arXiv subjects

Xinyi Chen

Publications and source records attributed to Xinyi Chen.

At least 37 records · Page 2Linked to original sources

arXiv2026

Sonic4D: Spatial Audio Generation for Immersive 4D Scene Exploration

Recent advancements in 4D generation have demonstrated its remarkable capability in synthesizing photorealistic renderings of dynamic 3D scenes. However, despite achieving impressive visual performance, almost all existing methods overlook the generation of spatial audio aligned with the corresponding 4D scenes, posing a significant limitation to truly immersive audiovisual experiences. To mitigate this issue, we propose Sonic4D, a novel framework that enables spatial audio generation for immersive exploration of 4D scenes. Specifically, our method is composed of three stages: 1) To capture both the dynamic visual content and raw auditory information from a monocular video, we first employ pre-trained expert models to generate the 4D scene and its corresponding monaural audio. 2) Subsequently, to transform the monaural audio into spatial audio, we localize and track the sound sources within the 4D scene, where their 3D spatial coordinates at different timestamps are estimated via a pixel-level visual grounding strategy. 3) Based on the estimated sound source locations, we further synthesize plausible spatial audio that varies across different viewpoints and timestamps using physics-based simulation. Extensive experiments have demonstrated that our proposed method generates realistic spatial audio consistent with the synthesized 4D scene in a training-free manner, significantly enhancing the immersive experience for users. Generated audio and video examples are available at https://x-drunker.github.io/Sonic4D-project-page.

cs.SD↗

arXiv2026

DuoDrama: Supporting Screenplay Refinement Through LLM-Assisted Human Reflection

AI has been increasingly integrated into screenwriting practice. In refinement, screenwriters expect AI to provide feedback that supports reflection across the internal perspective of characters and the external perspective of the overall story. However, existing AI tools cannot sufficiently coordinate the two perspectives to meet screenwriters' needs. To address this gap, we present DuoDrama, an AI system that generates feedback to assist screenwriters' reflection in refinement. To enable DuoDrama, based on performance theories and a formative study with nine professional screenwriters, we design the Experience-Grounded Feedback Generation Workflow for Human Reflection (ExReflect). In ExReflect, an AI agent adopts an experience role to generate experience and then shifts to an evaluation role to generate feedback based on the experience. A study with fourteen professional screenwriters shows that DuoDrama improves feedback quality and alignment and enhances the effectiveness, depth, and richness of reflection. We conclude by discussing broader implications and future directions.

cs.HC↗

arXiv2025

A Stepwise-Enhanced Reasoning Framework for Large Language Models Based on External Subgraph Generation

Large Language Models (LLMs) have achieved strong performance across a wide range of natural language processing tasks in recent years, including machine translation, text generation, and question answering. As their applications extend to increasingly complex scenarios, however, LLMs continue to face challenges in tasks that require deep reasoning and logical inference. In particular, models trained on large scale textual corpora may incorporate noisy or irrelevant information during generation, which can lead to incorrect predictions or outputs that are inconsistent with factual knowledge. To address this limitation, we propose a stepwise reasoning enhancement framework for LLMs based on external subgraph generation, termed SGR. The proposed framework dynamically constructs query relevant subgraphs from external knowledge bases and leverages their semantic structure to guide the reasoning process. By performing reasoning in a step by step manner over structured subgraphs, SGR reduces the influence of noisy information and improves reasoning accuracy. Specifically, the framework first generates an external subgraph tailored to the input query, then guides the model to conduct multi step reasoning grounded in the subgraph, and finally integrates multiple reasoning paths to produce the final answer. Experimental results on multiple benchmark datasets demonstrate that SGR consistently outperforms strong baselines, indicating its effectiveness in enhancing the reasoning capabilities of LLMs.

cs.CL↗

arXiv2025

Multiscale Cross-Modal Mapping of Molecular, Pathologic, and Radiologic Phenotypes in Lipid-Deficient Clear Cell Renal CellCarcinoma

