arXiv subjects

Xiaoming Shi

Publications and source records attributed to Xiaoming Shi.

At least 19 recordsLinked to original sources

arXiv2026

MedPixel: A Unified Pixel-Language Model for Medical Reasoning and Segmentation

Reliable medical image understanding requires models to connect clinical language and visual reasoning with pixel-level grounding. Yet medical vision-language models often lack precise localization, whereas medical segmenters typically rely on explicit target categories or precise spatial prompts. This divide is reinforced by a supervision mismatch: segmentation datasets provide precise masks but little language supervision, whereas medical vision-language data rarely pair language with dense spatial annotations. To address this gap, we present MedPixel, a unified medical pixel-language model built around a shared language--mask interface. To provide scalable supervision, we introduce MedPLG-440K, comprising approximately 440K pixel-language task samples constructed through a clinically motivated synthesis process without external LLM annotation. MedPixel is trained with joint multi-task supervised fine-tuning followed by Pixel-Level Preference Optimization, which uses ground-truth masks as offline verifiers to derive response preferences from mask quality. MedPixel supports a broad spectrum of tasks spanning explicit grounding, implicit reasoning, spatial interaction, grounded explanation, and medical VQA. Across this task spectrum, MedPixel achieves strong performance in both pixel-level prediction and response generation, together with effective zero-shot transfer to external grounding benchmarks and robustness to imperfect spatial prompts. Code and model checkpoints will be released at https://github.com/yhy-whu/Medpixel.

cs.CV↗

arXiv2026

xHC: Expanded Hyper-Connections

Hyper-Connections (HC) expand the residual stream of Transformers into $N$ parallel streams, providing a form of memory scaling beyond model width and depth. Manifold-Constrained HC (mHC) stabilizes this formulation at scale. The large gains from $N{=}1$ to $N{=}4$ suggest residual-stream expansion as a promising scaling axis. However, existing HC-family methods typically stop at $N{=}4$. Our experiments reveal why: scaling mHC beyond this point yields diminishing performance gains and rapidly increasing training cost. We attribute this limitation to two bottlenecks: insufficient write-back information for an expanding number of streams and residual-mixing generation whose cost scales cubically with $N$. To address both bottlenecks, we propose xHC (Expanded Hyper-Connections), the first HC-family method to achieve meaningful expansion beyond $N{=}4$. xHC combines temporal feature augmentation for richer write-back with a sparse residual-stream architecture that updates only $k=4$ of the $N=16$ streams while retaining dense access to the full residual state. Across 18B and 28B MoE models, xHC delivers strong and consistent downstream improvements. On an 18B MoE model, xHC improves the average downstream score by 4.0 points over mHC, while adding only modest training FLOPs over the vanilla baseline. Scaling-law experiments show that the vanilla and mHC require $1.50\times$ and $1.19\times$ the compute of xHC, respectively, to reach the same loss. Practical large-$N$ training also requires controlling memory traffic from the expanded residual state. We therefore introduce xHC-Flash, which reduces the per-sublayer memory traffic from $73.5C$ to $40C$, comparable to the $34C$ required by mHC at $N{=}4$, while retaining the gains of full xHC. Together, xHC and xHC-Flash make large-$N$ residual-stream expansion effective and practical for LLM pre-training.

cs.LG↗

arXiv2026

Dynamic Chunking for Diffusion Language Models

Block discrete diffusion language models factorize a sequence autoregressively over fixed-size positional blocks, decoupling within-block parallel denoising from across-block conditioning. We argue that this rigid partition wastes structure already present in the sequence: blocks defined by position rather than by content separate semantically coherent tokens and group unrelated ones together. We introduce the \textbf{D}ynamic \textbf{C}hunking \textbf{D}iffusion \textbf{M}odel (DCDM), which replaces positional blocks with content-defined semantic chunks. At its core is Chunking Attention, a differentiable layer that routes tokens into $K$ clusters parameterized by learnable subspaces and shaped end-to-end by the diffusion objective. The resulting cluster assignments induce a chunk-causal attention mask under which a discrete diffusion denoiser factorizes the sequence likelihood autoregressively over semantic chunks, strictly generalizing block discrete diffusion. On downstream benchmarks at parameter scales up to 1.5B, DCDM consistently improves over both unstructured and positional-block diffusion baselines, with the advantage stable across scales and visible early in training.

