arXiv subjects

Guo Chen

Publications and source records attributed to Guo Chen.

At least 55 records · Page 3Linked to original sources

arXiv2025

Learning Visual Affordance from Audio

We introduce Audio-Visual Affordance Grounding (AV-AG), a new task that segments object interaction regions from action sounds. Unlike existing approaches that rely on textual instructions or demonstration videos, which often limited by ambiguity or occlusion, audio provides real-time, semantically rich, and visually independent cues for affordance grounding, enabling more intuitive understanding of interaction regions. To support this task, we construct the first AV-AG dataset, comprising a large collection of action sounds, object images, and pixel-level affordance annotations. The dataset also includes an unseen subset to evaluate zero-shot generalization. Furthermore, we propose AVAGFormer, a model equipped with a semantic-conditioned cross-modal mixer and a dual-head decoder that effectively fuses audio and visual signals for mask prediction. Experiments show that AVAGFormer achieves state-of-the-art performance on AV-AG, surpassing baselines from related tasks. Comprehensive analyses highlight the distinctions between AV-AG and AVS, the benefits of end-to-end modeling, and the contribution of each component. Code and dataset have been released on https://jscslld.github.io/AVAGFormer/.

cs.CV↗

arXiv2025

M2G-Eval: Enhancing and Evaluating Multi-granularity Multilingual Code Generation

The rapid advancement of code large language models (LLMs) has sparked significant research interest in systematically evaluating their code generation capabilities, yet existing benchmarks predominantly assess models at a single structural granularity and focus on limited programming languages, obscuring fine-grained capability variations across different code scopes and multilingual scenarios. We introduce M2G-Eval, a multi-granularity, multilingual framework for evaluating code generation in large language models (LLMs) across four levels: Class, Function, Block, and Line. Spanning 18 programming languages, M2G-Eval includes 17K+ training tasks and 1,286 human-annotated, contamination-controlled test instances. We develop M2G-Eval-Coder models by training Qwen3-8B with supervised fine-tuning and Group Relative Policy Optimization. Evaluating 30 models (28 state-of-the-art LLMs plus our two M2G-Eval-Coder variants) reveals three main findings: (1) an apparent difficulty hierarchy, with Line-level tasks easiest and Class-level most challenging; (2) widening performance gaps between full- and partial-granularity languages as task complexity increases; and (3) strong cross-language correlations, suggesting that models learn transferable programming concepts. M2G-Eval enables fine-grained diagnosis of code generation capabilities and highlights persistent challenges in synthesizing complex, long-form code.

cs.CL↗

arXiv2025

A possible periodic RM evolution in the repeating FRB 20220529

Fast radio bursts (FRBs) are mysterious millisecond-duration radio transients of extragalactic origin. Some of them repeat, while others apparently do not. Investigations of periodic activity in repeating FRB have been conducted to probe their origins. While periodicity in the burst rate has been reported, studies of periodicities in other properties, such as dispersion measure (DM) and rotation measure (RM), are sparse. FRB~20220529 was monitored by the Five-hundred-meter Aperture Spherical radio Telescope (FAST) for nearly three years, providing an opportunity to investigate periodicity in its observed properties. Here we report a possible period of $\sim 200$ days in the RM evolution, with a significance of {4.1 $σ$} estimated via the Lomb-Scargle algorithm and {3.1 $σ$} with the phase-folding method. Periodicity in the burst rate was also investigated. It may indicate that the FRB progenitor is in a binary system, which is consistent with the significant RM increase and prompt recovery of this FRB on a week-timescale. Other scenarios, such as a system with an intermediate-mass black hole, are also explored.

astro-ph.HE↗

arXiv2025

Boosting Adversarial Transferability via Ensemble Non-Attention

Ensemble attacks integrate the outputs of surrogate models with diverse architectures, which can be combined with various gradient-based attacks to improve adversarial transferability. However, previous work shows unsatisfactory attack performance when transferring across heterogeneous model architectures. The main reason is that the gradient update directions of heterogeneous surrogate models differ widely, making it hard to reduce the gradient variance of ensemble models while making the best of individual model. To tackle this challenge, we design a novel ensemble attack, NAMEA, which for the first time integrates the gradients from the non-attention areas of ensemble models into the iterative gradient optimization process. Our design is inspired by the observation that the attention areas of heterogeneous models vary sharply, thus the non-attention areas of ViTs are likely to be the focus of CNNs and vice versa. Therefore, we merge the gradients respectively from the attention and non-attention areas of ensemble models so as to fuse the transfer information of CNNs and ViTs. Specifically, we pioneer a new way of decoupling the gradients of non-attention areas from those of attention areas, while merging gradients by meta-learning. Empirical evaluations on ImageNet dataset indicate that NAMEA outperforms AdaEA and SMER, the state-of-the-art ensemble attacks by an average of 15.0% and 9.6%, respectively. This work is the first attempt to explore the power of ensemble non-attention in boosting cross-architecture transferability, providing new insights into launching ensemble attacks.