Clear cell renal cell carcinoma (ccRCC) exhibits extensive intratumoral heterogeneity on multiple biological scales, contributing to variable clinical outcomes and limiting the effectiveness of conventional TNM staging, which highlights the urgent need for multiscale integrative analytic frameworks. The lipid-deficient de-clear cell differentiated (DCCD) ccRCC subtype, defined by multi-omics analyses, is associated with adverse outcomes even in early-stage disease. Here, we establish a hierarchical cross-scale framework for the preoperative identification of DCCD-ccRCC. At the highest layer, cross-modal mapping transferred molecular signatures to histological and CT phenotypes, establishing a molecular-to-pathology-to-radiology supervisory bridge. Within this framework, each modality-specific model is designed to mirror the inherent hierarchical structure of tumor biology. PathoDCCD captured multi-scale microscopic features, from cellular morphology and tissue architecture to meso-regional organization. RadioDCCD integrated complementary macroscopic information by combining whole-tumor and its habitat-subregions radiomics with a 2D maximal-section heterogeneity metric. These nested models enabled integrated molecular subtype prediction and clinical risk stratification. Across five cohorts totaling 1,659 patients, PathoDCCD reliably recapitulated molecular subtypes, while RadioDCCD provided reliable preoperative prediction. The consistent predictions identified patients with the poorest clinical outcomes. This cross-scale paradigm unifies molecular biology, computational pathology, and quantitative radiology into a biologically grounded strategy for preoperative noninvasive molecular phenotyping of ccRCC.

q-bio.QM↗

arXiv2025

MM-ACT: Learn from Multimodal Parallel Generation to Act

A generalist robotic policy needs both semantic understanding for task planning and the ability to interact with the environment through predictive capabilities. To tackle this, we present MM-ACT, a unified Vision-Language-Action (VLA) model that integrates text, image, and action in shared token space and performs generation across all three modalities. MM-ACT adopts a re-mask parallel decoding strategy for text and image generation, and employs a one-step parallel decoding strategy for action generation to improve efficiency. We introduce Context-Shared Multimodal Learning, a unified training paradigm that supervises generation in all three modalities from a shared context, enhancing action generation through cross-modal learning. Experiments were conducted on the LIBERO simulation and Franka real-robot setups as well as RoboTwin2.0 to assess in-domain and out-of-domain performances respectively. Our approach achieves a success rate of 96.3% on LIBERO, 72.0% across three tasks of real Franka, and 52.38% across eight bimanual tasks of RoboTwin2.0 with an additional gain of 9.25% from cross-modal learning. We release our codes, models and data at https://github.com/HHYHRHY/MM-ACT.

cs.CV↗

arXiv2025

HBFormer: A Hybrid-Bridge Transformer for Microtumor and Miniature Organ Segmentation

Medical image segmentation is a cornerstone of modern clinical diagnostics. While Vision Transformers that leverage shifted window-based self-attention have established new benchmarks in this field, they are often hampered by a critical limitation: their localized attention mechanism struggles to effectively fuse local details with global context. This deficiency is particularly detrimental to challenging tasks such as the segmentation of microtumors and miniature organs, where both fine-grained boundary definition and broad contextual understanding are paramount. To address this gap, we propose HBFormer, a novel Hybrid-Bridge Transformer architecture. The 'Hybrid' design of HBFormer synergizes a classic U-shaped encoder-decoder framework with a powerful Swin Transformer backbone for robust hierarchical feature extraction. The core innovation lies in its 'Bridge' mechanism, a sophisticated nexus for multi-scale feature integration. This bridge is architecturally embodied by our novel Multi-Scale Feature Fusion (MFF) decoder. Departing from conventional symmetric designs, the MFF decoder is engineered to fuse multi-scale features from the encoder with global contextual information. It achieves this through a synergistic combination of channel and spatial attention modules, which are constructed from a series of dilated and depth-wise convolutions. These components work in concert to create a powerful feature bridge that explicitly captures long-range dependencies and refines object boundaries with exceptional precision. Comprehensive experiments on challenging medical image segmentation datasets, including multi-organ, liver tumor, and bladder tumor benchmarks, demonstrate that HBFormer achieves state-of-the-art results, showcasing its outstanding capabilities in microtumor and miniature organ segmentation. Code and models are available at: https://github.com/lzeeorno/HBFormer.

cs.CV↗

arXiv2025

4DWorldBench: A Comprehensive Evaluation Framework for 3D/4D World Generation Models

World Generation Models are emerging as a cornerstone of next-generation multimodal intelligence systems. Unlike traditional 2D visual generation, World Models aim to construct realistic, dynamic, and physically consistent 3D/4D worlds from images, videos, or text. These models not only need to produce high-fidelity visual content but also maintain coherence across space, time, physics, and instruction control, enabling applications in virtual reality, autonomous driving, embodied intelligence, and content creation. However, prior benchmarks emphasize different evaluation dimensions and lack a unified assessment of world-realism capability. To systematically evaluate World Models, we introduce the 4DWorldBench, which measures models across four key dimensions: Perceptual Quality, Condition-4D Alignment, Physical Realism, and 4D Consistency. The benchmark covers tasks such as Image-to-3D/4D, Video-to-4D, Text-to-3D/4D. Beyond these, we innovatively introduce adaptive conditioning across multiple modalities, which not only integrates but also extends traditional evaluation paradigms. To accommodate different modality-conditioned inputs, we map all modality conditions into a unified textual space during evaluation, and further integrate LLM-as-judge, MLLM-as-judge, and traditional network-based methods. This unified and adaptive design enables more comprehensive and consistent evaluation of alignment, physical realism, and cross-modal coherence. Preliminary human studies further demonstrate that our adaptive tool selection achieves closer agreement with subjective human judgments. We hope this benchmark will serve as a foundation for objective comparisons and improvements, accelerating the transition from "visual generation" to "world generation." Our project can be found at https://yeppp27.github.io/4DWorldBench.github.io/.

