Searcharxiv⌕ Search

arXiv subjects

Hao Sun

Publications and source records attributed to Hao Sun.

At least 109 records · Page 6Linked to original sources
arXiv2026

DUET: Joint Exploration of User Item Profiles in Recommendation System

Traditional recommendation systems represent users and items as dense vectors and learn to align them in a shared latent space for relevance estimation. Recent LLM-based recommenders instead leverage natural-language representations that are easier to interpret and integrate with downstream reasoning modules. This paper studies how to construct effective textual profiles for users and items, and how to align them for recommendation. A central difficulty is that the best profile format is not known a priori: manually designed templates can be brittle and misaligned with task objectives. Moreover, generating user and item profiles independently may produce descriptions that are individually plausible yet semantically inconsistent for a specific user--item pair. We propose Duet, an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence. Duet follows a three-stage procedure: it first turns raw histories and metadata into compact cues, then expands these cues into paired profile prompts and then generate profiles, and finally optimizes the generation policy with reinforcement learning using downstream recommendation performance as feedback. Experiments on three real-world datasets show that Duet consistently outperforms strong baselines, demonstrating the benefits of template-free profile exploration and joint user-item textual alignment.

cs.IR↗
arXiv2026

Siamese Foundation Models for Crystal Structure Prediction

Predicting crystal structures from chemical compositions is a fundamental challenge in materials discovery, complicated by complex 3D geometries that distinguish it from fields like protein folding. Here, we present Diffusion-based Crystal Omni (DAO), a pretrain-finetune framework for crystal structure prediction integrating two Siamese foundation models: a structure generator and an energy predictor. The generator is pretrained via a two-stage pipeline on a vast dataset of stable and unstable structures, leveraging the predictor to relax unstable configurations and guide the generative sampling. Across two well-known benchmarks, pretraining significantly enhances performance across multiple backbone architectures. Ablation studies confirm that the synergy between the generator and predictor mutually benefits both components. We further validate DAO on three real-world superconductors ($\text{Cr}_6\text{Os}_2$, $\text{Zr}_{16}\text{Rh}_8\text{O}_4$, and $\text{Zr}_{16}\text{Pd}_8\text{O}_4$) typically inaccessible to conventional computation. For $\text{Cr}_6\text{Os}_2$, DAO achieves a 100\% match rate with experimental references and an atomic-position error of 0.0012 under 20-shot generation, performing over 2000$\times$ faster per iteration than DFT-based structure predictors. These compelling results collectively highlight the potential of our approach for advancing materials science research.

cond-mat.mtrl-sci↗
arXiv2026

Boosting Robust AIGI Detection with LoRA-based Pairwise Training

The proliferation of highly realistic AI-Generated Image (AIGI) has necessitated the development of practical detection methods. While current AIGI detectors perform admirably on clean datasets, their detection performance frequently decreases when deployed "in the wild", where images are subjected to unpredictable, complex distortions. To resolve the critical vulnerability, we propose a novel LoRA-based Pairwise Training (LPT) strategy designed specifically to achieve robust detection for AIGI under severe distortions. The core of our strategy involves the targeted finetuning of a visual foundation model, the deliberate simulation of data distribution during the training phase, and a unique pairwise training process. Specifically, we introduce distortion and size simulations to better fit the distribution from the validation and test sets. Based on the strong visual representation capability of the visual foundation model, we finetune the model to achieve AIGI detection. The pairwise training is utilized to improve the detection via decoupling the generalization and robustness optimization. Experiments show that our approach secured the 3th placement in the NTIRE Robust AI-Generated Image Detection in the Wild challenge

cs.CV↗
arXiv2026

Dynamic Summary Generation for Interpretable Multimodal Depression Detection

Depression remains widely underdiagnosed and undertreated because stigma and subjective symptom ratings hinder reliable screening. To address this challenge, we propose a coarse-to-fine, multi-stage framework that leverages large language models (LLMs) for accurate and interpretable detection. The pipeline performs binary screening, five-class severity classification, and continuous regression. At each stage, an LLM produces progressively richer clinical summaries that guide a multimodal fusion module integrating text, audio, and video features, yielding predictions with transparent rationale. The system then consolidates all summaries into a concise, human-readable assessment report. Experiments on the E-DAIC and CMDC datasets show significant improvements over state-of-the-art baselines in both accuracy and interpretability.