cs.CV↗

arXiv2025

NVIDIA Nemotron Nano V2 VL

We introduce Nemotron Nano V2 VL, the latest model of the Nemotron vision-language series designed for strong real-world document understanding, long video comprehension, and reasoning tasks. Nemotron Nano V2 VL delivers significant improvements over our previous model, Llama-3.1-Nemotron-Nano-VL-8B, across all vision and text domains through major enhancements in model architecture, datasets, and training recipes. Nemotron Nano V2 VL builds on Nemotron Nano V2, a hybrid Mamba-Transformer LLM, and innovative token reduction techniques to achieve higher inference throughput in long document and video scenarios. We are releasing model checkpoints in BF16, FP8, and FP4 formats and sharing large parts of our datasets, recipes and training code.

cs.LG↗

arXiv2025

EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT

Egocentric video reasoning centers on an unobservable agent behind the camera who dynamically shapes the environment, requiring inference of hidden intentions and recognition of fine-grained interactions. This core challenge limits current multimodal large language models MLLMs, which excel at visible event reasoning but lack embodied, first-person understanding. To bridge this gap, we introduce EgoThinker, a novel framework that endows MLLMs with robust egocentric reasoning capabilities through spatio-temporal chain-of-thought supervision and a two-stage learning curriculum. First, we introduce EgoRe-5M, a large-scale egocentric QA dataset constructed from 13M diverse egocentric video clips. This dataset features multi-minute segments annotated with detailed CoT rationales and dense hand-object grounding. Second, we employ SFT on EgoRe-5M to instill reasoning skills, followed by reinforcement fine-tuning RFT to further enhance spatio-temporal localization. Experimental results show that EgoThinker outperforms existing methods across multiple egocentric benchmarks, while achieving substantial improvements in fine-grained spatio-temporal localization tasks. Full code and data are released at https://github.com/InternRobotics/EgoThinker.

cs.CV↗

arXiv2025

Concise and Sufficient Sub-Sentence Citations for Retrieval-Augmented Generation

In retrieval-augmented generation (RAG) question answering systems, generating citations for large language model (LLM) outputs enhances verifiability and helps users identify potential hallucinations. However, we observe two problems in the citations produced by existing attribution methods. First, the citations are typically provided at the sentence or even paragraph level. Long sentences or paragraphs may include a substantial amount of irrelevant content. Second, sentence-level citations may omit information that is essential for verifying the output, forcing users to read the surrounding context. In this paper, we propose generating sub-sentence citations that are both concise and sufficient, thereby reducing the effort required by users to confirm the correctness of the generated output. To this end, we first develop annotation guidelines for such citations and construct a corresponding dataset. Then, we propose an attribution framework for generating citations that adhere to our standards. This framework leverages LLMs to automatically generate fine-tuning data for our task and employs a credit model to filter out low-quality examples. Our experiments on the constructed dataset demonstrate that the propose approach can generate high-quality and more readable citations.

cs.CL↗

arXiv2025

Text2Schema: Filling the Gap in Designing Database Table Structures based on Natural Language

People without a database background usually rely on file systems or tools such as Excel for data management, which often lead to redundancy and data inconsistency. Relational databases possess strong data management capabilities, but require a high level of professional expertise from users. Although there are already many works on Text2SQL to automate the translation of natural language into SQL queries for data manipulation, all of them presuppose that the database schema is pre-designed. In practice, schema design itself demands domain expertise, and research on directly generating schemas from textual requirements remains unexplored. In this paper, we systematically define a new problem, called Text2Schema, to convert a natural language text requirement into a relational database schema. With an effective Text2Schema technique, users can effortlessly create database table structures using natural language, and subsequently leverage existing Text2SQL techniques to perform data manipulations, which significantly narrows the gap between non-technical personnel and highly efficient, versatile relational database systems. We propose SchemaAgent, an LLM-based multi-agent framework for Text2Schema. We emulate the workflow of manual schema design by assigning specialized roles to agents and enabling effective collaboration to refine their respective subtasks. We also incorporate dedicated roles for reflection and inspection, along with an innovative error detection and correction mechanism to identify and rectify issues across various phases. Moreover, we build and open source a benchmark containing 381 pairs of requirement description and schema. Experimental results demonstrate the superiority of our approach over comparative work.