cs.CV↗

arXiv2025

Inferring the Impacts of Baryonic Feedback from Kinetic Sunyaev-Zeldovich Cross-Correlations

The complex processes of baryonic feedback associated with galaxy evolution are still poorly understood, and their impact on the clustering of matter on small scales remains difficult to quantify. While many fitting functions and emulators exist to model the matter power spectrum, their input parameters are not directly observable. However, recent studies using hydrodynamical simulations have identified a promising correlation between the gas content of halos and changes to the matter power spectrum from feedback. Building on these findings, we create the first fully data-driven power spectrum emulator. We utilize the kinematic Sunyaev-Zeldovich (kSZ) effect, a secondary anisotropy in the cosmic microwave background, as a tracer of free electrons in and around halos. We train a neural network to learn the mapping between the suppression of the matter power spectrum and the shape of the kSZ power spectrum extracted with a radial velocity template. We train and validate our algorithm using the FLAMINGO suite of hydrodynamical simulations, which encompasses a wide range of feedback models. Our emulator can reconstruct the matter power spectrum at the sub-percent level for scales $k\leq 5\;h/$Mpc and $0.2\leq z \leq 1.25$ directly from the data. Our model is robust and retains percent-level accuracy even for feedback models and cosmological parameter values not seen during training (except in a few extreme cases drastically different from the fiducial model). Due to its robustness, our algorithm offers a new way to identify the sources of suppression in the matter power spectrum, breaking the degeneracies between baryonic feedback and new physics. Finally, we present a forecast for reconstruction of the matter power spectrum combining maps of the microwave background anisotropies from a Simons Observatory-like experiment and galaxy catalogs from the Dark Energy Spectroscopic Instrument.

astro-ph.CO↗

arXiv2025

EvalCards: A Framework for Standardized Evaluation Reporting

Evaluation has long been a central concern in NLP, and transparent reporting practices are more critical than ever in today's landscape of rapidly released open-access models. Drawing on a survey of recent work on evaluation and documentation, we identify three persistent shortcomings in current reporting practices: reproducibility, accessibility, and governance. We argue that existing standardization efforts remain insufficient and introduce Evaluation Disclosure Cards (EvalCards) as a path forward. EvalCards are designed to enhance transparency for both researchers and practitioners while providing a practical foundation to meet emerging governance requirements.

cs.CL↗

arXiv2025

CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling

Recent vision-language-action (VLA) models built on pretrained vision-language models (VLMs) have demonstrated strong performance in robotic manipulation. However, these models remain constrained by the single-frame image paradigm and fail to fully leverage the temporal information offered by multi-frame histories, as directly feeding multiple frames into VLM backbones incurs substantial computational overhead and inference latency. We propose CronusVLA, a unified framework that extends single-frame VLA models to the multi-frame paradigm. CronusVLA follows a two-stage process: (1) Single-frame pretraining on large-scale embodied datasets with autoregressive prediction of action tokens, establishing an effective embodied vision-language foundation; (2) Multi-frame post-training, which adapts the prediction of the vision-language backbone from discrete tokens to learnable features, and aggregates historical information via feature chunking. CronusVLA effectively addresses the existing challenges of multi-frame modeling while enhancing performance and observational robustness. To evaluate the robustness under temporal and spatial disturbances, we introduce SimplerEnv-OR, a novel benchmark featuring 24 types of observational disturbances and 120 severity levels. Experiments across three embodiments in simulated and real-world environments demonstrate that CronusVLA achieves leading performance and superior robustness, with a 70.9% success rate on SimplerEnv, a 26.8% improvement over OpenVLA on LIBERO, and the highest robustness score on SimplerEnv-OR. These results highlight the potential of efficient multi-frame adaptation in VLA models for more powerful and robust real-world deployment.