cs.AI↗
arXiv2026

NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild

This paper presents an overview of the NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild, held in conjunction with the NTIRE workshop at CVPR 2026. The goal of this challenge was to develop detection models capable of distinguishing real images from generated ones in realistic scenarios: the images are often transformed (cropped, resized, compressed, blurred) for practical usage, and therefore, the detection models should be robust to such transformations. The challenge is based on a novel dataset consisting of 108,750 real and 185,750 AI-generated images from 42 generators comprising a large variety of open-source and closed-source models of various architectures, augmented with 36 image transformations. Methods were evaluated using ROC AUC on the full test set, including both transformed and untransformed images. A total of 511 participants registered, with 20 teams submitting valid final solutions. This report provides a comprehensive overview of the challenge, describes the proposed solutions, and can be used as a valuable reference for researchers and practitioners in increasing the robustness of the detection models to real-world transformations.

cs.CV↗
arXiv2026

CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wild

Discovering camouflaged objects is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. While the problem of camouflaged object detection over sequential video frames has received increasing attention, the scale and diversity of existing video camouflaged object detection (VCOD) datasets are greatly limited, which hinders the deeper analysis and broader evaluation of recent deep learning-based algorithms with data-hungry training strategy. To break this bottleneck, in this paper, we construct CAMotion, a high-quality benchmark covers a wide range of species for camouflaged moving object detection in the wild. CAMotion comprises various sequences with multiple challenging attributes such as uncertain edge, occlusion, motion blur, and shape complexity, etc. The sequence annotation details and statistical distribution are presented from various perspectives, allowing CAMotion to provide in-depth analyses on the camouflaged object's motion characteristics in different challenging scenarios. Additionally, we conduct a comprehensive evaluation of existing SOTA models on CAMotion, and discuss the major challenges in VCOD task. The benchmark is available at https://www.camotion.focuslab.net.cn, we hope that our CAMotion can lead to further advancements in the research community.

cs.CV↗
arXiv2026

Pressure-Induced Superconducting-like Transition in the $\it d$-wave Altermagnet Candidate CsV$_2$Se$_2$O

Altermagnetism generates exchange-type spin splitting without net magnetization and, in its $\it d$-wave form, resembles the angular symmetry of unconventional $\it d$-wave superconductivity. Whether this correspondence bears directly on superconducting instabilities in real correlated materials remains open. Here we study the quasi-two-dimensional vanadium oxychalcogenide CsV$_2$Se$_2$O (CVSO), a square-net $\it d$-wave altermagnet candidate, through combined experimental and theoretical investigation of its lattice structure, electronic structure and transport properties. At ambient pressure, CVSO is a weakly insulating parent state with a density-wave-like anomaly near 100 K, and its bulk properties are most consistent with a G-type compensated antiferromagnetic background. Under compression, the density-wave-like feature is suppressed, the magnetoresistance evolves from predominantly negative to positive, and a superconducting-like resistive downturn emerges below about 3 K. This low-temperature anomaly is reproducible across samples and pressure media, and is suppressed by magnetic field. Room-temperature X-ray diffraction reveals no symmetry lowering, whereas does show a pronounced compressibility anomaly over the same pressure range. CVSO thus reveals a pressure-tuned phase diagram in which a reconstructed weakly insulating parent state gives way to strange-metal-like transport and superconducting-like behavior, echoing broader phenomenology associated with unconventional superconductors, including cuprates and nickelates.

cond-mat.supr-con↗
arXiv2026

Theoretical study of $f_0(980)$, $a_0(980)$ and $Ξ(1/2^-)$ in the process $Ξ_c^+ \to Σ^+K^+K^-$

We employed the chiral unitarity approach to investigate the decay process $Ξ_c^+ \to Σ^+K^+K^-$, by considering that the low lying nucleon resonance $Ξ(1/2^-)$ and the low lying scalar meson $f_0(980)$ and $a_0(980)$ that could be dynamically generated through $S$-wave pseudoscalar meson-octet baryon and the $S$-wave pseudoscalar meson-pseudoscalar meson interactions, respectively. In the invariant mass distributions of $Σ^+K^-$ and $K^+K^-$, we observe a distinct peak structure associated with the resonant state $Ξ(1/2^-)$ and a bit enhancement near the $K^+K^-$ threshold that is corresponding to the mesons $f_0(980)$ and $a_0(980)$, respectively. Consequently, we recommend more precise experimental measurements of this process in the future.

