arXiv subjects

Chen Su

Publications and source records attributed to Chen Su.

17 recordsLinked to original sources

arXiv2026

Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting

Diffusion models have become a widely used framework for probabilistic time series forecasting, modeling the distribution of future values given an observed history. In time series forecasting, however, the future continues the observed history, creating an asymmetry the standard diffusion process leaves unaddressed, with slowly-varying content largely determined by the observed continuity while higher-frequency dynamics carry most of the residual uncertainty. Existing diffusion-based forecasters decouple this asymmetry through an external rule before generation, leaving the corruption trajectory blind to which parts of the target the history can already anchor. We propose DiffDiff, a diffusion framework that embeds this predictability asymmetry into the diffusion trajectory itself, so that a single end-to-end diffusion process becomes aware of which parts of the target the history can already anchor. DiffDiff makes the forward operator step-dependent so that the noisy intermediate state progressively shifts from the target itself toward its second-order differenced structure, while a conditioning pathway supplies the denoiser with both value-domain and differential history information balanced by a stage-adaptive gate at each diffusion step. The terminal distribution approaches a standard Gaussian, preserving compatibility with existing samplers. On seven benchmarks across four prediction horizons, DiffDiff outperforms six diffusion baselines, and our analysis confirms that DiffDiff concentrates the diffusion's generative effort on the most uncertain components of the target while relieving it from rebuilding the history-anchored content.

cs.AI↗

arXiv2026

SURGE: An Event-Centric Social Media Sentiment Time Series Benchmark with Interaction Structure

Public events on social media generate large volumes of discussion whose collective dynamics carry direct value for opinion forecasting and crisis response. Capturing how these dynamics evolve across an event's lifecycle requires organizing fragmented posts into event-level time series. Existing datasets cover only a small number of events within a single category, and typically discard the interaction structure between posts when constructing time series, which restricts both transfer across event types and controlled study of how interactions shape the resulting collective dynamics. We present SURGE, a multi-event social media benchmark that pairs event-level time series with aligned text and interaction structure linking posts within an event. SURGE is built through an automated pipeline that produces calendar-aligned time series at three temporal granularities, covering 67 events and more than 800K posts across five event categories. Each time bin is paired with flat and structured textual views derived from the same selected posts, enabling controlled evaluation of whether social interaction structure affects forecasting behavior. On top of SURGE we define benchmark protocols for numerical-only forecasting, text-augmented forecasting, high-interaction evaluation, and leave-one-category-out generalization. Experiments with representative time-series and multimodal forecasting models reveal three properties of the benchmark: a strong local-persistence regime in which naive baselines remain hard to beat under absolute error, limited transfer of existing text-augmented forecasters to event-driven social-media data, and increased difficulty on reply-dense periods that aggregate metrics tend to obscure. We further include a lightweight structure-aware probe as a reference implementation, illustrating how SURGE can support interaction-aware forecasting research.

cs.SI↗

arXiv2026

Learning Shared Sentiment Prototypes for Adaptive Multimodal Sentiment Analysis

Multimodal sentiment analysis (MSA) aims to predict human sentiment from textual, acoustic, and visual information in videos. Recent studies improve multimodal fusion by modeling modality interaction and assigning different modality weights. However, they usually compress diverse sentiment cues into a single compact representation before sentiment reasoning. This early aggregation makes it difficult to preserve the internal structure of sentiment evidence, where different cues may complement, conflict with, or differ in reliability from each other. In addition, modality importance is often determined only once during fusion, so later reasoning cannot further adjust modality contributions. To address these issues, we propose PRISM, a framework that unifies structured affective extraction and adaptive modality evaluation. PRISM organizes multimodal evidence in a shared prototype space, which supports structured cross-modal comparison and adaptive fusion. It further applies dynamic modality reweighting during reasoning, allowing modality contributions to be continuously refined as semantic interactions become deeper. Experiments on three benchmark datasets show that PRISM outperforms representative baselines.

