arXiv subjects

Xiang Li

Publications and source records attributed to Xiang Li.

At least 487 records · Page 27Linked to original sources

arXiv2025

Tightening the mixed integer linear formulation for the piecewise linear approximation in general dimensions

This paper addresses the problem of tightening the mixed-integer linear programming (MILP) formulation for continuous piecewise linear (CPWL) approximations of data sets in arbitrary dimensions. The MILP formulation leverages the difference-of-convex (DC) representation of CPWL functions. We introduce the concept of well-behaved CPWL interpolations and demonstrate that any CPWL interpolation of a data set has a well-behaved version. This result is critical to tighten the MILP problem. We present six different strategies to tighten the problem, which include fixing the values of some variables, introducing additional constraints, identifying small big-M parameter values and applying tighter variable bounds. These methods leverage key aspects of the DC representation and the inherent structure of well-behaved CPWL interpolations. Experimental results demonstrate that specific combinations of these tightening strategies lead to significant improvement in solution times, especially for tightening strategies that consider well-behaved CPWL solutions.

math.OC↗

arXiv2025

Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models

Recent advancements in Large Video Language Models (LVLMs) have highlighted their potential for multi-modal understanding, yet evaluating their factual grounding in videos remains a critical unsolved challenge. To address this gap, we introduce Video SimpleQA, the first comprehensive benchmark tailored for factuality evaluation in video contexts. Our work differs from existing video benchmarks through the following key features: 1) Knowledge required: demanding integration of external knowledge beyond the video's explicit narrative; 2) Multi-hop fact-seeking question: Each question involves multiple explicit facts and requires strict factual grounding without hypothetical or subjective inferences. We also include per-hop single-fact-based sub-QAs alongside final QAs to enable fine-grained, stepby-step evaluation; 3) Short-form definitive answer: Answers are crafted as unambiguous and definitively correct in a short format with minimal scoring variance; 4) Temporal grounded required: Requiring answers to rely on one or more temporal segments in videos, rather than single frames. We extensively evaluate 33 state-of-the-art LVLMs and summarize key findings as follows: 1) Current LVLMs exhibit notable deficiencies in factual adherence, with the best-performing model o3 merely achieving an F-score of 66.3%; 2) Most LVLMs are overconfident in what they generate, with self-stated confidence exceeding actual accuracy; 3) Retrieval-augmented generation demonstrates consistent improvements at the cost of additional inference time overhead; 4) Multi-hop QA demonstrates substantially degraded performance compared to single-hop sub-QAs, with first-hop object or event recognition emerging as the primary bottleneck. We position Video SimpleQA as the cornerstone benchmark for video factuality assessment, aiming to steer LVLM development toward verifiable grounding in real-world contexts.

cs.CV↗

arXiv2025

Emotion-Qwen: A Unified Framework for Emotion and Vision Understanding

Accurate emotion understanding in videos necessitates effectively recognizing and interpreting emotional states by integrating visual, textual, auditory, and contextual cues. Although recent Large Multimodal Models (LMMs) have exhibited significant progress in general vision-language (VL) tasks, their performance often deteriorates in emotion-specific scenarios, exhibiting catastrophic forgetting when fine-tuned on emotion-centric tasks. To overcome these limitations, we propose Emotion-Qwen, a unified multimodal framework designed to simultaneously enable robust emotion understanding and preserve general VL reasoning capabilities. Emotion-Qwen introduces a novel Hybrid Compressor based on a Mixture-of-Experts (MoE) architecture, dynamically routing inputs to optimally balance emotion-specific processing and general multimodal reasoning. We further propose a carefully structured three-stage pre-training pipeline, leveraging extensive general and emotion-focused datasets to strengthen multimodal representation robustness and model adaptability. Additionally, we develop the Video Emotion Reasoning (VER) dataset, a large-scale bilingual resource containing over 40K video clips annotated with detailed context-aware emotional descriptions, significantly facilitating research on fine-grained emotional reasoning. Extensive experiments confirm that Emotion-Qwen achieves state-of-the-art performance across multiple emotion recognition and reasoning benchmarks, while maintaining highly competitive results in general VL tasks.

cs.MM↗

arXiv2025

Handows: A Palm-Based Interactive Multi-Window Management System in Virtual Reality