cs.DB↗

arXiv2025

Detection of OH and Fe in the dayside atmosphere of the hottest ultra-hot Jupiter KELT-9b with SPIRou

Simultaneous measurements of volatile and refractory elements are essential for tracing the formation and migration of ultra-hot Jupiters (UHJs). High-resolution infrared emission spectroscopy has been widely used to probe their atmospheres, covering molecules and atoms. For the hottest known planet, KELT-9b, whose dayside atmosphere is nearly fully dissociated and ionized, no molecules had been firmly detected. Here we report the first detection of OH in the dayside atmosphere of KELT-9b, based on two thermal emission observations with the SPIRou spectrograph, and confirm the presence of Fe. We performed a self-consistent retrieval under chemical equilibrium, constraining elemental abundances and metallicity. A significant thermal inversion layer is confirmed. No significant Doppler shifts were found, and the retrieved equatorial rotation matches the tidally locked value. The oxygen abundance is consistent with solar to supersolar (0.61$_{-0.58}^{+1.19}$ dex), while the C/O ratio and metallicity are subsolar to solar. The low metallicity may indicate a well-mixed envelope and interior. Constraints remain broad, and the data are consistent with supersolar C/O and subsolar O. Combined [C/O] and [O/H] are compatible with formation beyond the water snowline followed by inward migration, though other scenarios cannot be excluded. Volatile-to-refractory ratios, [O/Fe] = 1.25$_{-0.74}^{+0.99}$ dex and [C/Fe] = 0.60$_{-0.74}^{+0.62}$ dex, lie in the solar to supersolar range, but uncertainties limit firm conclusions. Results provide tentative evidence for volatile enrichment. Future high-resolution optical-to-infrared spectra with JWST will enable more precise abundance constraints and stronger insights into UHJ formation and migration. We also advocate a retrieval-guided cross-correlation strategy to reduce risk of missing marginal detections, as illustrated by tentative evidence for CO.

astro-ph.EP↗

arXiv2025

GS-RoadPatching: Inpainting Gaussians via 3D Searching and Placing for Driving Scenes

This paper presents GS-RoadPatching, an inpainting method for driving scene completion by referring to completely reconstructed regions, which are represented by 3D Gaussian Splatting (3DGS). Unlike existing 3DGS inpainting methods that perform generative completion relying on 2D perspective-view-based diffusion or GAN models to predict limited appearance or depth cues for missing regions, our approach enables substitutional scene inpainting and editing directly through the 3DGS modality, extricating it from requiring spatial-temporal consistency of 2D cross-modals and eliminating the need for time-intensive retraining of Gaussians. Our key insight is that the highly repetitive patterns in driving scenes often share multi-modal similarities within the implicit 3DGS feature space and are particularly suitable for structural matching to enable effective 3DGS-based substitutional inpainting. Practically, we construct feature-embedded 3DGS scenes to incorporate a patch measurement method for abstracting local context at different scales and, subsequently, propose a structural search method to find candidate patches in 3D space effectively. Finally, we propose a simple yet effective substitution-and-fusion optimization for better visual harmony. We conduct extensive experiments on multiple publicly available datasets to demonstrate the effectiveness and efficiency of our proposed method in driving scenes, and the results validate that our method achieves state-of-the-art performance compared to the baseline methods in terms of both quality and interoperability. Additional experiments in general scenes also demonstrate the applicability of the proposed 3D inpainting strategy. The project page and code are available at: https://shanzhaguoo.github.io/GS-RoadPatching/