cs.MM↗

arXiv2026

Constraining Neutrino Mass with the Void Weak Lensing Effect

Cosmic voids, the underdense regions of the Large Scale Structure (LSS), provide cosmological information highly complementary to that obtained from overdense regions. In this work, we investigate the constraining power of the void-shear cross-correlation (void lensing effect) on the total neutrino mass. Based on cosmological $N$-body simulations with varying neutrino masses, we populate BOSS LOW-Z-like galaxies at $0.2<z<0.4$ using HOD fitting, identify voids with the DIVE void finder and obtain their density profiles from the underlying dark matter and neutrino distributions. We then generate mock shear catalogues through ray-tracing and measure the corresponding void lensing signals, assuming a source number density of $10/{\rm arcmin}^{2}$ and sky area of around $8400\,{\rm deg}^2$. Under this setup, void lensing independently yields a constraint on total neutrino mass as $\sigma(M_{\nu})=0.096\,{\rm eV}$ ($M_{\nu}<0.232\,{\rm eV}$, 95% C.L.) in the absence of shape noise, and $\sigma(M_{\nu})=0.340\,{\rm eV}$ ($M_{\nu}<0.707\,{\rm eV}$, 95% C.L.) when adopting a Stage-III-like shape noise. Moreover, we find a clear linear relationship between the void lensing signal and neutrino mass. We further validate the forward modelling of the void lensing signal from the void density profiles across different cosmologies, demonstrating its accuracy and potential for future applications. These findings highlight void lensing as a promising probe of massive neutrinos and motivate its applications to galaxy survey data as well as the combination with other cosmological observables.

astro-ph.CO↗

arXiv2026

RA-SSU: Towards Fine-Grained Audio-Visual Learning with Region-Aware Sound Source Understanding

Audio-Visual Learning (AVL) is one fundamental task of multi-modality learning and embodied intelligence, displaying the vital role in scene understanding and interaction. However, previous researchers mostly focus on exploring downstream tasks from a coarse-grained perspective (e.g., audio-visual correspondence, sound source localization, and audio-visual event localization). Considering providing more specific scene perception details, we newly define a fine-grained Audio-Visual Learning task, termed Region-Aware Sound Source Understanding (RA-SSU), which aims to achieve region-aware, frame-level, and high-quality sound source understanding. To support this goal, we innovatively construct two corresponding datasets, i.e. fine-grained Music (f-Music) and fine-grained Lifescene (f-Lifescene), each containing annotated sound source masks and frame-by-frame textual descriptions. The f-Music dataset includes 3,976 samples across 22 scene types related to specific application scenarios, focusing on music scenes with complex instrument mixing. The f-Lifescene dataset contains 6,156 samples across 61 types representing diverse sounding objects in life scenarios. Moreover, we propose SSUFormer, a Sound-Source Understanding TransFormer benchmark that facilitates both the sound source segmentation and sound region description with a multi-modal input and multi-modal output architecture. Specifically, we design two modules for this framework, Mask Collaboration Module (MCM) and Mixture of Hierarchical-prompted Experts (MoHE), to respectively enhance the accuracy and enrich the elaboration of the sound source description. Extensive experiments are conducted on our two datasets to verify the feasibility of the task, evaluate the availability of the datasets, and demonstrate the superiority of the SSUFormer, which achieves SOTA performance on the Sound Source Understanding benchmark.

cs.CV↗

arXiv2026

Millimeter-scale rigid diamond probe for high sensitivity endoscopic-magnetometry applications

Magnetometry based on diamond nitrogen-vacancy (NV) centers has been extensively studied for applications requiring diverse capabilities, spanning from nanometer spatial resolution to subpicotesla sensitivity. Among various applications, diamond magnetometers can demonstrate high sensitivity magnetic sensing within millimeter-scale size for endoscopic applications. However, the trade-off between sensitivity and spatial resolution of diamond magnetometry makes it difficult to achieve such a probe. In this study, we present a millimeter-scale rigid diamond magnetometer probe with enhanced sensitivity via optimizing the optical design. By coupling the frustum diamond with the miniaturized compound parabolic concentrator (CPC) lens, we enhance the fluorescence collection efficiency by 37% within 4 mm diameter, and the achieved sensitivity is 200 pT/Hz1/2 based on the sample with the resonance linewidth of ~8 MHz. With this verified structure, endoscopes with mm-size probe and picotesla sensitivity can be projected for surgical and industrial applications in the future.