cs.RO↗

arXiv2025

Modelling the Spatially Varying Non-Linear Effects of Heat Exposure

Exposure to high ambient temperatures is a significant driver of preventable mortality, with non-linear health effects and elevated risks in specific regions. To capture this complexity and account for spatial dependencies across small areas, we propose a Bayesian framework that integrates non-linear functions with the Besag, York, and Mollie (BYM2) model. Applying this framework to all-cause mortality data in Switzerland, we quantified spatial inequalities in heat-related mortality. We retrieved daily all-cause mortality at small areas (2,145 municipalities) for people older than 65 years from the Swiss Federal Office of Public Health and daily mean temperature at 1km$\times$1km grid from the Swiss Federal Office of Meteorology. By fully propagating uncertainties, we derived key epidemiological metrics, including heat-related excess mortality and minimum mortality temperature (MMT). Heat-related excess mortality rates were higher in northern Switzerland, while lower MMTs were observed in mountainous regions. Further, we explored the role of the proportion of individuals older than 85 years, green space, average temperature, deprivation, urbanicity, air pollution, and language regions in explaining these discrepancies. We found that spatial disparities in heat-related excess mortality were primarily driven by population age distribution, green space, and vulnerabilities associated with elevated temperature exposure.

stat.AP↗

arXiv2025

Lost at the Beginning of Reasoning

Recent advancements in large language models (LLMs) have significantly advanced complex reasoning capabilities, particularly through extended chain-of-thought (CoT) reasoning that incorporates mechanisms such as backtracking, self-reflection, and self-correction. Despite these developments, the self-correction abilities of LLMs during long CoT reasoning remain underexplored. And recent findings on overthinking suggest that such models often engage in unnecessarily redundant reasoning. In this work, we empirically show that the first reasoning step exerts a disproportionately large influence on the final prediction. I.e., errors introduced at this stage can substantially degrade subsequent reasoning quality. This phenomenon is consistently observed across various state-of-the-art open- and closed-source reasoning models. Leveraging this insight, we propose an efficient sampling strategy that leverages a reward model to identify and retain high-quality first reasoning steps while discarding suboptimal ones, achieving up to a 70% reduction in inference cost without sacrificing any accuracy. Our work highlights the central role of the first reasoning step in generating a high-quality reasoning trajectory, and thus enabling significantly efficient sampling.

cs.CL↗

arXiv2025

InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

We introduce InternVLA-M1, a unified framework for spatial grounding and robot control that advances instruction-following robots toward scalable, general-purpose intelligence. Its core idea is spatially guided vision-language-action training, where spatial grounding serves as the critical link between instructions and robot actions. InternVLA-M1 employs a two-stage pipeline: (i) spatial grounding pre-training on over 2.3M spatial reasoning data to determine ``where to act'' by aligning instructions with visual, embodiment-agnostic positions, and (ii) spatially guided action post-training to decide ``how to act'' by generating embodiment-aware actions through plug-and-play spatial prompting. This spatially guided training recipe yields consistent gains: InternVLA-M1 outperforms its variant without spatial guidance by +14.6% on SimplerEnv Google Robot, +17% on WidowX, and +4.3% on LIBERO Franka, while demonstrating stronger spatial reasoning capability in box, point, and trace prediction. To further scale instruction following, we built a simulation engine to collect 244K generalizable pick-and-place episodes, enabling a 6.2% average improvement across 200 tasks and 3K+ objects. In real-world clustered pick-and-place, InternVLA-M1 improved by 7.3%, and with synthetic co-training, achieved +20.6% on unseen objects and novel configurations. Moreover, in long-horizon reasoning-intensive scenarios, it surpassed existing works by over 10%. These results highlight spatially guided training as a unifying principle for scalable and resilient generalist robots. Code and models are available at https://github.com/InternRobotics/InternVLA-M1.

cs.RO↗

arXiv2025

Efficient Training of Spiking Neural Networks by Spike-aware Data Pruning

Spiking neural networks (SNNs), recognized as an energy-efficient alternative to traditional artificial neural networks (ANNs), have advanced rapidly through the scaling of models and datasets. However, such scaling incurs considerable training overhead, posing challenges for researchers with limited computational resources and hindering the sustained development of SNNs. Data pruning is a promising strategy for accelerating training by retaining the most informative examples and discarding redundant ones, but it remains largely unexplored in SNNs. Directly applying ANN-based data pruning methods to SNNs fails to capture the intrinsic importance of examples and suffers from high gradient variance. To address these challenges, we propose a novel spike-aware data pruning (SADP) method. SADP reduces gradient variance by determining each example's selection probability to be proportional to its gradient norm, while avoiding the high cost of direct gradient computation through an efficient upper bound, termed spike-aware importance score. This score accounts for the influence of all-or-nothing spikes on the gradient norm and can be computed with negligible overhead. Extensive experiments across diverse datasets and architectures demonstrate that SADP consistently outperforms data pruning baselines and achieves training speedups close to the theoretical maxima at different pruning ratios. Notably, SADP reduces training time by 35% on ImageNet while maintaining accuracy comparable to that of full-data training. This work, therefore, establishes a data-centric paradigm for efficient SNN training and paves the way for scaling SNNs to larger models and datasets. The source code will be released publicly after the review process.

cs.NE↗

arXiv2025

What if Othello-Playing Language Models Could See?