Window management in virtual reality (VR) remains a challenging task due to the spatial complexity and physical demands of current interaction methods. We introduce Handows, a palm-based interface that enables direct manipulation of spatial windows through familiar smartphone-inspired gestures on the user's non-dominant hand. Combining ergonomic layout design with body-centric input and passive haptics, Handows supports four core operations: window selection, closure, positioning, and scaling. We evaluate Handows in a user study (N=15) against two common VR techniques (virtual hand and controller) across these core window operations. Results show that Handows significantly reduces physical effort and head movement while improving task efficiency and interaction precision. A follow-up case study (N=8) demonstrates Handows' usability in realistic multitasking scenarios, highlighting user-adapted workflows and spontaneous layout strategies. Our findings suggest the potential of embedding mobile-inspired metaphors into proprioceptive body-centric interfaces to support low-effort and spatially coherent interaction in VR.

cs.HC↗

arXiv2025

DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection

One of the primary challenges in Synthetic Aperture Radar (SAR) object detection lies in the pervasive influence of coherent noise. As a common practice, most existing methods, whether handcrafted approaches or deep learning-based methods, employ the analysis or enhancement of object spatial-domain characteristics to achieve implicit denoising. In this paper, we propose DenoDet V2, which explores a completely novel and different perspective to deconstruct and modulate the features in the transform domain via a carefully designed attention architecture. Compared to DenoDet V1, DenoDet V2 is a major advancement that exploits the complementary nature of amplitude and phase information through a band-wise mutual modulation mechanism, which enables a reciprocal enhancement between phase and amplitude spectra. Extensive experiments on various SAR datasets demonstrate the state-of-the-art performance of DenoDet V2. Notably, DenoDet V2 achieves a significant 0.8\% improvement on SARDet-100K dataset compared to DenoDet V1, while reducing the model complexity by half. The code is available at https://github.com/GrokCV/GrokSAR.

cs.CV↗

arXiv2025

Intercalation-Induced Near Room-Temperature Ferromagnetism in CrI3 via Synergistic Exchange Pathways

The development of room-temperature magnetic semiconductors is critical for advancing spintronic technologies, yet van der Waals magnets like CrI3 exhibit intrinsically low Curie temperatures (Tc = 45 K). This study employs first-principles calculations to demonstrate that atom intercalation, particularly lithium (Li), dramatically enhances magnetic exchange couplings in CrI3, achieving near room-temperature ferromagnetism with a predicted Tc of 286 K-aligning with experimental reports of 420 K. The underlying mechanism involves synergistic superexchange and double-exchange interactions: intercalation reduces the |Ep-Ed| energy difference between iodine p-orbitals and chromium d-orbitals, strengthening superexchange pathways, while charge transfer induces valence mixing (e.g., Cr3+ to Cr2+, as confirmed by experimental X-ray photoelectron spectrometry data), promoting double-exchange. Theoretical predictions extend to other intercalants including Cu and Na, with Cu0.25CrI3 and Na0.25CrI3 exhibiting Tc of 267 K and 247 K, respectively, establishing a versatile strategy for designing high-Tc magnetic semiconductors. This work bridges theoretical insights with experimental validation, offering a transferable framework for intercalation-driven material design and accelerating practical spintronic device realization.

cond-mat.mtrl-sci↗

arXiv2025

SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection

Synthetic Aperture Radar (SAR) object detection has gained significant attention recently due to its irreplaceable all-weather imaging capabilities. However, this research field suffers from both limited public datasets (mostly comprising <2K images with only mono-category objects) and inaccessible source code. To tackle these challenges, we establish a new benchmark dataset and an open-source method for large-scale SAR object detection. Our dataset, SARDet-100K, is a result of intense surveying, collecting, and standardizing 10 existing SAR detection datasets, providing a large-scale and diverse dataset for research purposes. To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created. With this high-quality dataset, we conducted comprehensive experiments and uncovered a crucial challenge in SAR object detection: the substantial disparities between the pretraining on RGB datasets and finetuning on SAR datasets in terms of both data domain and model structure. To bridge these gaps, we propose a novel Multi-Stage with Filter Augmentation (MSFA) pretraining framework that tackles the problems from the perspective of data input, domain transition, and model migration. The proposed MSFA method significantly enhances the performance of SAR object detection models while demonstrating exceptional generalizability and flexibility across diverse models. This work aims to pave the way for further advancements in SAR object detection. The dataset and code is available at https://github.com/zcablii/SARDet_100K.