physics.ins-det↗

arXiv2025

Chain-of-thought Reviewing and Correction for Time Series Question Answering

With the advancement of large language models (LLMs), diverse time series analysis tasks are reformulated as time series question answering (TSQA) through a unified natural language interface. However, existing LLM-based approaches largely adopt general natural language processing techniques and are prone to reasoning errors when handling complex numerical sequences. Different from purely textual tasks, time series data are inherently verifiable, enabling consistency checking between reasoning steps and the original input. Motivated by this property, we propose T3LLM, which performs multi-step reasoning with an explicit correction mechanism for time series question answering. The T3LLM framework consists of three LLMs, namely, a worker, a reviewer, and a student, that are responsible for generation, review, and reasoning learning, respectively. Within this framework, the worker generates step-wise chains of thought (CoT) under structured prompts, while the reviewer inspects the reasoning, identifies erroneous steps, and provides corrective comments. The collaboratively generated corrected CoT are used to fine-tune the student model, internalizing multi-step reasoning and self-correction into its parameters. Experiments on multiple real-world TSQA benchmarks demonstrate that T3LLM achieves state-of-the-art performance over strong LLM-based baselines.

cs.CL↗

arXiv2025

The Shear-to-Cosmology Paradigm I. Hybrid Field-Level and Simulation-Based Framework for Weak Lensing Surveys

Precise cosmological inference from next-generation weak lensing surveys requires extracting non-Gaussian information beyond standard two-point statistics. We present a hybrid machine-learning (ML) framework that integrates field-level inference (FLI) with simulation-based inference (SBI) to map observed shear fields directly to cosmological parameters, eliminating the need for convergence reconstruction. The FLI network extracts rich non-Gaussian information from the shear field to produce informative features, which are then used by SBI to model the resulting complex posteriors. To mitigate noise from intrinsic galaxy shapes, we develop a blind, training-free, PCA-based shear denoising method. Tests on CSST-like mock catalogs reveal significant performance gains. The shear-based inference achieves approximately twice the cosmological constraining power in Figure of Merit (FoM) compared to the conventional convergence-based approach. Moreover, the combination of PCA denoising and ML compression can deliver a 36.4% improvement in FoM over standard shear two-point statistics. This work establishes a scalable and robust pathway for cosmological inference, unlocking the full potential of Stage-IV weak-lensing surveys.

astro-ph.CO↗

arXiv2025

Text Reinforcement for Multimodal Time Series Forecasting

Recent studies in time series forecasting (TSF) use multimodal inputs, such as text and historical time series data, to predict future values. These studies mainly focus on developing advanced techniques to integrate textual information with time series data to perform the task and achieve promising results. Meanwhile, these approaches rely on high-quality text and time series inputs, whereas in some cases, the text does not accurately or fully capture the information carried by the historical time series, which leads to unstable performance in multimodal TSF. Therefore, it is necessary to enhance the textual content to improve the performance of multimodal TSF. In this paper, we propose improving multimodal TSF by reinforcing the text modalities. We propose a text reinforcement model (TeR) to generate reinforced text that addresses potential weaknesses in the original text, then apply this reinforced text to support the multimodal TSF model's understanding of the time series, improving TSF performance. To guide the TeR toward producing higher-quality reinforced text, we design a reinforcement learning approach that assigns rewards based on the impact of each reinforced text on the performance of the multimodal TSF model and its relevance to the TSF task. We optimize the TeR accordingly, so as to improve the quality of the generated reinforced text and enhance TSF performance. Extensive experiments on a real-world benchmark dataset covering various domains demonstrate the effectiveness of our approach, which outperforms strong baselines and existing studies on the dataset.

cs.CL↗

arXiv2025

ReMeREC: Relation-aware and Multi-entity Referring Expression Comprehension

Referring Expression Comprehension (REC) aims to localize specified entities or regions in an image based on natural language descriptions. While existing methods handle single-entity localization, they often ignore complex inter-entity relationships in multi-entity scenes, limiting their accuracy and reliability. Additionally, the lack of high-quality datasets with fine-grained, paired image-text-relation annotations hinders further progress. To address this challenge, we first construct a relation-aware, multi-entity REC dataset called ReMeX, which includes detailed relationship and textual annotations. We then propose ReMeREC, a novel framework that jointly leverages visual and textual cues to localize multiple entities while modeling their inter-relations. To address the semantic ambiguity caused by implicit entity boundaries in language, we introduce the Text-adaptive Multi-entity Perceptron (TMP), which dynamically infers both the quantity and span of entities from fine-grained textual cues, producing distinctive representations. Additionally, our Entity Inter-relationship Reasoner (EIR) enhances relational reasoning and global scene understanding. To further improve language comprehension for fine-grained prompts, we also construct a small-scale auxiliary dataset, EntityText, generated using large language models. Experiments on four benchmark datasets show that ReMeREC achieves state-of-the-art performance in multi-entity grounding and relation prediction, outperforming existing approaches by a large margin.