cs.CL↗

arXiv2026

A Survey of Inductive Reasoning for Large Language Models

Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the fundamental types, which is characterized by its particular-to-general thinking process and the non-uniqueness of its answers. The inductive mode is crucial for knowledge generalization and aligns better with human cognition, so it is a fundamental mode of learning, hence attracting increasing interest. Despite the importance of inductive reasoning, there is no systematic summary of it. Therefore, this paper presents the first comprehensive survey of inductive reasoning for LLMs. First, methods for improving inductive reasoning are categorized into three main areas: post-training, test-time scaling, and data augmentation. Then, current benchmarks of inductive reasoning are summarized, and a unified sandbox-based evaluation approach with the observation coverage metric is derived. Finally, we offer some analyses regarding the source of inductive ability and how simple model architectures and data help with inductive tasks, providing a solid foundation for future research.

cs.CL↗

arXiv2026

Robust Electrocaloric Performance Enabled by Highly-Polar Frustrated Nanodomains in NaNbO3-Based Ferrodistortive Relaxor

Solid-state refrigeration technologies, represented by electrocaloric effect (ECE), are renowned for zero global-warming-potential and high cooling efficiency. Synergistically achieving high electrocaloric effect (ΔT) and wide temperature span (ΔTspan) for EC materials takes a leapfrog toward practical cooling applications, typical for integrated circuits. Guided by phase-field simulation, Ba(Ti, Hf)O3 dubbed as a polar wrench, establishes polar frustration by setting up local stress field and manipulating octahedral oxygen tilt (OOT) in NaNbO3-based relaxor. The resultant P4bm framework entails short-range and highly-polar ferrodistortive nanodomains, i.e., the abundant highly-polar nanodomains facilitate to increase entropy change and robust OOT enables to impede thermal perturbations. Consequently, a large ΔT of 0.85 K and 0.70 K with an ultrawide ΔTspan of 118 K and 130 K is obtained, contributing to an ultrahigh figure of merit of > 90 K2 in NaNbO3-Ba(Ti, Hf)O3, significantly outperforms its counterparts. The local structure responsible for robust EC performances are decrypted through 2D information from atomic-resolution scanning transmission electron microscope, 3D big-box model constructed from neutron total scattering and DFT calculations. These findings highlight that polar frustration strategy in ferrodistortive relaxor enables to pioneer emergent EC performances, and also unearth potential entropy-change-based ferroelectric and ferromagnetic materials beyond.

cond-mat.mtrl-sci↗

arXiv2025

Ophiuchus: Incentivizing Tool-augmented "Think with Images" for Joint Medical Segmentation, Understanding and Reasoning

Recent medical MLLMs have made significant progress in generating step-by-step textual reasoning chains. However, they still struggle with complex clinical tasks that necessitate dynamic and iterative focusing on fine-grained visual regions. To close this gap, we introduce Ophiuchus, a versatile, tool-augmented framework that equips an MLLM to (i) decide when fine-grained visual evidence is needed, (ii) determine where to probe and ground within the medical image, and (iii) seamlessly weave the relevant sub-image content back into an interleaved, multimodal chain of thought for precise segmentation and diagnosis. Ophiuchus moves beyond mere tool-calling by tightly fusing the MLLM's inherent grounding and reasoning capabilities with external tools, enabling more accurate and trustworthy decisions. The core of our method is a three-stage training strategy: cold-start SFT for basic tool selection; self-reflection fine-tuning to strengthen decision revision; and agentic tool reinforcement learning to elicit sophisticated, expert-like diagnostic behaviors. Extensive experiments show that Ophiuchus consistently outperforms both closed-source and open-source SOTA methods across diverse medical benchmarks, including VQA, detection, and reasoning-based segmentation. Our project code is available at https://github.com/SII-zyj/Ophiuchus.

cs.AI↗

arXiv2025

TK-Mamba: Marrying KAN With Mamba for Text-Driven 3D Medical Image Segmentation

3D medical image segmentation is important for clinical diagnosis and treatment but faces challenges from high-dimensional data and complex spatial dependencies. Traditional single-modality networks, such as CNNs and Transformers, are often limited by computational inefficiency and constrained contextual modeling in 3D settings. To alleviate these limitations, we propose TK-Mamba, a multimodal framework that fuses the linear-time Mamba with Kolmogorov-Arnold Networks (KAN) to form an efficient hybrid backbone. Our approach is characterized by two primary technical contributions. Firstly, we introduce the novel 3D-Group-Rational KAN (3D-GR-KAN), which marks the first application of KAN in 3D medical imaging, providing a superior and computationally efficient nonlinear feature transformation crucial for complex volumetric structures. Secondly, we devise a dual-branch text-driven strategy using Pubmedclip's embeddings. This strategy significantly enhances segmentation robustness and accuracy by simultaneously capturing inter-organ semantic relationships to mitigate label inconsistencies and aligning image features with anatomical texts. By combining this advanced backbone and vision-language knowledge, TK-Mamba offers a unified and scalable solution for both multi-organ and tumor segmentation. Experiments on multiple datasets demonstrate that our framework achieves state-of-the-art performance in both organ and tumor segmentation tasks, surpassing existing methods in both accuracy and efficiency. Our code is publicly available at https://github.com/yhy-whu/TK-Mamba