cs.CV↗

arXiv2025

STORM: Token-Efficient Long Video Understanding for Multimodal LLMs

Recent advances in video-based multimodal large language models (Video-LLMs) have significantly improved video understanding by processing videos as sequences of image frames. However, many existing methods treat frames independently in the vision backbone, lacking explicit temporal modeling, which limits their ability to capture dynamic patterns and efficiently handle long videos. To address these limitations, we introduce STORM (Spatiotemporal TOken Reduction for Multimodal LLMs), a novel architecture incorporating a dedicated temporal encoder between the image encoder and the LLM. Our temporal encoder leverages the Mamba State Space Model to integrate temporal information into image tokens, generating enriched representations that preserve inter-frame dynamics across the entire video sequence. This enriched encoding not only enhances video reasoning capabilities but also enables effective token reduction strategies, including test-time sampling and training-based temporal and spatial pooling, substantially reducing computational demands on the LLM without sacrificing key temporal information. By integrating these techniques, our approach simultaneously reduces training and inference latency while improving performance, enabling efficient and robust video understanding over extended temporal contexts. Extensive evaluations show that STORM achieves state-of-the-art results across various long video understanding benchmarks (more than 5% improvement on MLVU and LongVideoBench) while reducing the computation costs by up to $8\times$ and the decoding latency by 2.4-2.9$\times$ for the fixed numbers of input frames. Project page is available at https://research.nvidia.com/labs/lpr/storm

cs.CV↗

arXiv2025

Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models

As inference-time scaling becomes critical for enhanced reasoning capabilities, it is increasingly becoming important to build models that are efficient to infer. We introduce Nemotron-H, a family of 8B and 56B/47B hybrid Mamba-Transformer models designed to reduce inference cost for a given accuracy level. To achieve this goal, we replace the majority of self-attention layers in the common Transformer model architecture with Mamba layers that perform constant computation and require constant memory per generated token. We show that Nemotron-H models offer either better or on-par accuracy compared to other similarly-sized state-of-the-art open-sourced Transformer models (e.g., Qwen-2.5-7B/72B and Llama-3.1-8B/70B), while being up to 3$\times$ faster at inference. To further increase inference speed and reduce the memory required at inference time, we created Nemotron-H-47B-Base from the 56B model using a new compression via pruning and distillation technique called MiniPuzzle. Nemotron-H-47B-Base achieves similar accuracy to the 56B model, but is 20% faster to infer. In addition, we introduce an FP8-based training recipe and show that it can achieve on par results with BF16-based training. This recipe is used to train the 56B model. We are releasing Nemotron-H base model checkpoints with support in Hugging Face and NeMo.

cs.CL↗

arXiv2025

Advances in Speech Separation: Techniques, Challenges, and Future Trends

The field of speech separation, addressing the "cocktail party problem", has seen revolutionary advances with DNNs. Speech separation enhances clarity in complex acoustic environments and serves as crucial pre-processing for speech recognition and speaker recognition. However, current literature focuses narrowly on specific architectures or isolated approaches, creating fragmented understanding. This survey addresses this gap by providing systematic examination of DNN-based speech separation techniques. Our work differentiates itself through: (I) Comprehensive perspective: We systematically investigate learning paradigms, separation scenarios with known/unknown speakers, comparative analysis of supervised/self-supervised/unsupervised frameworks, and architectural components from encoders to estimation strategies. (II) Timeliness: Coverage of cutting-edge developments ensures access to current innovations and benchmarks. (III) Unique insights: Beyond summarization, we evaluate technological trajectories, identify emerging patterns, and highlight promising directions including domain-robust frameworks, efficient architectures, multimodal integration, and novel self-supervised paradigms. (IV) Fair evaluation: We provide quantitative evaluations on standard datasets, revealing true capabilities and limitations of different methods. This comprehensive survey serves as an accessible reference for experienced researchers and newcomers navigating speech separation's complex landscape.

cs.SD↗

arXiv2025

Enhancing Spectrogram Realism in Singing Voice Synthesis via Explicit Bandwidth Extension Prior to Vocoder

This paper addresses the challenge of enhancing the realism of vocoder-generated singing voice audio by mitigating the distinguishable disparities between synthetic and real-life recordings, particularly in high-frequency spectrogram components. Our proposed approach combines two innovations: an explicit linear spectrogram estimation step using denoising diffusion process with DiT-based neural network architecture optimized for time-frequency data, and a redesigned vocoder based on Vocos specialized in handling large linear spectrograms with increased frequency bins. This integrated method can produce audio with high-fidelity spectrograms that are challenging for both human listeners and machine classifiers to differentiate from authentic recordings. Objective and subjective evaluations demonstrate that our streamlined approach maintains high audio quality while achieving this realism. This work presents a substantial advancement in overcoming the limitations of current vocoding techniques, particularly in the context of adversarial attacks on fake spectrogram detection.