cs.CV↗

arXiv2025

Diffusion Models for Time Series Forecasting: A Survey

Diffusion models, initially developed for image synthesis, demonstrate remarkable generative capabilities. Recently, their application has expanded to time series forecasting (TSF), yielding promising results. Existing surveys on time series primarily focus on the application of diffusion models to time series tasks or merely provide model-by-model introductions of diffusion-based TSF models, without establishing a systematic taxonomy for existing diffusion-based TSF models. In this survey, we firstly introduce several standard diffusion models and their prevalent variants, explaining their adaptation to TSF tasks. Then, we provide a comprehensive review of diffusion models for TSF, paying special attention to the sources of conditional information and the mechanisms for integrating this conditioning within the models. In analyzing existing approaches using diffusion models for TSF, we provide a systematic categorization and a comprehensive summary of them in this survey. Furthermore, we examine several foundational diffusion models applied to TSF, alongside commonly used datasets and evaluation metrics. Finally, we discuss the progress and limitations of these approaches, as well as potential future research directions for diffusion-based TSF. Overall, this survey offers a comprehensive overview of recent progress and future prospects for diffusion models in TSF, serving as a valuable reference for researchers in the field.

stat.ML↗

arXiv2025

Fusing Large Language Models with Temporal Transformers for Time Series Forecasting

Recently, large language models (LLMs) have demonstrated powerful capabilities in performing various tasks and thus are applied by recent studies to time series forecasting (TSF) tasks, which predict future values with the given historical time series. Existing LLM-based approaches transfer knowledge learned from text data to time series prediction using prompting or fine-tuning strategies. However, LLMs are proficient at reasoning over discrete tokens and semantic patterns but are not initially designed to model continuous numerical time series data. The gaps between text and time series data lead LLMs to achieve inferior performance to a vanilla Transformer model that is directly trained on TSF data. However, the vanilla Transformers often struggle to learn high-level semantic patterns. In this paper, we design a novel Transformer-based architecture that complementarily leverages LLMs and vanilla Transformers, so as to integrate the high-level semantic representations learned by LLMs into the temporal information encoded by time series Transformers, where a hybrid representation is obtained by fusing the representations from the LLM and the Transformer. The resulting fused representation contains both historical temporal dynamics and semantic variation patterns, allowing our model to predict more accurate future values. Experiments on benchmark datasets demonstrate the effectiveness of the proposed approach.

cs.CL↗

arXiv2025

Computed Tomography Visual Question Answering with Cross-modal Feature Graphing

Visual question answering (VQA) in medical imaging aims to support clinical diagnosis by automatically interpreting complex imaging data in response to natural language queries. Existing studies typically rely on distinct visual and textual encoders to independently extract features from medical images and clinical questions, which are subsequently combined to generate answers. Specifically, in computed tomography (CT), such approaches are similar to the conventional practices in medical image analysis. However, these approaches pay less attention to the spatial continuity and inter-slice correlations in the volumetric CT data, leading to fragmented and imprecise responses. In this paper, we propose a novel large language model (LLM)-based framework enhanced by a graph representation of salient features. Different from conventional multimodal encoding strategies, our approach constructs a cross-modal graph integrating both visual and textual features, treating individual CT slices and question tokens as nodes within the graph. We further leverage an attentive graph convolutional network to dynamically fuse information within this structure. The resulting aggregated graph features then serve as a soft prompt to guide a large language model in generating accurate answers. Extensive experiments on the M3D-VQA benchmark demonstrate that our approach consistently outperforms baselines across multiple evaluation metrics, offering more robust reasoning capabilities.

