arXiv subjects

Lei Chen

Publications and source records attributed to Lei Chen.

At least 145 records · Page 8Linked to original sources

arXiv2026

Graph-Structured Driven Dual Adaptation for Mitigating Popularity Bias

Popularity bias is a common challenge in recommender systems. It often causes unbalanced item recommendation performance and intensifies the Matthew effect. Due to limited user-item interactions, unpopular items are frequently constrained to the embedding neighborhoods of only a few users, leading to representation collapse and weakening the model's generalization. Although existing supervised alignment and reweighting methods can help mitigate this problem, they still face two major limitations: (1) they overlook the inherent variability among different Graph Convolutional Networks (GCNs) layers, which can result in negative gains in deeper layers; (2) they rely heavily on fixed hyperparameters to balance popular and unpopular items, limiting adaptability to diverse data distributions and increasing model complexity. To address these challenges, we propose Graph-Structured Dual Adaptation Framework (GSDA), a dual adaptive framework for mitigating popularity bias in recommendation. Our theoretical analysis shows that supervised alignment in GCNs is hindered by the over-smoothing effect, where the distinction between popular and unpopular items diminishes as layers deepen, reducing the effectiveness of alignment at deeper levels. To overcome this limitation, GSDA integrates a hierarchical adaptive alignment mechanism that counteracts entropy decay across layers together with a distribution-aware contrastive weighting strategy based on the Gini coefficient, enabling the model to adapt its debiasing strength dynamically without relying on fixed hyperparameters. Extensive experiments on three benchmark datasets demonstrate that GSDA effectively alleviates popularity bias while consistently outperforming state-of-the-art methods in recommendation performance.

cs.IR↗

arXiv2026

A unified multimodal understanding and generation model for cross-disciplinary scientific research

Scientific discovery increasingly relies on integrating heterogeneous, high-dimensional data across disciplines nowadays. While AI models have achieved notable success across various scientific domains, they typically remain domain-specific or lack the capability of simultaneously understanding and generating multimodal scientific data, particularly for high-dimensional data. Yet, many pressing global challenges and scientific problems are inherently cross-disciplinary and require coordinated progress across multiple fields. Here, we present FuXi-Uni, a native unified multimodal model for scientific understanding and high-fidelity generation across scientific domains within a single architecture. Specifically, FuXi-Uni aligns cross-disciplinary scientific tokens within natural language tokens and employs science decoder to reconstruct scientific tokens, thereby supporting both natural language conversation and scientific numerical prediction. Empirically, we validate FuXi-Uni in Earth science and Biomedicine. In Earth system modeling, the model supports global weather forecasting, tropical cyclone (TC) forecast editing, and spatial downscaling driven by only language instructions. FuXi-Uni generates 10-day global forecasts at 0.25° resolution that outperform the SOTA physical forecasting system. It shows superior performance for both TC track and intensity prediction relative to the SOTA physical model, and generates high-resolution regional weather fields that surpass standard interpolation baselines. Regarding biomedicine, FuXi-Uni outperforms leading multimodal large language models on multiple biomedical visual question answering benchmarks. By unifying heterogeneous scientific modalities within a native shared latent space while maintaining strong domain-specific performance, FuXi-Uni provides a step forward more general-purpose, multimodal scientific models.

cs.AI↗

arXiv2026

Circle action of the punctured mapping class group and cross homomorphism

In the following short note, we give a new geometric interpretation of the generator of the infinite cyclic group $H^1(\text{Mod}(S_{g,1});H^1(S_g;\mathbb{Z}))$ (this computation is proved by Morita). There are several constructions of this class given by Earle, Morita, Trapp and Furuta. The construction we give here uses the action of $\text{Mod}(S_{g,1})$ on the circle and its rotation numbers. We also show that our construction is the same as the construction by Furuta and Trapp using winding numbers.

