experiments on various public benchmarks show that RASLF achieves the highest reconstruction accuracy while remaining highly computationally efficient.

cs.CV↗
arXiv2026

EyeWorld: A Generative World Model of Ocular State and Dynamics

Ophthalmic decision-making depends on subtle lesion-scale cues interpreted across multimodal imaging and over time, yet most medical foundation models remain static and degrade under modality and acquisition shifts. Here we introduce EyeWorld, a generative world model that conceptualizes the eye as a partially observed dynamical system grounded in clinical imaging. EyeWorld learns an observation-stable latent ocular state shared across modalities, unifying fine-grained parsing, structure-preserving cross-modality translation and quality-robust enhancement within a single framework. Longitudinal supervision further enables time-conditioned state transitions, supporting forecasting of clinically meaningful progression while preserving stable anatomy. By moving from static representation learning to explicit dynamical modeling, EyeWorld provides a unified approach to robust multimodal interpretation and prognosis-oriented simulation in medicine.

cs.CV↗
arXiv2026

EyeAgent: An Agentic AI System for Multimodal Clinical Decision Support in Ophthalmology

Artificial intelligence has shown promise in medical imaging, yet most existing systems lack flexibility, interpretability, and adaptability - challenges especially pronounced in ophthalmology, where diverse imaging modalities are essential. We present EyeAgent, the first agentic AI framework for comprehensive and interpretable clinical decision support in ophthalmology. Using a large language model (DeepSeek-V3) as its central reasoning engine, EyeAgent interprets user queries and dynamically orchestrates 53 validated ophthalmic tools across 23 imaging modalities for diverse tasks including classification, segmentation, detection, image/report generation, and quantitative analysis. Stepwise ablation analysis demonstrated a progressive improvement in diagnostic accuracy, rising from a baseline of 69.71% (using only 5 general tools) to 80.79% when the full suite of 53 specialized tools was integrated. In an expert rating study on 200 real-world clinical cases, EyeAgent achieved 93.7% tool selection accuracy and received expert ratings of more than 88% across accuracy, completeness, safety, reasoning, and interpretability. In human-AI collaboration, EyeAgent matched or exceeded the performance of senior ophthalmologists and, when used as an assistant, improved overall diagnostic accuracy by 18.51% and report quality scores by 19%, with the greatest benefit observed among junior ophthalmologists. These findings establish EyeAgent as a scalable and trustworthy AI framework for ophthalmology and provide a blueprint for modular, multimodal, and clinically aligned next-generation AI systems.

cs.HC↗
arXiv2026

Optimal Allocations under Strongly Pigou-Dalton Criteria: Hidden Layer Structure & Efficient Combinatorial Approach

We investigate optimal social welfare allocations of $m$ items to $n$ agents with binary additive or submodular valuations. For binary additive valuations, we prove that the set of optimal allocations coincides with the set of so-called \emph{stable allocations}, as long as the employed criterion for evaluating social welfare is strongly Pigou-Dalton (SPD) and symmetric. Many common criteria are SPD and symmetric, such as Nash social welfare, leximax, leximin, Gini index, entropy, and envy sum. We also design efficient algorithms for finding a stable allocation, including an $O(m^2n)$ time algorithm for the case of indivisible items, and an $O(m^2n^5)$ time one for the case of divisible items. The first is faster than the existing algorithms or has a simpler analysis. The latter is the first combinatorial algorithm for that problem. It utilizes a hidden layer partition of items and agents admitted by all stable allocations, and cleverly reduces the case of divisible items to the case of indivisible items.In addition, we show that the profiles of different optimal allocations have a small Chebyshev distance, which is 0 for the case of divisible items under binary additive valuations, and is at most 1 for the case of indivisible items under binary submodular valuations.

cs.GT↗
arXiv2025

Discrete Effort Distribution via Regret-enabled Greedy Algorithm

This paper addresses resource allocation problem with a separable objective function under a single linear constraint, formulated as maximizing $\sum_{j=1}^{n}R_j(x_j)$ subject to $\sum_{j=1}^{n}x_j=k$ and $x_j\in\{0,\dots,m\}$. While classical dynamic programming approach solves this problem in $O(n^2m^2)$ time, we propose a regret-enabled greedy algorithm that achieves $O(n\log n)$ time when $m=O(1)$. The algorithm significantly outperforms traditional dynamic programming for small $m$. Our algorithm actually solves the problem for all $k~(0\leq k\leq nm)$ in the mentioned time.