cs.CV↗

arXiv2025

LSKNet: A Foundation Lightweight Backbone for Remote Sensing

Remote sensing images pose distinct challenges for downstream tasks due to their inherent complexity. While a considerable amount of research has been dedicated to remote sensing classification, object detection and semantic segmentation, most of these studies have overlooked the valuable prior knowledge embedded within remote sensing scenarios. Such prior knowledge can be useful because remote sensing objects may be mistakenly recognized without referencing a sufficiently long-range context, which can vary for different objects. This paper considers these priors and proposes a lightweight Large Selective Kernel Network (LSKNet) backbone. LSKNet can dynamically adjust its large spatial receptive field to better model the ranging context of various objects in remote sensing scenarios. To our knowledge, large and selective kernel mechanisms have not been previously explored in remote sensing images. Without bells and whistles, our lightweight LSKNet sets new state-of-the-art scores on standard remote sensing classification, object detection and semantic segmentation benchmarks. Our comprehensive analysis further validated the significance of the identified priors and the effectiveness of LSKNet. The code is available at https://github.com/zcablii/LSKNet.

cs.CV↗

arXiv2025

Large Model Driven Solar Activity AI Forecaster: A Scalable Dual Data-Model Framework

Solar activity drives space weather, affecting Earth's magnetosphere and technological infrastructure, which makes accurate solar flare forecasting critical. Current space weather models under-utilize multi-modal solar data, lack iterative enhancement via expert knowledge, and rely heavily on human forecasters under the Observation-Orientation-Decision-Action (OODA) paradigm. Here we present the "Solar Activity AI Forecaster", a scalable dual data-model driven framework built on foundational models, integrating expert knowledge to autonomously replicate human forecasting tasks with quantifiable outputs. It is implemented in the OODA paradigm and comprises three modules: a Situational Perception Module that generates daily solar situation awareness maps by integrating multi-modal observations; In-Depth Analysis Tools that characterize key solar features (active regions, coronal holes, filaments); and a Flare Prediction Module that forecasts strong flares for the full solar disk and active regions. Executed within a few minutes, the model outperforms or matches human forecasters in generalization across multi-source data, forecast accuracy, and operational efficiency. This work establishes a new paradigm for AI-based space weather forecasting, demonstrating AI's potential to enhance forecast accuracy and efficiency, and paving the way for autonomous operational forecasting systems.

astro-ph.SR↗

arXiv2025

From Generation to Consumption: Personalized List Value Estimation for Re-ranking

Re-ranking is critical in recommender systems for optimizing the order of recommendation lists, thus improving user satisfaction and platform revenue. Most existing methods follow a generator-evaluator paradigm, where the evaluator estimates the overall value of each candidate list. However, they often ignore the fact that users may exit before consuming the full list, leading to a mismatch between estimated generation value and actual consumption value. To bridge this gap, we propose CAVE, a personalized Consumption-Aware list Value Estimation framework. CAVE formulates the list value as the expectation over sub-list values, weighted by user-specific exit probabilities at each position. The exit probability is decomposed into an interest-driven component and a stochastic component, the latter modeled via a Weibull distribution to capture random external factors such as fatigue. By jointly modeling sub-list values and user exit behavior, CAVE yields a more faithful estimate of actual list consumption value. We further contribute three large-scale real-world list-wise benchmarks from the Kuaishou platform, varying in size and user activity patterns. Extensive experiments on these benchmarks, two Amazon datasets, and online A/B testing on Kuaishou show that CAVE consistently outperforms strong baselines, highlighting the benefit of explicitly modeling user exits in re-ranking.

cs.IR↗

arXiv2025

CodeBoost: Boosting Code LLMs by Squeezing Knowledge from Code Snippets with RL

Code large language models (LLMs) have become indispensable tools for building efficient and automated coding pipelines. Existing models are typically post-trained using reinforcement learning (RL) from general-purpose LLMs using "human instruction-final answer" pairs, where the instructions are usually from manual annotations. However, collecting high-quality coding instructions is both labor-intensive and difficult to scale. On the other hand, code snippets are abundantly available from various sources. This imbalance presents a major bottleneck in instruction-based post-training. We propose CodeBoost, a post-training framework that enhances code LLMs purely from code snippets, without relying on human-annotated instructions. CodeBoost introduces the following key components: (1) maximum-clique curation, which selects a representative and diverse training corpus from code; (2) bi-directional prediction, which enables the model to learn from both forward and backward prediction objectives; (3) error-aware prediction, which incorporates learning signals from both correct and incorrect outputs; (4) heterogeneous augmentation, which diversifies the training distribution to enrich code semantics; and (5) heterogeneous rewarding, which guides model learning through multiple reward types including format correctness and execution feedback from both successes and failures. Extensive experiments across several code LLMs and benchmarks verify that CodeBoost consistently improves performance, demonstrating its effectiveness as a scalable and effective training pipeline.