math.GT↗

arXiv2026

Optimizing Retrieval for RAG via Reinforcement Learning

As retrieval-augmented generation (RAG) becomes more widespread, the role of retrieval is shifting from retrieving information for human browsing to retrieving context for AI reasoning. This shift creates more complex search environments, where relevance is difficult to pre-define. Existing retrievers rely on supervised fine-tuning (SFT) with human labels or synthetic data, resulting in static relevance that struggles to adapt to diverse RAG environments. To address this challenge, we propose R3, a Retrieval framework optimized for RAG through Reinforcement learning (RL). Specifically, we adopt an RL training paradigm that enables the retriever to explore and self-improve within given RAG environments, automating the learning process with minimal manual experimentation or tuning effort. Extensive experiments across diverse tasks demonstrate that R3 improves RAG performance by 5.2% over the original retriever and surpasses state-of-the-art retrievers by 4.9%, while achieving comparable results to LLM-augmented retrieval and RAG systems built on post-trained or instruction-tuned LLMs. It is both efficient and practical, requiring only 4 GPUs and completing training within a single day.

cs.CL↗

arXiv2025

A DeepSeek-Powered AI System for Automated Chest Radiograph Interpretation in Clinical Practice

A global shortage of radiologists has been exacerbated by the significant volume of chest X-ray workloads, particularly in primary care. Although multimodal large language models show promise, existing evaluations predominantly rely on automated metrics or retrospective analyses, lacking rigorous prospective clinical validation. Janus-Pro-CXR (1B), a chest X-ray interpretation system based on DeepSeek Janus-Pro model, was developed and rigorously validated through a multicenter prospective trial (NCT07117266). Our system outperforms state-of-the-art X-ray report generation models in automated report generation, surpassing even larger-scale models including ChatGPT 4o (200B parameters), while demonstrating reliable detection of six clinically critical radiographic findings. Retrospective evaluation confirms significantly higher report accuracy than Janus-Pro and ChatGPT 4o. In prospective clinical deployment, AI assistance significantly improved report quality scores, reduced interpretation time by 18.3% (P < 0.001), and was preferred by a majority of experts in 54.3% of cases. Through lightweight architecture and domain-specific optimization, Janus-Pro-CXR improves diagnostic reliability and workflow efficiency, particularly in resource-constrained settings. The model architecture and implementation framework will be open-sourced to facilitate the clinical translation of AI-assisted radiology solutions.

cs.AI↗

arXiv2025

Various Vicsek Models with Underlying Network Characteristics

Collective motion is a fundamental phenomenon in biological swarms. As a framework for studying synchronization in motions, the Vicsek model is simple and efficient, assuming isotropic interactions with a complete field of view. Drawing inspiration from natural swarms, we incorporate realistic constraints into the model. By analysing the interaction structures from the complex network perspective, we demonstrate that models with the homogeneous interaction rules naturally form Erdos-Renyi networks, whereas the introduction of heterogeneity leads to Barabasi-Albert networks. Furthermore, we discover that the model's synchronization is fundamentally governed by the average degree of the interaction network. Through a comparative analysis across these topologies, we identify a stretched-exponential relationship between the average degree and the synchronization metrics.

physics.soc-ph↗

arXiv2025

A Large Language Model Based Method for Complex Logical Reasoning over Knowledge Graphs

Reasoning over knowledge graphs (KGs) with first-order logic (FOL) queries is challenging due to the inherent incompleteness of real-world KGs and the compositional complexity of logical query structures. Most existing methods rely on embedding entities and relations into continuous geometric spaces and answer queries via differentiable set operations. While effective for simple query patterns, these approaches often struggle to generalize to complex queries involving multiple operators, deeper reasoning chains, or heterogeneous KG schemas. We propose ROG (Reasoning Over knowledge Graphs with large language models), an ensemble-style framework that combines query-aware KG neighborhood retrieval with large language model (LLM)-based chain-of-thought reasoning. ROG decomposes complex FOL queries into sequences of simpler sub-queries, retrieves compact, query-relevant subgraphs as contextual evidence, and performs step-by-step logical inference using an LLM, avoiding the need for task-specific embedding optimization. Experiments on standard KG reasoning benchmarks demonstrate that ROG consistently outperforms strong embedding-based baselines in terms of mean reciprocal rank (MRR), with particularly notable gains on high-complexity query types. These results suggest that integrating structured KG retrieval with LLM-driven logical reasoning offers a robust and effective alternative for complex KG reasoning tasks.