cs.DS↗
arXiv2025

Neovascularization Segmentation via a Multilateral Interaction-Enhanced Graph Convolutional Network

Choroidal neovascularization (CNV), a primary characteristic of wet age-related macular degeneration (wet AMD), represents a leading cause of blindness worldwide. In clinical practice, optical coherence tomography angiography (OCTA) is commonly used for studying CNV-related pathological changes, due to its micron-level resolution and non-invasive nature. Thus, accurate segmentation of CNV regions and vessels in OCTA images is crucial for clinical assessment of wet AMD. However, challenges existed due to irregular CNV shapes and imaging limitations like projection artifacts, noises and boundary blurring. Moreover, the lack of publicly available datasets constraints the CNV analysis. To address these challenges, this paper constructs the first publicly accessible CNV dataset (CNVSeg), and proposes a novel multilateral graph convolutional interaction-enhanced CNV segmentation network (MTG-Net). This network integrates both region and vessel morphological information, exploring semantic and geometric duality constraints within the graph domain. Specifically, MTG-Net consists of a multi-task framework and two graph-based cross-task modules: Multilateral Interaction Graph Reasoning (MIGR) and Multilateral Reinforcement Graph Reasoning (MRGR). The multi-task framework encodes rich geometric features of lesion shapes and surfaces, decoupling the image into three task-specific feature maps. MIGR and MRGR iteratively reason about higher-order relationships across tasks through a graph mechanism, enabling complementary optimization for task-specific objectives. Additionally, an uncertainty-weighted loss is proposed to mitigate the impact of artifacts and noise on segmentation accuracy. Experimental results demonstrate that MTG-Net outperforms existing methods, achieving a Dice socre of 87.21\% for region segmentation and 88.12\% for vessel segmentation.

cs.CV↗
arXiv2025

$L^2$FMamba: Lightweight Light Field Image Super-Resolution with State Space Model

Transformers bring significantly improved performance to the light field image super-resolution task due to their long-range dependency modeling capability. However, the inherently high computational complexity of their core self-attention mechanism has increasingly hindered their advancement in this task. To address this issue, we first introduce the LF-VSSM block, a novel module inspired by progressive feature extraction, to efficiently capture critical long-range spatial-angular dependencies in light field images. LF-VSSM successively extracts spatial features within sub-aperture images, spatial-angular features between sub-aperture images, and spatial-angular features between light field image pixels. On this basis, we propose a lightweight network, $L^2$FMamba (Lightweight Light Field Mamba), which integrates the LF-VSSM block to leverage light field features for super-resolution tasks while overcoming the computational challenges of Transformer-based approaches. Extensive experiments on multiple light field datasets demonstrate that our method reduces the number of parameters and complexity while achieving superior super-resolution performance with faster inference speed.

eess.IV↗
arXiv2025

Sum-of-Max Chain Partition of a Tree

Path partition problems on trees have found various applications. In this paper, we present an $O(n \log n)$ time algorithm for solving the following variant of path partition problem: given a rooted tree of $n$ nodes $1, \ldots, n$, where vertex $i$ is associated with a weight $w_i$ and a cost $s_i$, partition the tree into several disjoint chains $C_1,\ldots,C_k$, so that the weight of each chain is no more than a threshold $w_0$ and the sum of the largest $s_i$ in each chain is minimized. We also generalize the algorithm to the case where the cost of a chain is determined by the $s_i$ of the vertex with the highest rank in the chain, which can be determined by an arbitrary total order defined on all nodes instead of the value of $s_i$.

cs.DS↗
arXiv2025

DeepSeek-R1 Outperforms Gemini 2.0 Pro, OpenAI o1, and o3-mini in Bilingual Complex Ophthalmology Reasoning