Language models are often said to face a symbol grounding problem. While some have argued the problem can be solved without resort to other modalities, many have speculated that grounded learning is more efficient. We explore this question in Othello, a simplified, rule-based world that offers a controlled and interpretable testbed for studying world understanding. Building on prior work, we introduce VISOTHELLO, a multi-modal model trained jointly on move sequences and board images. Using the Othello rule understanding task, we examine whether multi-modal learning provides advantages over text-only approaches. We further evaluate robustness under semantically irrelevant perturbations and analyze the consistency of cross-modal alignment. Our results suggest that multi-modal training not only improves performance and robustness but also promotes convergence toward shared internal representations across different model architectures.

cs.AI↗

arXiv2025

PodEval: A Multimodal Evaluation Framework for Podcast Audio Generation

Recently, an increasing number of multimodal (text and audio) benchmarks have emerged, primarily focusing on evaluating models' understanding capability. However, exploration into assessing generative capabilities remains limited, especially for open-ended long-form content generation. Significant challenges lie in no reference standard answer, no unified evaluation metrics and uncontrollable human judgments. In this work, we take podcast-like audio generation as a starting point and propose PodEval, a comprehensive and well-designed open-source evaluation framework. In this framework: 1) We construct a real-world podcast dataset spanning diverse topics, serving as a reference for human-level creative quality. 2) We introduce a multimodal evaluation strategy and decompose the complex task into three dimensions: text, speech and audio, with different evaluation emphasis on "Content" and "Format". 3) For each modality, we design corresponding evaluation methods, involving both objective metrics and subjective listening test. We leverage representative podcast generation systems (including open-source, close-source, and human-made) in our experiments. The results offer in-depth analysis and insights into podcast generation, demonstrating the effectiveness of PodEval in evaluating open-ended long-form audio. This project is open-source to facilitate public use: https://github.com/yujxx/PodEval.

cs.SD↗

arXiv2025

INTA: Intent-Based Translation for Network Configuration with LLM Agents

Translating configurations between different network devices is a common yet challenging task in modern network operations. This challenge arises in typical scenarios such as replacing obsolete hardware and adapting configurations to emerging paradigms like Software Defined Networking (SDN) and Network Function Virtualization (NFV). Engineers need to thoroughly understand both source and target configuration models, which requires considerable effort due to the complexity and evolving nature of these specifications. To promote automation in network configuration translation, we propose INTA, an intent-based translation framework that leverages Large Language Model (LLM) agents. The key idea of INTA is to use configuration intent as an intermediate representation for translation. It first employs LLMs to decompose configuration files and extract fine-grained intents for each configuration fragment. These intents are then used to retrieve relevant manuals of the target device. Guided by a syntax checker, INTA incrementally generates target configurations. The translated configurations are further verified and refined for semantic consistency. We implement INTA and evaluate it on real-world configuration datasets from the industry. Our approach outperforms state-of-the-art methods in translation accuracy and exhibits strong generalizability. INTA achieves an accuracy of 98.15% in terms of both syntactic and view correctness, and a command recall rate of 84.72% for the target configuration. The semantic consistency report of the translated configuration further demonstrates its practical value in real-world network operations.

cs.NI↗

arXiv2025

AFT: An Exemplar-Free Class Incremental Learning Method for Environmental Sound Classification

As sounds carry rich information, environmental sound classification (ESC) is crucial for numerous applications such as rare wild animals detection. However, our world constantly changes, asking ESC models to adapt to new sounds periodically. The major challenge here is catastrophic forgetting, where models lose the ability to recognize old sounds when learning new ones. Many methods address this using replay-based continual learning. This could be impractical in scenarios such as data privacy concerns. Exemplar-free methods are commonly used but can distort old features, leading to worse performance. To overcome such limitations, we propose an Acoustic Feature Transformation (AFT) technique that aligns the temporal features of old classes to the new space, including a selectively compressed feature space. AFT mitigates the forgetting of old knowledge without retaining past data. We conducted experiments on two datasets, showing consistent improvements over baseline models with accuracy gains of 3.7\% to 3.9\%.

eess.AS↗