cs.CL↗

arXiv2025

Quasiprimitive and bi-quasiprimitive highly-arc-transitive digraphs and finite simple groups

We extend the notion of an $H$-normal quotient digraph of an $H$-vertex-transitive digraph to that of an $H$-subnormal quotient digraph. Using these concepts, together with bipartite halves of bipartite digraphs, we show that, for each finite connected $H$-vertex-transitive, $(H,s)$-arc-transitive digraph with $s\geqslant6$, either some $H$-normal quotient is a directed cycle of length at least $3$, or there is an $(L,t)$-arc-transitive digraph with $t\geqslant (s-3)/2$, and $L$ a vertex-quasiprimitive almost simple group with socle a composition factor of $H$. This connection demonstrates that, to understand finite $s$-arc-transitive digraphs with large $s$, those admitting a vertex-quasiprimitive almost simple $s$-arc-transitive subgroup of automorphisms play a central role. We show that for each $s$ and each odd valency $k$, there are infinitely many $(H,s)$-arc-transitive digraphs of valency $k$ with $H$ a finite alternating group. In addition we discovered a novel construction which takes as input a connected non-bipartite $H$-vertex-transitive, $(H,s)$-arc-transitive digraph, and outputs a connected bipartite $G$-vertex-transitive, $(G,2s)$-arc-transitive digraph with $G=(H\times H).2$. This leads to construction of vertex-bi-quasiprimitive $s$-arc-transitive digraphs, for arbitrarily large $s$. Our investigations yield several new open problems.

math.CO↗

arXiv2025

Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR

Reading text from images or scanned documents via OCR models has been a longstanding focus of researchers. Intuitively, text reading is perceived as a straightforward perceptual task, and existing work primarily focuses on constructing enriched data engineering to enhance SFT capabilities. In this work, we observe that even advanced OCR models exhibit significantly higher entropy in formatted text (\emph{e.g.}, formula, table, etc.) compared to plain text, often by an order of magnitude. These statistical patterns reveal that advanced OCR models struggle with high output uncertainty when dealing with format sensitive document, suggesting that reasoning over diverse reading pathways may improve OCR performance. To address this, we propose format decoupled reinforcement learning (FD-RL), which leverages high-entropy patterns for targeted optimization. Our approach employs entropy-based data filtration strategy to identify format-intensive instances, and adopt format decoupled rewards tailored to different format types, enabling format-level validation rather than token-level memorization. FD-RL achieves an average score of 90.41 on OmniDocBench, setting a new record for end-to-end models on this highly popular benchmark. More importantly, we conduct comprehensive ablation studies over data, training, filtering, and rewarding strategies, thoroughly validating their effectiveness.