Purpose: To evaluate the accuracy and reasoning ability of DeepSeek-R1 and three other recently released large language models (LLMs) in bilingual complex ophthalmology cases. Methods: A total of 130 multiple-choice questions (MCQs) related to diagnosis (n = 39) and management (n = 91) were collected from the Chinese ophthalmology senior professional title examination and categorized into six topics. These MCQs were translated into English using DeepSeek-R1. The responses of DeepSeek-R1, Gemini 2.0 Pro, OpenAI o1 and o3-mini were generated under default configurations between February 15 and February 20, 2025. Accuracy was calculated as the proportion of correctly answered questions, with omissions and extra answers considered incorrect. Reasoning ability was evaluated through analyzing reasoning logic and the causes of reasoning error. Results: DeepSeek-R1 demonstrated the highest overall accuracy, achieving 0.862 in Chinese MCQs and 0.808 in English MCQs. Gemini 2.0 Pro, OpenAI o1, and OpenAI o3-mini attained accuracies of 0.715, 0.685, and 0.692 in Chinese MCQs (all P<0.001 compared with DeepSeek-R1), and 0.746 (P=0.115), 0.723 (P=0.027), and 0.577 (P<0.001) in English MCQs, respectively. DeepSeek-R1 achieved the highest accuracy across five topics in both Chinese and English MCQs. It also excelled in management questions conducted in Chinese (all P<0.05). Reasoning ability analysis showed that the four LLMs shared similar reasoning logic. Ignoring key positive history, ignoring key positive signs, misinterpretation medical data, and too aggressive were the most common causes of reasoning errors. Conclusion: DeepSeek-R1 demonstrated superior performance in bilingual complex ophthalmology reasoning tasks than three other state-of-the-art LLMs. While its clinical applicability remains challenging, it shows promise for supporting diagnosis and clinical decision-making.

cs.CL↗
arXiv2025

Can OpenAI o1 Reason Well in Ophthalmology? A 6,990-Question Head-to-Head Evaluation Study

Question: What is the performance and reasoning ability of OpenAI o1 compared to other large language models in addressing ophthalmology-specific questions? Findings: This study evaluated OpenAI o1 and five LLMs using 6,990 ophthalmological questions from MedMCQA. O1 achieved the highest accuracy (0.88) and macro-F1 score but ranked third in reasoning capabilities based on text-generation metrics. Across subtopics, o1 ranked first in ``Lens'' and ``Glaucoma'' but second to GPT-4o in ``Corneal and External Diseases'', ``Vitreous and Retina'' and ``Oculoplastic and Orbital Diseases''. Subgroup analyses showed o1 performed better on queries with longer ground truth explanations. Meaning: O1's reasoning enhancements may not fully extend to ophthalmology, underscoring the need for domain-specific refinements to optimize performance in specialized fields like ophthalmology.

cs.CL↗
arXiv2024

EyeCLIP: A visual-language foundation model for multi-modal ophthalmic image analysis

Early detection of eye diseases like glaucoma, macular degeneration, and diabetic retinopathy is crucial for preventing vision loss. While artificial intelligence (AI) foundation models hold significant promise for addressing these challenges, existing ophthalmic foundation models primarily focus on a single modality, whereas diagnosing eye diseases requires multiple modalities. A critical yet often overlooked aspect is harnessing the multi-view information across various modalities for the same patient. Additionally, due to the long-tail nature of ophthalmic diseases, standard fully supervised or unsupervised learning approaches often struggle. Therefore, it is essential to integrate clinical text to capture a broader spectrum of diseases. We propose EyeCLIP, a visual-language foundation model developed using over 2.77 million multi-modal ophthalmology images with partial text data. To fully leverage the large multi-modal unlabeled and labeled data, we introduced a pretraining strategy that combines self-supervised reconstructions, multi-modal image contrastive learning, and image-text contrastive learning to learn a shared representation of multiple modalities. Through evaluation using 14 benchmark datasets, EyeCLIP can be transferred to a wide range of downstream tasks involving ocular and systemic diseases, achieving state-of-the-art performance in disease classification, visual question answering, and cross-modal retrieval. EyeCLIP represents a significant advancement over previous methods, especially showcasing few-shot, even zero-shot capabilities in real-world long-tail scenarios.

cs.CV↗
arXiv2024

Scheduling two types of jobs with minimum makespan

We consider scheduling two types of jobs (A-job and B-job) to $p$ machines and minimizing their makespan. A group of same type of jobs processed consecutively by a machine is called a batch. For machine $v$, processing $x$ A-jobs in a batch takes $k^A_vx^2$ time units for a given speed $k^A_v$, and processing $x$ B-jobs in a batch takes $k^B_vx^2$ time units for a given speed $k^B_v$. We give an $O(n^2p\log(n))$ algorithm based on dynamic programming and binary search for solving this problem, where $n$ denotes the maximal number of A-jobs and B-jobs to be distributed to the machines. Our algorithm also fits the easier linear case where each batch of length $x$ of $A$-jobs takes $k^A_v x$ time units and each batch of length $x$ of $B$-jobs takes $k^B_vx$ time units. The running time is the same as the above case.