hep-ph↗
arXiv2026

ETA-VLA: Efficient Token Adaptation via Temporal Fusion and Intra-LLM Sparsification for Vision-Language-Action Models

The integration of Vision-Language-Action (VLA) models into autonomous driving systems offers a unified framework for interpreting complex scenes and executing control commands. However, the necessity to incorporate historical multi-view frames for accurate temporal reasoning imposes a severe computational burden, primarily driven by the quadratic complexity of self-attention mechanisms in Large Language Models (LLMs). To alleviate this bottleneck, we propose ETA-VLA, an Efficient Token Adaptation framework for VLA models. ETA-VLA processes the past $n$ frames of multi-view images and introduces a novel Intra-LLM Sparse Aggregator (ILSA). Drawing inspiration from human driver attention allocation, ILSA dynamically identifies and prunes redundant visual tokens guided by textual queries and temporal consistency. Specifically, we utilize a text-guided scoring mechanism alongside a diversity-preserving sparsification strategy to select a sparse subset of critical tokens, ensuring comprehensive awareness of the driving scene. Extensive experiments on the NAVSIM v2 demonstrate that ETA-VLA achieves driving performance comparable to state-of-the-art baselines while reducing computational FLOPs by approximately 32\%. Notably, our method prunes 85% of visual tokens and reduces inference FLOPs by 61\%, but still retaining 94% of the original accuracy on the NAVSIM v2 benchmark.

cs.RO↗
arXiv2026

L2V-CoT: Cross-Modal Transfer of Chain-of-Thought Reasoning via Latent Intervention

Recently, Chain-of-Thought (CoT) reasoning has significantly enhanced the capabilities of large language models (LLMs), but Vision-Language Models (VLMs) still struggle with multi-step reasoning tasks due to limited multimodal reasoning data. To bridge this gap, researchers have explored methods to transfer CoT reasoning from LLMs to VLMs. However, existing approaches either need high training costs or require architectural alignment. In this paper, we use Linear Artificial Tomography (LAT) to empirically show that LLMs and VLMs share similar low-frequency latent representations of CoT reasoning despite architectural differences. Based on this insight, we propose L2V-CoT, a novel training-free latent intervention approach that transfers CoT reasoning from LLMs to VLMs. L2V-CoT extracts and resamples low-frequency CoT representations from LLMs in the frequency domain, enabling dimension matching and latent injection into VLMs during inference to enhance reasoning capabilities. Extensive experiments demonstrate that our approach consistently outperforms training-free baselines and even surpasses supervised methods.

cs.CL↗
arXiv2026

Benchmarking Semantic Segmentation Models via Appearance and Geometry Attribute Editing

Semantic segmentation takes pivotal roles in various applications such as autonomous driving and medical image analysis. When deploying segmentation models in practice, it is critical to test their behaviors in varied and complex scenes in advance. In this paper, we construct an automatic data generation pipeline Gen4Seg to stress-test semantic segmentation models by generating various challenging samples with different attribute changes. Beyond previous evaluation paradigms focusing solely on global weather and style transfer, we investigate variations in both appearance and geometry attributes at the object and image level. These include object color, material, size, position, as well as image-level variations such as weather and style. To achieve this, we propose to edit visual attributes of existing real images with precise control of structural information, empowered by diffusion models. In this way, the existing segmentation labels can be reused for the edited images, which greatly reduces the labor costs. Using our pipeline, we construct two new benchmarks, Pascal-EA and COCO-EA. We benchmark a wide variety of semantic segmentation models, spanning from closed-set models to open-vocabulary large models. We have several key findings: 1) advanced open-vocabulary models do not exhibit greater robustness compared to closed-set methods under geometric variations; 2) data augmentation techniques, such as CutOut and CutMix, are limited in enhancing robustness against appearance variations; 3) our pipeline can also be employed as a data augmentation tool and improve both in-distribution and out-of-distribution performances. Our work suggests the potential of generative models as effective tools for automatically analyzing segmentation models, and we hope our findings will assist practitioners and researchers in developing more robust and reliable segmentation models.

