Searcharxiv⌕ Search

arXiv subjects

Sirui Wang

Publications and source records attributed to Sirui Wang.

At least 19 recordsLinked to original sources

Rapid Graviton Thermalization through a Scalar--Gauss--Bonnet Coupling

We show that gravitons can thermalize much faster than the universe expands in an effective scalar-mediated model. A thermal fermion bath maintains a massive scalar close to equilibrium, while scalar decay and inverse decay, $ϕ\rightleftarrows g+g$, drive the graviton distribution toward a Bose--Einstein distribution with zero chemical potential. We establish this equilibrium state and calculate how it is reached from an initially empty graviton sector. For a scalar mass of $1\,{\rm TeV}$, an interaction scale $Λ_{\rm int}=m_ϕ/0.03$, and a Yukawa coupling $y=0.03$, the graviton occupations approach their equilibrium values to within $0.1\%$ over $0.1\leq p/T\leq5$ after approximately $0.024$ initial Hubble times, including cosmic expansion and energy transfer from the bath. This interval contains the thermal energy-spectrum peak. The scalar remains close to equilibrium, its vacuum decay widths are narrow, and the graviton interaction is perturbative over the reaction domain. Assuming the effective theory applies on this domain, our results demonstrate that gravitons can reach near-thermal equilibrium under these conditions. We also derive the present-day thermal spectrum for a specified decoupling and entropy history.

astro-ph.CO↗

LandslideFM: A Foundation Model Towards Unified Landslide Perception and Understanding

Intelligent landslide detection is essential for disaster prevention. However, existing models primarily focus on isolated visual tasks, require extensive labeled data, and lack deep analytical and scene-understanding capabilities. To address these limitations, we propose LandslideFM, the first unified foundation model that connects visual perception tasks with contextual interpretation of landslides. Specifically, LandslideFM adapts to multiple visual tasks via a Source-Agreement Graduated Trust semi-supervised learning framework that leverages limited labeled data alongside abundant unlabeled data. Furthermore, predicted landslide regions provide explicit spatial guidance to a Vision-Language Model adapted through parameter-efficient fine-tuning, enabling comprehensive landslide reasoning. To support training and evaluation in this domain, we also present LandslideVL, the first benchmark for intelligent landslide analysis, combining visual imagery and newly introduced textual prompts. Comprehensive experiments across public datasets and LandslideVL demonstrate that LandslideFM achieves superior quantitative and qualitative performance. Most importantly, LandslideFM surpasses general-purpose VLMs in specialized landslide reasoning and scene analysis. Our code is released at https://github.com/wangshanwen001/LandslideFM.

cs.AI↗

Tempo-Zero: Recursive Self-Play in Executable Worlds for Video Reasoning

Video reasoning requires understanding how events unfold over time, yet videos with accurate temporal annotations are expensive to collect. Self-play offers an alternative by letting a model generate and solve its own tasks without manual annotation. However, existing video self-play methods train on fixed sets of recorded videos, so they cannot alter the underlying event dynamics and rely on noisy pseudo-labels derived from the model's own outputs, such as majority voting, that risk reinforcing shared model errors. To overcome these limitations, we introduce Tempo-Zero, a self-improvement framework that closes a loop of executable environments, execution-verified self-play, and environment evolution, where executing a program renders a video with the ground-truth option and interval of every question. A single policy plays both Questioner and Solver, proposing questions and answering them with timestamped evidence lines, and is trained on execution-grounded rewards instead of model consensus. The Solver's performance steers a curriculum over tasks and difficulty levels, and the policy selects rule changes that enrich the event dynamics of later rounds. Despite being trained solely on simple programs, without supervised fine-tuning or external video data which prior methods typically require, Tempo-Zero outperforms the base models and recent self-play baselines on average across twelve real-world video benchmarks at different model scales, with particularly strong gains on temporal grounding tasks. Project page: https://alchemist-jo.github.io/tempo-zero/

cs.CV↗

When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents

Large language model agents increasingly improve by distilling experience into reusable skills, but errors in that experience can persist in learned rules and affect later tasks. Existing evaluations largely examine clean learning or perturbations encountered after skills are frozen, leaving robustness during self-evolution insufficiently understood. We introduce RSE-Bench, to our knowledge the first benchmark for evaluating skill self-evolution under ordinary, non-adversarial noise. It spans four domains and six benchmarks, with controlled perturbations to instructions, environmental evidence, execution records, and outcome--record pairings that preserve the underlying tasks and native scoring rules. The protocol separates noise during learning from input-side noise at evaluation, testing frozen skill stores on held-out tasks. We also introduce \textsc{RSEClaw}, a method-agnostic framework supporting consistent noise injection and process diagnostics of actual exposure and skill updates. Across three methods and two backbones, noisy learning retains only $25.5\%$--$42.1\%$ of the aggregate gain achieved by clean self-evolution, depending on the noise type. Perturbations confined to execution records and outcome--record pairings cause average losses comparable to input-side noise, despite leaving the original executions and evaluations intact. Diagnostics further identify differences in candidate skill text that coexist with small changes in mean held-out performance.