cs.CV↗

arXiv2025

Multimodal Conditioned Diffusive Time Series Forecasting

Diffusion models achieve remarkable success in processing images and text, and have been extended to special domains such as time series forecasting (TSF). Existing diffusion-based approaches for TSF primarily focus on modeling single-modality numerical sequences, overlooking the rich multimodal information in time series data. To effectively leverage such information for prediction, we propose a multimodal conditioned diffusion model for TSF, namely, MCD-TSF, to jointly utilize timestamps and texts as extra guidance for time series modeling, especially for forecasting. Specifically, Timestamps are combined with time series to establish temporal and semantic correlations among different data points when aggregating information along the temporal dimension. Texts serve as supplementary descriptions of time series' history, and adaptively aligned with data points as well as dynamically controlled in a classifier-free manner. Extensive experiments on real-world benchmark datasets across eight domains demonstrate that the proposed MCD-TSF model achieves state-of-the-art performance.

cs.CL↗

arXiv2025

Cosmological Constraints with Void Lensing I: the Simulation-Based Inference Framework

We present a Simulation-Based Inference (SBI) framework for cosmological parameter estimation via void lensing analysis. Despite the absence of an analytical model of void lensing, SBI can effectively learn posterior distributions through forward modeling of mock data. We develop a forward modeling pipeline that accounts for both cosmology and the galaxy-halo connection. By training a neural density estimator on simulated data, we infer the posteriors of two cosmological parameters, $\Omega_m$ and $S_8$. Validation tests are conducted on posteriors derived from different cosmological parameters and a fiducial sample. The results demonstrate that SBI provides unbiased estimates of mean values and accurate uncertainties. These findings highlight the potential to apply void lensing analysis to observational data even without an analytical void lensing model.

astro-ph.CO↗

arXiv2024

CURLING - I. The Influence of Point-like Image Approximation on the Outcomes of Cluster Strong Lens Modeling

Cluster-scale strong lensing is a powerful tool for exploring the properties of dark matter and constraining cosmological models. However, due to the complex parameter space, pixelized strong lens modeling in galaxy clusters is computationally expensive, leading to the point-source approximation of strongly lensed extended images, potentially introducing systematic biases. Herein, as the first paper of the ClUsteR strong Lens modelIng for the Next-Generation observations (CURLING) program, we use lensing ray-tracing simulations to quantify the biases and uncertainties arising from the point-like image approximation for JWST-like observations. Our results indicate that the approximation works well for reconstructing the total cluster mass distribution, but can bias the magnification measurements near critical curves and the constraints on the cosmological parameters, the total matter density of the Universe $\Omega_{\rm m}$, and dark energy equation of state parameter $w$. To mitigate the biases, we propose incorporating the extended surface brightness distribution of lensed sources into the modeling. This approach reduces the bias in magnification from 46.2 per cent to 0.09 per cent for $\mu \sim 1000$. Furthermore, the median values of cosmological parameters align more closely with the fiducial model. In addition to the improved accuracy, we also demonstrate that the constraining power can be substantially enhanced. In conclusion, it is necessary to model cluster-scale strong lenses with pixelized multiple images, especially for estimating the intrinsic luminosity of highly magnified sources and accurate cosmography in the era of high-precision observations.

astro-ph.CO↗

arXiv2022

Void Lensing in Cubic Galileon Gravity

Weak lensing studies via cosmic voids are a promising probe of Modified Gravity (MG). Excess surface mass density (ESD) is widely used as a lensing statistic in weak lensing research. In this paper, we use the ray-tracing method to study the ESD around voids in simulations based on Cubic Galileon (CG) gravity. With the compilation of N-body simulation and ray-tracing method, changes in structure formation and deflection angle resulting from MG can both be considered, making the extraction of lensing signals more realistic. We find good agreements between the measurement and theoretical prediction of ESD for CG gravity. Meanwhile, the lensing signals are much less affected by the change of the deflection angle than the change of the structure formation, indicating a good approximation of regarding ESD (statistics) as the projection of 3D dark matter density field. Finally, we demonstrate that it is impossible to distinguish CG and General Relativity in our simulation, however, in the next-generation survey, thanks to the large survey area and the increased galaxy number density, detecting the differences between these two models is possible. The methodology employed in this paper that combines N-body simulation and ray-tracing method can be a robust way to measure the lensing signals from simulations based on the MGs, and especially on that which significantly modifies the deflection angle.

astro-ph.CO↗