cs.CV↗
arXiv2026

Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning

Reinforcement Learning with verifiable rewards (RLVR) has emerged as a primary learning paradigm for enhancing the reasoning capabilities of multi-modal large language models (MLLMs). However, during RL training, the enormous state space of MLLM and sparse rewards often leads to entropy collapse, policy degradation, or over-exploitation of suboptimal behaviors. This necessitates an exploration strategy that maintains productive stochasticity while avoiding the drawbacks of uncontrolled random sampling, yielding inefficient exploration. In this paper, we propose CalibRL, a hybrid-policy RLVR framework that supports controllable exploration with expert guidance, enabled by two key mechanisms. First, a distribution-aware advantage weighting scales updates by group rareness to calibrate the distribution, therefore preserving exploration. Meanwhile, the asymmetric activation function (LeakyReLU) leverages the expert knowledge as a calibration baseline to moderate overconfident updates while preserving their corrective direction. CalibRL increases policy entropy in a guided manner and clarifies the target distribution by estimating the on-policy distribution through online sampling. Updates are driven by these informative behaviors, avoiding convergence to erroneous patterns. Importantly, these designs help alleviate the distributional mismatch between the model's policy and expert trajectories, thereby achieving a more stable balance between exploration and exploitation. Extensive experiments across eight benchmarks, including both in-domain and out-of-domain settings, demonstrate consistent improvements, validating the effectiveness of our controllable hybrid-policy RLVR training. Code is available at https://github.com/zhh6425/CalibRL.

cs.LG↗
arXiv2026

WAT: Online Video Understanding Needs Watching Before Thinking

Multimodal Large Language Models (MLLMs) have shown strong capabilities in image understanding, motivating recent efforts to extend them to video reasoning. However, existing Video LLMs struggle in online streaming scenarios, where long temporal context must be preserved under strict memory constraints. We propose WAT (Watching Before Thinking), a two-stage framework for online video reasoning. WAT separates processing into a query-independent watching stage and a query-triggered thinking stage. The watching stage builds a hierarchical memory system with a Short-Term Memory (STM) that buffers recent frames and a fixed-capacity Long-Term Memory (LTM) that maintains a diverse summary of historical content using a redundancy-aware eviction policy. In the thinking stage, a context-aware retrieval mechanism combines the query with the current STM context to retrieve relevant historical frames from the LTM for cross-temporal reasoning. To support training for online video tasks, we introduce WAT-85K, a dataset containing streaming-style annotations emphasizing real-time perception, backward tracing, and forecasting. Experiments show that WAT achieves state-of-the-art performance on online video benchmarks, including 77.7% accuracy on StreamingBench and 55.2% on OVO-Bench, outperforming existing open-source online Video LLMs while operating at real-time frame rates.

cs.CV↗
arXiv2026

Flexible Multi-Target Angular Emulation for Over-the-Air Testing of Large-Scale ISAC Base Stations: Principle and Experimental Verification

Over-the-air (OTA) emulation of diverse sensing target characteristics in a controlled laboratory environment is pivotal for advancing integrated sensing and communication (ISAC) technology, as it facilitates the non-invasive performance evaluation of ISAC base stations (BSs) across complex scenarios. In this work, a flexible multi-target OTA emulation framework based on a wireless cable method is proposed to evaluate the sensing performance of large-scale ISAC BSs. The core concept leverages an amplitude and phase modulation (APM) network to simultaneously establish wireless cables and simulate target spatial characteristics without consuming additional resources on costly radar target emulators. For the wireless cable method, the condition number increases as the number of antennas scales up, which affects the performance of the wireless cable. Although the wireless cable concept has been established for devices-under-test (DUTs) with a limited number of antenna ports, establishing wireless cables for large-scale DUTs remains an open question in the community. We address this problem by optimizing the OTA probe array configuration based on the theoretical properties of strictly diagonally dominant matrices. Experimental results validate the proposed framework, demonstrating high-isolation wireless cables for a 32-element DUT and an extremely low condition number for a 128-element synthetic array. Furthermore, the OTA emulation of a dynamic dual-drone scenario confirms the method's effectiveness and practicality in reproducing complex sensing environments.