cs.DS↗
arXiv2024

A technique for solving the polygon inclusion problems

We propose a technique called Rotate-and-Kill for solving the polygon inclusion and circumscribing problems. By applying this technique, we obtain $O(n)$ time algorithms for computing (1) the maximum area triangle in a given $n$-sided convex polygon $P$, (2) the minimum area triangle enclosing $P$, (3) the minimum area triangle enclosing $P$ touching edge-to-edge, i.e. the minimum area triangle that is the intersection of three half-planes out of the $n$ half-planes defining $P$, and (4) the minimum perimeter triangle enclosing $P$ touching edge-to-edge. Our algorithm for computing the maximum area triangle is simpler than the alternatives given in [Chandran and Mount, IJCGA'92] and [Kallus, arXiv'17]. Our algorithms for computing the minimum area or perimeter triangle enclosing $P$ touching edge-to-edge improve the $O(n\log n)$ or $O(n\log^2n)$ time algorithms given in [Boyce \emph{et al.}, STOC'82], [Aggarwal \emph{et al.}, Algorithmica'87], [Aggarwal and J. Park., FOCS'88], [Aggarwal \emph{et al.}, DCG'94], and [Schieber, SODA'95].

cs.CG↗
arXiv2024

Simple $k$-crashing Plan with a Good Approximation Ratio

In project management, a project is typically described as an activity-on-edge network (AOE network), where each activity / job is represented as an edge of some network $N$ (which is a DAG). Some jobs must be finished before others can be started, as described by the topology structure of $N$. It is known that job $j_i$ in normal speed would require $b_i$ days to be finished after it is started. Given the network $N$ with the associated edge lengths $b_1,\ldots,b_m$, the duration of the project is determined, which equals the length of the critical path (namely, the longest path) of $N$. To speed up the project (i.e. reduce the duration), the manager can crash a few jobs (namely, reduce the length of the corresponding edges) by investing extra resources into that job. However, the time for completing $j_i$ has a lower bound due to technological limits -- it requires at least $a_i$ days to be completed. Moreover, it is expensive to buy resources. Given $N$ and an integer $k\geq 1$, the $k$-crashing problem asks the minimum amount of resources required to speed up the project by $k$ days. We show a simple and efficient algorithm with an approximation ratio $\frac{1}{1}+\ldots+\frac{1}{k}$ for this problem. We also study a related problem called $k$-LIS, in which we are given a sequence $ω$ of numbers and we aim to find $k$ disjoint increasing subsequence of $ω$ with the largest total length. We show a $(1-\frac{1}{e})$-approximation algorithm which is simple and efficient.

cs.DS↗
arXiv2023

Masked Contrastive Reconstruction for Cross-modal Medical Image-Report Retrieval

Cross-modal medical image-report retrieval task plays a significant role in clinical diagnosis and various medical generative tasks. Eliminating heterogeneity between different modalities to enhance semantic consistency is the key challenge of this task. The current Vision-Language Pretraining (VLP) models, with cross-modal contrastive learning and masked reconstruction as joint training tasks, can effectively enhance the performance of cross-modal retrieval. This framework typically employs dual-stream inputs, using unmasked data for cross-modal contrastive learning and masked data for reconstruction. However, due to task competition and information interference caused by significant differences between the inputs of the two proxy tasks, the effectiveness of representation learning for intra-modal and cross-modal features is limited. In this paper, we propose an efficient VLP framework named Masked Contrastive and Reconstruction (MCR), which takes masked data as the sole input for both tasks. This enhances task connections, reducing information interference and competition between them, while also substantially decreasing the required GPU memory and training time. Moreover, we introduce a new modality alignment strategy named Mapping before Aggregation (MbA). Unlike previous methods, MbA maps different modalities to a common feature space before conducting local feature aggregation, thereby reducing the loss of fine-grained semantic information necessary for improved modality alignment. Qualitative and quantitative experiments conducted on the MIMIC-CXR dataset validate the effectiveness of our approach, demonstrating state-of-the-art performance in medical cross-modal retrieval tasks.

cs.CV↗