cs.CV↗

arXiv2025

Throughput Maximization for Multiuser Communications with Flexible-Sector 6DMA

This paper presents a cost-effective and easily-deployable flexible-sector six-dimensional movable antenna (6DMA) architecture for future wireless communication networks, which enables flexible antenna configurations to match users' spatial distribution for capacity enhancement. Different from conventional sectorized base station (BS) with fixed-position antennas (FPAs), the flexible-sector 6DMA-enabled BS employs multiple directional sector antenna arrays that can flexibly move along a common circular track. By properly moving antennas across sectors and rotating all sector antenna arrays synchronously, the flexible-sector BS can adjust the coverage regions of all sectors with flexible antenna allocations over them. In particular, we consider the multiuser downlink communication employing the orthogonal multiple access (OMA) to serve users in each sector. Under this setup, we jointly optimize the sector rotation and the antenna allocation at the flexible-sector BS to maximize the average common throughput achievable for all users based on their spatial distribution. We solve this non-convex optimization problem by deriving closed-form solutions and thereby analyze the effect of users' spatial distribution on the achievable common throughput. It is shown that equal user distribution over sectors is optimal for maximizing the common throughput. Motivated by this result, we further develop a low-complexity suboptimal solution for the sector rotation that minimizes the variance of user numbers across sectors. Finally, we provide simulation results to verify our analytical results and validate the performance of our proposed solutions. It is demonstrated that the flexible-sector BS significantly improves the network throughput as compared to other benchmark schemes.

cs.IT↗

arXiv2025

In-plane polar domains enhanced energy storage

Relaxor ferroelectric thin films are recognized for their ultrahigh power density, rendering them highly promising for energy storage applications in electrical and electronic systems. However, achieving high energy storage performance with chemically homogeneous, environmentally friendly and compositionally stable materials remains challenging. In this work, we present a design of dielectrics with high energy storage performance via an in-plane polar domains incorporating polar nanoregions mechanism. Guided by phase-field simulations, we synthesized La/Si co-doping BaTiO3 solid-solution thin films with high chemical homogeneity to realize high energy storage performance. Given that, we achieve a high energy density of 203.7J/cm3 and an energy efficiency of approximately 80% at an electric field of 6.15MV/cm. This mechanism holds significant promise for the design of next-generation high-performance dielectric materials for energy storage and other advanced functional materials.

cond-mat.mtrl-sci↗

arXiv2025

Flexible-Sector 6DMA Base Station: Modeling and Design

Six-dimensional movable antenna (6DMA) has emerged as a promising new technology for future wireless networks, which can adaptively adjust the three-dimensional (3D) positions and 3D rotations of antennas/antenna arrays for performance enhancement. This paper proposes a novel cost-effective 6DMA-based base station (BS) architecture, termed the \textit{flexible-sector} BS, which allows the deployed antennas to flexibly rotate and move along a circular track, thus enabling common sector rotation and flexible antenna allocation across sectors to adapt to the spatial user distribution efficiently. In particular, we focus on the uplink transmission in a single-cell system, where the flexible-sector BS receives independent messages from multiple users. We introduce an angular-domain user distribution model, which captures the users' spatial clustering or hot-spot distribution effectively. Assuming the zero-forcing (ZF) based receiver applied at the BS to decode multiuser signals, we derive the average sum rate achievable for the users as a function of the common rotation of sectors and the antenna allocation over them. Moreover, we develop a two-step algorithm to jointly optimize the common sector rotation and antenna allocation to maximize the average sum rate of all users. It is shown that the optimal antenna number in each sector linearly increases with the number of users in it. It is also revealed that under the most favorable user distribution, the achievable sum rate gain increases in the order of $\log_{2}(B)$ in the regime of asymptotically large number of antennas, where $B$ denotes the number of sectors. Numerically results also show that as $B$ increases, the proposed flexible-sector BS achieves higher sum rate, and it outperforms other benchmark schemes, such as the traditional fixed-sector BS as well as the BS with sector rotation or antenna allocation optimization only.