cs.CV↗

arXiv2025

RelServe: Fast LLM Inference Serving on Relational Data

The use of Large Language Models (LLMs) for querying relational data has given rise to relQuery, a workload pattern that applies templated LLM calls to structured tables. As relQuery services become more widely adopted in applications such as AI-powered spreadsheets, fast response times under concurrent query loads are increasingly important. Unfortunately, current LLM engines face severe latency bottlenecks from Head-of-Line (HoL) blocking across three comparable inference phases: waiting, core running, and tail running. Existing static priority scheduling methods only address HoL blocking during the waiting phase, leaving two critical problems unsolved. First, the absence of a priority update mechanism causes inaccurate prioritization and continued HoL blocking during core execution. Second, suboptimal prefill-decode batching exacerbates HoL blocking in tail execution and worsens latency trade-offs between running and waiting relQueries. To address these problems, we propose RelServe, an optimized LLM engine for low-latency relQuery serving. RelServe features two core innovations: a Dynamic Priority Updater that continuously adjusts priorities while minimizing overhead via statistical approximations, and an Adaptive Batch Arranger that quantitatively evaluates candidate prefill and decode batches to minimize projected average latency. Extensive experiments on four real-world datasets using LLMs ranging from 13B to 70B parameters show that RelServe reduces average serving latency by up to 3.1x compared to vLLM.

cs.DB↗

arXiv2025

InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue

We introduce InteractiveOmni, a unified and open-source omni-modal large language model for audio-visual multi-turn interaction, ranging from 4B to 8B parameters, designed to lead the field of lightweight models by offering comprehensive omni-modal understanding and speech generation capabilities. To achieve this, we integrate the vision encoder, audio encoder, large language model, and speech decoder into a unified model for understanding and generation tasks. We design a multi-stage training strategy to ensure robust cross-modal capabilities, including pre-training for omni-modal understanding, followed by post-training with speech conversation and audio-visual interaction. To enable human-like long-term conversational ability, we meticulously curate a multi-turn training dataset that enhances the model's ability to handle complex and multi-turn interactions. To effectively evaluate the multi-turn memory and speech interaction capabilities, we construct the multi-modal multi-turn memory benchmark and the multi-turn speech interaction benchmark. Experiments demonstrate that InteractiveOmni significantly outperforms leading open-source models and provides a more intelligent multi-turn audio-visual experience, particularly in its long-term memory capabilities. Notably, InteractiveOmni-4B is comparable to the much larger model like Qwen2.5-Omni-7B on general benchmarks, and it can retain 97% of the performance of the InteractiveOmni-8B while utilizing only 50% of the model size. Achieving state-of-the-art results against similarly sized models across image, audio, video understanding, and speech generation tasks, InteractiveOmni is an accessible, open-source foundation for next-generation intelligent interactive systems.

cs.CV↗

arXiv2025

Neural Discrete Representation Learning for Sparse-View CBCT Reconstruction: From Algorithm Design to Prospective Multicenter Clinical Evaluation

Cone beam computed tomography (CBCT)-guided puncture has become an established approach for diagnosing and treating early- to mid-stage thoracic tumours, yet the associated radiation exposure substantially elevates the risk of secondary malignancies. Although multiple low-dose CBCT strategies have been introduced, none have undergone validation using large-scale multicenter retrospective datasets, and prospective clinical evaluation remains lacking. Here, we propose DeepPriorCBCT - a three-stage deep learning framework that achieves diagnostic-grade reconstruction using only one-sixth of the conventional radiation dose. 4102 patients with 8675 CBCT scans from 12 centers were included to develop and validate DeepPriorCBCT. Additionally, a prospective cross-over trial (Registry number: NCT07035977) which recruited 138 patients scheduled for percutaneous thoracic puncture was conducted to assess the model's clinical applicability. Assessment by 11 physicians confirmed that reconstructed images were indistinguishable from original scans. Moreover, diagnostic performance and overall image quality were comparable to those generated by standard reconstruction algorithms. In the prospective trial, five radiologists reported no significant differences in image quality or lesion assessment between DeepPriorCBCT and the clinical standard (all P>0.05). Likewise, 25 interventionalists expressed no preference between model-based and full-sampling images for surgical guidance (Kappa<0.2). Radiation exposure with DeepPriorCBCT was reduced to approximately one-sixth of that with the conventional approach, and collectively, the findings confirm that it enables high-quality CBCT reconstruction under sparse sampling conditions while markedly decreasing intraoperative radiation risk.