cs.CL↗

arXiv2025

Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection

Recent advances in parameter-efficient transfer learning have demonstrated the utility of composing LoRA adapters from libraries of pretrained modules. However, most existing approaches rely on simple retrieval heuristics or uniform averaging, which overlook the latent structure of task relationships in representation space. We propose a new framework for adapter reuse that moves beyond retrieval, formulating adapter composition as a geometry-aware sparse reconstruction problem. Specifically, we represent each task by a latent prototype vector derived from the base model's encoder and aim to approximate the target task prototype as a sparse linear combination of retrieved reference prototypes, under an $\ell_1$-regularized optimization objective. The resulting combination weights are then used to blend the corresponding LoRA adapters, yielding a composite adapter tailored to the target task. This formulation not only preserves the local geometric structure of the task representation manifold, but also promotes interpretability and efficient reuse by selecting a minimal set of relevant adapters. We demonstrate the effectiveness of our approach across multiple domains-including medical image segmentation, medical report generation and image synthesis. Our results highlight the benefit of coupling retrieval with latent geometry-aware optimization for improved zero-shot generalization.

cs.LG↗

arXiv2025

The Multi-Round Diagnostic RAG Framework for Emulating Clinical Reasoning

In recent years, accurately and quickly deploying medical large language models (LLMs) has become a trend. Among these, retrieval-augmented generation (RAG) has garnered attention due to rapid deployment and privacy protection. However, the challenge hinder the practical deployment of RAG for medical diagnosis: the semantic gap between colloquial patient descriptions and the professional terminology within medical knowledge bases. We try to address the challenge from the data perspective and the method perspective. First, to address the semantic gap in existing knowledge bases, we construct DiagnosGraph, a generalist knowledge graph covering both modern medicine and Traditional Chinese Medicine. It contains 876 common diseases with the graph of 7,997 nodes and 37,201 triples. To bridge the gap between colloquial patient narratives and academic medical knowledge, DiagnosGraph also introduces $1,908$ medical record by formalizing the patient chief complaint and proposing a medical diagnosis. Second, we introduce the Multi-Round Diagnostic RAG (MRD-RAG) framework. It utilizes a multi-round dialogue to refine diagnostic possibilities, emulating the clinical reasoning of a physician. Experiments conducted on four medical benchmarks, with evaluations by human physicians, demonstrate that MRD-RAG enhances the diagnostic performance of LLMs, highlighting its potential to make automated diagnosis more accurate and human-aligned.

cs.CL↗

arXiv2025

FinKario: Event-Enhanced Automated Construction of Financial Knowledge Graph

Individual investors are significantly outnumbered and disadvantaged in financial markets, overwhelmed by abundant information and lacking professional analysis. Equity research reports stand out as crucial resources, offering valuable insights. By leveraging these reports, large language models (LLMs) can enhance investors' decision-making capabilities and strengthen financial analysis. However, two key challenges limit their effectiveness: (1) the rapid evolution of market events often outpaces the slow update cycles of existing knowledge bases, (2) the long-form and unstructured nature of financial reports further hinders timely and context-aware integration by LLMs. To address these challenges, we tackle both data and methodological aspects. First, we introduce the Event-Enhanced Automated Construction of Financial Knowledge Graph (FinKario), a dataset comprising over 305,360 entities, 9,625 relational triples, and 19 distinct relation types. FinKario automatically integrates real-time company fundamentals and market events through prompt-driven extraction guided by professional institutional templates, providing structured and accessible financial insights for LLMs. Additionally, we propose a Two-Stage, Graph-Based retrieval strategy (FinKario-RAG), optimizing the retrieval of evolving, large-scale financial knowledge to ensure efficient and precise data access. Extensive experiments show that FinKario with FinKario-RAG achieves superior stock trend prediction accuracy, outperforming financial LLMs by 18.81% and institutional strategies by 17.85% on average in backtesting.