eess.SP↗
arXiv2026

Searching for ALP Lepton Flavor Violation via ALP Decays at the LHC

In the ALP model, lepton flavor violation (LFV) can arise from off-diagonal ALP-lepton couplings ($g_{a\ell_i\ell_j}$), which are absent in the Standard Model. We focus on ALP production via gluon fusion ($pp \to a$) at the Large Hadron Collider (LHC), which dominates the ALP mass range of 5-1000 GeV due to its high cross section and manageable backgrounds. We are interested in the decay of an axion into an electron and a muon, two oppositely charged leptons of different flavors. After background suppression, we obtain the sensitivity to ALP in this mass range, finding significantly improved limits for $5 < m_a < 1000$ GeV, where SM backgrounds are suppressed. Our research is complementary with relevant studies.

hep-ph↗
arXiv2026

CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown Conditions

Deep learning has demonstrated remarkable capabilities in simulating complex dynamic systems. However, existing methods require known physical properties as supervision or inputs, limiting their applicability under unknown conditions. To explore this challenge, we introduce Cloth Dynamics Grounding (CDG), a novel scenario for unsupervised learning of cloth dynamics from multi-view visual observations. We further propose Cloth Dynamics Splatting (CloDS), an unsupervised dynamic learning framework designed for CDG. CloDS adopts a three-stage pipeline that first performs video-to-geometry grounding and then trains a dynamics model on the grounded meshes. To cope with large non-linear deformations and severe self-occlusions during grounding, we introduce a dual-position opacity modulation that supports bidirectional mapping between 2D observations and 3D geometry via mesh-based Gaussian splatting in video-to-geometry grounding stage. It jointly considers the absolute and relative position of Gaussian components. Comprehensive experimental evaluations demonstrate that CloDS effectively learns cloth dynamics from visual data while maintaining strong generalization capabilities for unseen configurations. Our code is available at https://github.com/whynot-zyl/CloDS. Visualization results are available at https://github.com/whynot-zyl/CloDS_video}.%\footnote{As in this example.

cs.CV↗
arXiv2026

CG-DMER: Hybrid Contrastive-Generative Framework for Disentangled Multimodal ECG Representation Learning

Accurate interpretation of electrocardiogram (ECG) signals is crucial for diagnosing cardiovascular diseases. Recent multimodal approaches that integrate ECGs with accompanying clinical reports show strong potential, but they still face two main concerns from a modality perspective: (1) intra-modality: existing models process ECGs in a lead-agnostic manner, overlooking spatial-temporal dependencies across leads, which restricts their effectiveness in modeling fine-grained diagnostic patterns; (2) inter-modality: existing methods directly align ECG signals with clinical reports, introducing modality-specific biases due to the free-text nature of the reports. In light of these two issues, we propose CG-DMER, a contrastive-generative framework for disentangled multimodal ECG representation learning, powered by two key designs: (1) Spatial-temporal masked modeling is designed to better capture fine-grained temporal dynamics and inter-lead spatial dependencies by applying masking across both spatial and temporal dimensions and reconstructing the missing information. (2) A representation disentanglement and alignment strategy is designed to mitigate unnecessary noise and modality-specific biases by introducing modality-specific and modality-shared encoders, ensuring a clearer separation between modality-invariant and modality-specific representations. Experiments on three public datasets demonstrate that CG-DMER achieves state-of-the-art performance across diverse downstream tasks.

cs.AI↗
arXiv2026

Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Context

While Large Language Models (LLMs) demonstrate remarkable capabilities in scientific tasks such as literature analysis and experimental design (e.g., accurately extracting key findings from papers or generating coherent experimental procedures), existing evaluation benchmarks primarily assess performance using rich contextual inputs. We introduce LiveIdeaBench, a comprehensive benchmark evaluating LLMs' scientific idea generation by assessing divergent thinking capabilities using single-keyword prompts. Drawing from Guilford's creativity theory, our benchmark employs a dynamic panel of state-of-the-art LLMs to assess generated ideas across five key dimensions: originality, feasibility, fluency, flexibility, and clarity. Through extensive experimentation with over 40 leading models across 1,180 keywords spanning 22 scientific domains, we reveal that the scientific idea generation capabilities measured by our benchmark, are poorly predicted by standard metrics of general intelligence. Our results demonstrate that models like QwQ-32B-preview achieve creative performance comparable to top-tier models such as claude-3.7-sonnet:thinking, despite significant gaps in their general intelligence scores. These findings highlight the need for specialized evaluation benchmarks for scientific idea generation and suggest that enhancing these idea generation capabilities in LLMs may require different training strategies than those used for improving general problem-solving abilities, potentially enabling a wider range of AI tools tailored for different stages of the scientific process.

cs.CL↗