cs.CV↗

arXiv2025

LongCat-Flash-Omni Technical Report

We introduce LongCat-Flash-Omni, a state-of-the-art open-source omni-modal model with 560 billion parameters, excelling at real-time audio-visual interaction. By adopting a curriculum-inspired progressive training strategy that transitions from simpler to increasingly complex modality sequence modeling tasks, LongCat-Flash-Omni attains comprehensive multimodal capabilities while maintaining strong unimodal capability. Building upon LongCat-Flash, which adopts a high-performance Shortcut-connected Mixture-of-Experts (MoE) architecture with zero-computation experts, LongCat-Flash-Omni integrates efficient multimodal perception and speech reconstruction modules. Despite its immense size of 560B parameters (with 27B activated), LongCat-Flash-Omni achieves low-latency real-time audio-visual interaction. For training infrastructure, we developed a modality-decoupled parallelism scheme specifically designed to manage the data and model heterogeneity inherent in large-scale multimodal training. This innovative approach demonstrates exceptional efficiency by sustaining over 90% of the throughput achieved by text-only training. Extensive evaluations show that LongCat-Flash-Omni achieves state-of-the-art performance on omni-modal benchmarks among open-source models. Furthermore, it delivers highly competitive results across a wide range of modality-specific tasks, including text, image, and video understanding, as well as audio understanding and generation. We provide a comprehensive overview of the model architecture design, training procedures, and data strategies, and open-source the model to foster future research and development in the community.

cs.MM↗

arXiv2025

The normal closure of a homological genus 0 bounding pair map

Justin Lanier and the authors recently determined the group normally generated by a single bounding pair map of genus $n$. We related this subgroup with the Chillingworth subgroup and the Casson--Morita's $d$ map. In this paper, we extend the results to the case when $n=0$. Let $\mathcal{M}_g^1$ be the mapping class group, $\text{Ch}_g^1$ be the Chillingworth subgroup and $d$ be the Casson--Morita's $d$-map. We show that $\text{Ker}(d)=[\text{Ch}_g^1,\mathcal{M}_g^1]$ and it is generated by a single homological genus 0 bounding pair map. We also construct an element $H_0\in \text{Ch}_g^1$, and show that $\text{Ch}_g^1$ is normally generated by this single element $H_0$.

math.GT↗

arXiv2025

Invested and Potential Magic Resources in Measurement-Based Quantum Computation

Magic states and magic gates are crucial for achieving universal quantum computation, but important questions about how magic resources should be implemented to attain maximal quantum advantage have remained unexplored, especially in the context of measurement-based quantum computation (MQC). This work bridges the gap between MQC and the resource theory of magic by introducing the key concepts of "invested" and "potential" magic resources. The former quantifies the magic cost associated with MQC, serving as both a resource witness and a feasible upper bound for the practical realization, and is gate-order independent; The latter represents the maximal achievable magic resource in a given graph structure defining MQC. We utilize both concepts to analyze the quantum Fourier transform (QFT) and provide a fresh perspective on the universality of MQC, highlighting the crucial role of non-Pauli measurements in injecting magic. In particular, we theoretically prove that high-dimensional graphs can generate an exponential advantage of MQC compared to classical computing. We demonstrate experimentally our theoretical findings in a high-fidelity four-photon setup, surpassing conventional magic state injection (MSI) methods in both qubit efficiency and resource utilization. Our findings pave the way for future research exploring magic resource optimization and novel distillation schemes within the MQC framework, advancing fault-tolerant universal quantum computation.

quant-ph↗

arXiv2025

Mitigating Recommendation Biases via Group-Alignment and Global-Uniformity in Representation Learning