cs.NI↗

arXiv2025

U-Cast: Learning Hierarchical Structures for High-Dimensional Time Series Forecasting

Time series forecasting (TSF) is a central problem in time series analysis. However, as the number of channels in time series datasets scales to the thousands or more, a scenario we define as High-Dimensional Time Series Forecasting (HDTSF), it introduces significant new modeling challenges that are often not the primary focus of traditional TSF research. HDTSF is challenging because the channel correlation often forms complex and hierarchical patterns. Existing TSF models either ignore these interactions or fail to scale as dimensionality grows. To address this issue, we propose U-Cast, a channel-dependent forecasting architecture that learns latent hierarchical channel structures with an innovative query-based attention. To disentangle highly correlated channel representation, U-Cast adds a full-rank regularization during training. We also release Time-HD, the first benchmark of large, diverse, high-dimensional datasets. Our theory shows that exploiting cross-channel information lowers forecasting risk, and experiments on Time-HD demonstrate that U-Cast surpasses strong baselines in both accuracy and efficiency. Together, U-Cast and Time-HD provide a solid basis for future HDTSF research.

cs.LG↗

arXiv2025

Mix-Ecom: Towards Mixed-Type E-Commerce Dialogues with Complex Domain Rules

E-commerce agents contribute greatly to helping users complete their e-commerce needs. To promote further research and application of e-commerce agents, benchmarking frameworks are introduced for evaluating LLM agents in the e-commerce domain. Despite the progress, current benchmarks lack evaluating agents' capability to handle mixed-type e-commerce dialogue and complex domain rules. To address the issue, this work first introduces a novel corpus, termed Mix-ECom, which is constructed based on real-world customer-service dialogues with post-processing to remove user privacy and add CoT process. Specifically, Mix-ECom contains 4,799 samples with multiply dialogue types in each e-commerce dialogue, covering four dialogue types (QA, recommendation, task-oriented dialogue, and chit-chat), three e-commerce task types (pre-sales, logistics, after-sales), and 82 e-commerce rules. Furthermore, this work build baselines on Mix-Ecom and propose a dynamic framework to further improve the performance. Results show that current e-commerce agents lack sufficient capabilities to handle e-commerce dialogues, due to the hallucination cased by complex domain rules. The dataset will be publicly available.

cs.AI↗

arXiv2025

RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models

Large Language Models (LLMs) have exhibited significant proficiency in code debugging, especially in automatic program repair, which may substantially reduce the time consumption of developers and enhance their efficiency. Significant advancements in debugging datasets have been made to promote the development of code debugging. However, these datasets primarily focus on assessing the LLM's function-level code repair capabilities, neglecting the more complex and realistic repository-level scenarios, which leads to an incomplete understanding of the LLM's challenges in repository-level debugging. While several repository-level datasets have been proposed, they often suffer from limitations such as limited diversity of tasks, languages, and error types. To mitigate this challenge, this paper introduces RepoDebug, a multi-task and multi-language repository-level code debugging dataset with 22 subtypes of errors that supports 8 commonly used programming languages and 3 debugging tasks. Furthermore, we conduct evaluation experiments on 10 LLMs, where Claude 3.5 Sonnect, the best-performing model, still cannot perform well in repository-level debugging.

cs.SE↗

arXiv2025

LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios

As Large Language Models (LLMs) evolve in natural language processing (NLP), their ability to stably follow instructions in long-context inputs has become critical for real-world applications. However, existing benchmarks seldom focus on instruction-following in long-context scenarios or stability on different inputs. To bridge this gap, we introduce LIFBench, a scalable dataset designed to evaluate LLMs' instruction-following capabilities and stability across long contexts. LIFBench comprises three long-context scenarios and eleven diverse tasks, featuring 2,766 instructions generated through an automated expansion method across three dimensions: length, expression, and variables. For evaluation, we propose LIFEval, a rubric-based assessment method that enables precise, automated scoring of complex LLM responses without reliance on LLM-assisted assessments or human judgment. This method allows for a comprehensive analysis of model performance and stability from multiple perspectives. We conduct detailed experiments on 20 prominent LLMs across six length intervals. Our work contributes LIFBench and LIFEval as robust tools for assessing LLM performance in complex and long-context settings, offering valuable insights to guide future advancements in LLM development.