cs.LG↗

arXiv2025

Hybrid CNN-Mamba Enhancement Network for Robust Multimodal Sentiment Analysis

Multimodal Sentiment Analysis (MSA) with missing modalities has recently attracted increasing attention. Although existing research mainly focuses on designing complex model architectures to handle incomplete data, it still faces significant challenges in effectively aligning and fusing multimodal information. In this paper, we propose a novel framework called the Hybrid CNN-Mamba Enhancement Network (HCMEN) for robust multimodal sentiment analysis under missing modality conditions. HCMEN is designed around three key components: (1) hierarchical unimodal modeling, (2) cross-modal enhancement and alignment, and (3) multimodal mix-up fusion. First, HCMEN integrates the strengths of Convolutional Neural Network (CNN) for capturing local details and the Mamba architecture for modeling global contextual dependencies across different modalities. Furthermore, grounded in the principle of Mutual Information Maximization, we introduce a cross-modal enhancement mechanism that generates proxy modalities from mixed token-level representations and learns fine-grained token-level correspondences between modalities. The enhanced unimodal features are then fused and passed through the CNN-Mamba backbone, enabling local-to-global cross-modal interaction and comprehensive multimodal integration. Extensive experiments on two benchmark MSA datasets demonstrate that HCMEN consistently outperforms existing state-of-the-art methods, achieving superior performance across various missing modality scenarios. The code will be released publicly in the near future.

cs.MM↗

arXiv2025

LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning

Recent generative models face significant risks of producing harmful content, which has underscored the importance of machine unlearning (MU) as a critical technique for eliminating the influence of undesired data. However, existing MU methods typically assign the same weight to all data to be forgotten, which makes it difficult to effectively forget certain data that is harder to unlearn than others. In this paper, we empirically demonstrate that the loss of data itself can implicitly reflect its varying difficulty. Building on this insight, we introduce Loss-based Reweighting Unlearning (LoReUn), a simple yet effective plug-and-play strategy that dynamically reweights data during the unlearning process with minimal additional computational overhead. Our approach significantly reduces the gap between existing MU methods and exact unlearning in both image classification and generation tasks, effectively enhancing the prevention of harmful content generation in text-to-image diffusion models.

cs.LG↗

arXiv2025

Integrating LLM-Derived Multi-Semantic Intent into Graph Model for Session-based Recommendation

Session-based recommendation (SBR) is mainly based on anonymous user interaction sequences to recommend the items that the next user is most likely to click. Currently, the most popular and high-performing SBR methods primarily leverage graph neural networks (GNNs), which model session sequences as graph-structured data to effectively capture user intent. However, most GNNs-based SBR methods primarily focus on modeling the ID sequence information of session sequences, while neglecting the rich semantic information embedded within them. This limitation significantly hampers model's ability to accurately infer users' true intention. To address above challenge, this paper proposes a novel SBR approach called Integrating LLM-Derived Multi-Semantic Intent into Graph Model for Session-based Recommendation (LLM-DMsRec). The method utilizes a pre-trained GNN model to select the top-k items as candidate item sets and designs prompts along with a large language model (LLM) to infer multi-semantic intents from these candidate items. Specifically, we propose an alignment mechanism that effectively integrates the semantic intent inferred by the LLM with the structural intent captured by GNNs. Extensive experiments conducted on the Beauty and ML-1M datasets demonstrate that the proposed method can be seamlessly integrated into GNNs framework, significantly enhancing its recommendation performance.

cs.IR↗

arXiv2025

Advancing Textual Prompt Learning with Anchored Attributes

Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current training is restricted to aligning images with predefined known categories and cannot be associated with unknown categories. In this work, we propose utilizing universal attributes as a bridge to enhance the alignment between images and unknown categories. Specifically, we introduce an Attribute-anchored Textual Prompt learning method for vision-language models, named ATPrompt. This approach expands the learning space of soft prompts from the original one-dimensional category level into the multi-dimensional attribute level by incorporating multiple attribute tokens into the learnable soft prompts. Through this modification, we transform the text prompt from a category-centric form to an attribute-category hybrid form. Additionally, we introduce a straightforward differentiable attribute search method to identify representative and suitable attributes for downstream tasks. As an easy-to-use plug-in technique, ATPrompt can seamlessly replace the existing basic prompt format in textual-based methods, providing general improvements at a negligible computational cost. Extensive experiments across 11 datasets validate the effectiveness of our method. Code is publicly available at https://github.com/zhengli97/ATPrompt.

cs.CV↗