Collaborative Filtering~(CF) plays a crucial role in modern recommender systems, leveraging historical user-item interactions to provide personalized suggestions. However, CF-based methods often encounter biases due to imbalances in training data. This phenomenon makes CF-based methods tend to prioritize recommending popular items and performing unsatisfactorily on inactive users. Existing works address this issue by rebalancing training samples, reranking recommendation results, or making the modeling process robust to the bias. Despite their effectiveness, these approaches can compromise accuracy or be sensitive to weighting strategies, making them challenging to train. In this paper, we deeply analyze the causes and effects of the biases and propose a framework to alleviate biases in recommendation from the perspective of representation distribution, namely Group-Alignment and Global-Uniformity Enhanced Representation Learning for Debiasing Recommendation (AURL). Specifically, we identify two significant problems in the representation distribution of users and items, namely group-discrepancy and global-collapse. These two problems directly lead to biases in the recommendation results. To this end, we propose two simple but effective regularizers in the representation space, respectively named group-alignment and global-uniformity. The goal of group-alignment is to bring the representation distribution of long-tail entities closer to that of popular entities, while global-uniformity aims to preserve the information of entities as much as possible by evenly distributing representations. Our method directly optimizes both the group-alignment and global-uniformity regularization terms to mitigate recommendation biases. Extensive experiments on three real datasets and various recommendation backbones verify the superiority of our proposed framework.

cs.IR↗

arXiv2025

DINOv3-Guided Cross Fusion Framework for Semantic-aware CT generation from MRI and CBCT

Generating synthetic CT images from CBCT or MRI has a potential for efficient radiation dose planning and adaptive radiotherapy. However, existing CNN-based models lack global semantic understanding, while Transformers often overfit small medical datasets due to high model capacity and weak inductive bias. To address these limitations, we propose a DINOv3-Guided Cross Fusion (DGCF) framework that integrates a frozen self-supervised DINOv3 Transformer with a trainable CNN encoder-decoder. It hierarchically fuses global representation of Transformer and local features of CNN via a learnable cross fusion module, achieving balanced local appearance and contextual representation. Furthermore, we introduce a Multi-Level DINOv3 Perceptual (MLDP) loss that encourages semantic similarity between synthetic CT and the ground truth in DINOv3's feature space. Experiments on the SynthRAD2023 pelvic dataset demonstrate that DGCF achieved state-of-the-art performance in terms of MS-SSIM, PSNR and segmentation-based metrics on both MRI$\rightarrow$CT and CBCT$\rightarrow$CT translation tasks. To the best of our knowledge, this is the first work to employ DINOv3 representations for medical image translation, highlighting the potential of self-supervised Transformer guidance for semantic-aware CT synthesis. The code is available at https://github.com/HiLab-git/DGCF.

cs.CV↗

arXiv2025

Token Painter: Training-Free Text-Guided Image Inpainting via Mask Autoregressive Models

Text-guided image inpainting aims to inpaint masked image regions based on a textual prompt while preserving the background. Although diffusion-based methods have become dominant, their property of modeling the entire image in latent space makes it challenging for the results to align well with prompt details and maintain a consistent background. To address these issues, we explore Mask AutoRegressive (MAR) models for this task. MAR naturally supports image inpainting by generating latent tokens corresponding to mask regions, enabling better local controllability without altering the background. However, directly applying MAR to this task makes the inpainting content either ignore the prompts or be disharmonious with the background context. Through analysis of the attention maps from the inpainting images, we identify the impact of background tokens on text tokens during the MAR generation, and leverage this to design \textbf{Token Painter}, a training-free text-guided image inpainting method based on MAR. Our approach introduces two key components: (1) Dual-Stream Encoder Information Fusion (DEIF), which fuses the semantic and context information from text and background in frequency domain to produce novel guidance tokens, allowing MAR to generate text-faithful inpainting content while keeping harmonious with background context. (2) Adaptive Decoder Attention Score Enhancing (ADAE), which adaptively enhances attention scores on guidance tokens and inpainting tokens to further enhance the alignment of prompt details and the content visual quality. Extensive experiments demonstrate that our training-free method outperforms prior state-of-the-art methods across almost all metrics. Codes: https://github.com/longtaojiang/Token-Painter.

cs.CV↗