cs.SD↗

arXiv2025

EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs

Transferring and integrating knowledge across first-person (egocentric) and third-person (exocentric) viewpoints is intrinsic to human intelligence, enabling humans to learn from others and convey insights from their own experiences. Despite rapid progress in multimodal large language models (MLLMs), their ability to perform such cross-view reasoning remains unexplored. To address this, we introduce EgoExoBench, the first benchmark for egocentric-exocentric video understanding and reasoning. Built from publicly available datasets, EgoExoBench comprises over 7,300 question-answer pairs spanning eleven sub-tasks organized into three core challenges: semantic alignment, viewpoint association, and temporal reasoning. We evaluate 13 state-of-the-art MLLMs and find that while these models excel on single-view tasks, they struggle to align semantics across perspectives, accurately associate views, and infer temporal dynamics in the ego-exo context. We hope EgoExoBench can serve as a valuable resource for research on embodied agents and intelligent assistants seeking human-like cross-view intelligence.

cs.CV↗

arXiv2025

AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs

Despite progress in video understanding, current MLLMs struggle with counting tasks. Existing benchmarks are limited by short videos, close-set queries, lack of clue annotations, and weak multimodal coverage. In this paper, we introduce CG-AV-Counting, a manually-annotated clue-grounded counting benchmark with 1,027 multimodal questions and 5,845 annotated clues over 497 long videos. It supports both black-box and white-box evaluation, serving as a comprehensive testbed for both end-to-end and reasoning-based counting. To explore ways to improve model's counting capability, we propose AV-Reasoner, a model trained with GRPO and curriculum learning to generalize counting ability from related tasks. AV-Reasoner achieves state-of-the-art results across multiple benchmarks, demonstrating the effectiveness of reinforcement learning. However, experiments show that on out-of-domain benchmarks, reasoning in the language space fails to bring performance gains. The code and benchmark have been released on https://av-reasoner.github.io.

cs.CV↗

arXiv2025

Miniaturized optically-generated Bessel beam ultrasound for volumetric transcranial brain stimulation

Non-invasive stimulation of small, variably shaped brain sub-regions is crucial for advancing our understanding of brain functions. Current ultrasound neuromodulation faces two significant trade-offs when targeting brain sub-regions: miniaturization versus volumetric control and spatial resolution versus transcranial capability. Here, we present an optically-generated Bessel beam ultrasound (OBUS) device designed to overcome these limitations. This 2.33 mm-diameter miniaturized device delivers a column-shaped field achieving a lateral resolution of 152 um and an axial resolution of 1.93 mm, targeting brain sub-regions with an elongated volume of tissue activation. Immunofluorescence imaging of mouse brain slices confirms its ability to stimulate cells at a depth of 2.2 mm. Additionally, OBUS outperforms conventional Gaussian ultrasound in transcranial transmission efficiency and beam shape preservation. Electrophysiological recordings and functional MRI captured rodent brain responses evoked by OBUS, demonstrating OBUS's ability to non-invasively activate neural circuits in intact brains. This technology offers new possibilities for studying brain functions with precision and volumetric control.

q-bio.NC↗

arXiv2025

A Real-time Endoscopic Image Denoising System

Endoscopes featuring a miniaturized design have significantly enhanced operational flexibility, portability, and diagnostic capability while substantially reducing the invasiveness of medical procedures. Recently, single-use endoscopes equipped with an ultra-compact analogue image sensor measuring less than 1mm x 1mm bring revolutionary advancements to medical diagnosis. They reduce the structural redundancy and large capital expenditures associated with reusable devices, eliminate the risk of patient infections caused by inadequate disinfection, and alleviate patient suffering. However, the limited photosensitive area results in reduced photon capture per pixel, requiring higher photon sensitivity settings to maintain adequate brightness. In high-contrast medical imaging scenarios, the small-sized sensor exhibits a constrained dynamic range, making it difficult to simultaneously capture details in both highlights and shadows, and additional localized digital gain is required to compensate. Moreover, the simplified circuit design and analog signal transmission introduce additional noise sources. These factors collectively contribute to significant noise issues in processed endoscopic images. In this work, we developed a comprehensive noise model for analog image sensors in medical endoscopes, addressing three primary noise types: fixed-pattern noise, periodic banding noise, and mixed Poisson-Gaussian noise. Building on this analysis, we propose a hybrid denoising system that synergistically combines traditional image processing algorithms with advanced learning-based techniques for captured raw frames from sensors. Experiments demonstrate that our approach effectively reduces image noise without fine detail loss or color distortion, while achieving real-time performance on FPGA platforms and an average PSNR improvement from 21.16 to 33.05 on our test dataset.

eess.IV↗