cs.CL↗

arXiv2025

Cost-effective Instruction Learning for Pathology Vision and Language Analysis

The advent of vision-language models fosters the interactive conversations between AI-enabled models and humans. Yet applying these models into clinics must deal with daunting challenges around large-scale training data, financial, and computational resources. Here we propose a cost-effective instruction learning framework for conversational pathology named as CLOVER. CLOVER only trains a lightweight module and uses instruction tuning while freezing the parameters of the large language model. Instead of using costly GPT-4, we propose well-designed prompts on GPT-3.5 for building generation-based instructions, emphasizing the utility of pathological knowledge derived from the Internet source. To augment the use of instructions, we construct a high-quality set of template-based instructions in the context of digital pathology. From two benchmark datasets, our findings reveal the strength of hybrid-form instructions in the visual question-answer in pathology. Extensive results show the cost-effectiveness of CLOVER in answering both open-ended and closed-ended questions, where CLOVER outperforms strong baselines that possess 37 times more training parameters and use instruction data generated from GPT-4. Through the instruction tuning, CLOVER exhibits robustness of few-shot learning in the external clinical dataset. These findings demonstrate that cost-effective modeling of CLOVER could accelerate the adoption of rapid conversational applications in the landscape of digital pathology.

cs.AI↗

arXiv2025

Hybrid Near-Far Field 6D Movable Antenna Design Exploiting Directional Sparsity and Deep Learning

Six-dimensional movable antenna (6DMA) has been identified as a new disruptive technology for future wireless systems to support a large number of users with only a few antennas. However, the intricate relationships between the signal carrier wavelength and the transceiver region size lead to inaccuracies in traditional far-field 6DMA channel model, causing discrepancies between the model predictions and the hybrid-field channel characteristics in practical 6DMA systems, where users might be in the far-field region relative to the antennas on the same 6DMA surface, while simultaneously being in the near-field region relative to different 6DMA surfaces. Moreover, due to the high-dimensional channel and the coupled position and rotation constraints, the estimation of the 6DMA channel and the joint design of the 6DMA positions and rotations and the transmit beamforming at the base station (BS) incur extremely high computational complexity. To address these issues, we propose an efficient hybrid-field generalized 6DMA channel model, which accounts for planar-wave propagation within individual 6DMA surfaces and spherical-wave propagation among different 6DMA surfaces. Furthermore, by leveraging directional sparsity, we propose a low-overhead channel estimation algorithm that efficiently constructs a complete channel map for all potential antenna position-rotation pairs while limiting the training overhead incurred by antenna movement. In addition, we propose a low-complexity design leveraging deep reinforcement learning (DRL), which facilitates the joint design of the 6DMA positions, rotations, and beamforming in a unified manner. Numerical results demonstrate that the proposed hybrid-field channel model and channel estimation algorithm outperform existing approaches and that the DRL-enhanced 6DMA system significantly surpasses flexible antenna systems.

cs.IT↗

arXiv2025

Real Space Visualization of Order-Disorder Transition in BaTiO3

Ferroelectricity in BaTiO3 was observed nearly eighty years ago, but the mechanism underlying its ferroelectric-paraelectric phase transition remains elusive. The order-disorder transition has been recognized as playing a critical role, however, the precise nature of the order parameter still remains under scrutiny, including the local dipole direction and the correlations above and below the Curie temperature. Using in situ scanning transmission electron microscopy, we directly map polar displacements in BaTiO3 across the ferroelectric-paraelectric phase transition, providing atomistic insights into a order-disorder mechanism. Atomic tracking reveals finite polar Ti displacements in the paraelectric phase where they manifest as random polar nanoregions. The displacements align along <111> direction in both the ferroelectric and paraelectric phases. The paraelectric-ferroelectric transition emerges from real-space correlations of the <111> polar Ti displacements. Our direct visualizations provides atomic insights into the order-disorder mechanism in the ferroelectric-paraelectric transition of BaTiO3.

cond-mat.mtrl-sci↗

arXiv2025

dots.llm1 Technical Report

Mixture of Experts (MoE) models have emerged as a promising paradigm for scaling language models efficiently by activating only a subset of parameters for each input token. In this report, we present dots.llm1, a large-scale MoE model that activates 14B parameters out of a total of 142B parameters, delivering performance on par with state-of-the-art models while reducing training and inference costs. Leveraging our meticulously crafted and efficient data processing pipeline, dots.llm1 achieves performance comparable to Qwen2.5-72B after pretraining on 11.2T high-quality tokens and post-training to fully unlock its capabilities. Notably, no synthetic data is used during pretraining. To foster further research, we open-source intermediate training checkpoints at every one trillion tokens, providing valuable insights into the learning dynamics of large language models.

cs.CL↗