cs.LG↗

ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning

Remote multimodal models offer strong numerical reasoning capabilities over charts and speech, but sending private inputs risks exposing sensitive content. Text-only sanitization cannot directly satisfy fixed media interfaces, while identity anonymization leaves the underlying task content exposed. We introduce ReCast, an agentic plug-in framework that replaces source-specific content while preserving task-relevant relations and the required input modality. ReCast locally converts inputs into a shared textual evidence-query record, jointly rewrites entities and topics with a distilled 4B model, and substitutes values through a locally invertible, role-aware numerical map. A reconstruction agent generates and validates the required media from the protected record. The remote solver returns a program whose protected operands are restored locally before execution. On 4,000 held-out ChartQA and NMSQA examples, ReCast achieves 75.10% accuracy, retaining 92.43% of unprotected remote accuracy, while a model-based audit flags source-content leakage in 7.95% of solver-bound requests. It outperforms all evaluated local baselines, preserving the benefit of remote reasoning while reducing source-content exposure under existing media interfaces.

cs.CR↗

Evaluation Is All You Need for Multi-Modal Autonomous Driving

Multi-modal planning is promising for autonomous driving by representing multiple plausible behaviors in ambiguous and long-tail scenarios. Existing methods mainly focus on improving trajectory multi-modality, enhancing trajectory representations, or reshaping the candidate distribution. Nevertheless, we identify a pronounced generation-evaluation asymmetry in multi-modal planning: despite strong oracle performance, existing planners often fail to reliably select the best available candidate, leaving substantial planning potential unrealized. To address this challenge, we propose iDriveVLA, a multi-modal planning framework that improves the candidate trajectory space while enabling more reliable and context-aware trajectory evaluation. Specifically, iDriveVLA introduces a unified trajectory evaluator comprising a Safety-aware Scorer for quality and risk estimation, together with a VLM-guided Modulator for scene-adaptive criterion weighting. We further develop an oracle-aligned progressive training strategy consisting of candidate imitation pretraining, candidate space refinement, and semantic ranking alignment. On the public NAVSIM v1 leaderboard, iDriveVLA achieves a new state-of-the-art performance of 94.95 PDMS, surpassing the human-expert reference.

cs.RO↗

Schrödinger Bridge Mamba for One-Step Speech Enhancement

We present Schrödinger Bridge Mamba (SBM), a novel model for efficient speech enhancement by integrating the Schrödinger Bridge (SB) training paradigm and the Mamba architecture. Experiments of joint denoising and dereverberation tasks demonstrate SBM outperforms strong generative and discriminative methods on multiple metrics with only one step of inference while achieving a competitive real-time factor for streaming feasibility. Ablation studies reveal that the SB paradigm consistently yields improved performance across diverse architectures over conventional mapping. Furthermore, Mamba exhibits a stronger performance under the SB paradigm compared to Multi-Head Self-Attention (MHSA) and Long Short-Term Memory (LSTM) backbones. These findings highlight the synergy between the Mamba architecture and the SB trajectory-based training, providing a high-quality solution for real-world speech enhancement. Demo page: https://sbmse.github.io

cs.SD↗

RSGPNet: Geometric Prompting for Remote Sensing Open-Vocabulary Semantic Segmentation

Open-vocabulary semantic segmentation (OVSS) enables text-guided segmentation of unseen objects, breaking fixed-class limitations to achieve open-world understanding. However, existing OVSS methods primarily focus on modifying the CLIP attention mechanism, which still suffers from unstable local segmentation for remote sensing (RS) domain. To address these limitations, we propose RSGPNet, a training-free geometric prompting framework for RS OVSS that refines segmentation by leveraging object geometric areas and consistency constraints. Specifically, RSGPNet comprises three core modules: a Text-guided Coarse Mask module (TCM), a Geometric Re-prompting Module (GRP), and a Coarse-to-fine Consistency Verification Mechanism (CVM). TCM utilizes text prompts and the input image to construct initial coarse segmentation masks. GRP then converts these coarse masks into geometric box prompts, feeding them back into the segmentation model to generate refined masks. Finally, CVM employs consistency computation to prevent prompting from reinforcing erroneous regions. They allow the model to improve segmentation accuracy in complex areas, such as category boundaries. Extensive experiments on RS datasets demonstrate that RSGPNet significantly outperforms state-of-the-art methods across both quantitative and qualitative metrics while exhibiting excellent interpretability. The code is released at \href{https://github.com/wangshanwen001/RSGPNet}{https://github.com/wangshanwen001/RSGPNet}.

cs.CV↗

CADDesigner: Conceptual CAD Model Generation with a General-Purpose Agent

Computer-Aided Design (CAD) is widely used for conceptual design and parametric 3D modeling, but typically requires a high level of expertise from designers. To lower the entry barrier and facilitate early-stage CAD modeling, we present CADDesigner, an LLM-powered agent for conceptual CAD design. The agent accepts both textual descriptions and sketches as input, engaging in interactive dialogue with users to refine and clarify design requirements through comprehensive requirement analysis. Built upon a novel Explicit Context Imperative Paradigm (ECIP), the agent generates high-quality CAD modeling code. During the generation process, the agent incorporates iterative visual feedback to improve model quality. Generated design cases can be stored in a structured knowledge base, providing a mechanism for continual knowledge accumulation and future improvement of code generation. Experimental results show that CADDesigner achieves competitive performance and outperforms representative baselines on conceptual CAD model generation tasks.

cs.AI↗

Design and Evaluation of a PMT High-Voltage system for Deepsea Neutrino Telescope

We present the design and characterization of a Cockcroft--Walton (CW) high-voltage (HV) system developed for deep-sea neutrino telescopes. The system provides independently adjustable bias voltages for 31 three-inch photomultiplier tubes (PMTs) housed in a hybrid Digital Optical Module (hDOM). We describe the system architecture, control logic, and laboratory test procedures, and report the combined PMT--base performance in terms of baseline stability, gain uniformity, and timing accuracy under conditions designed to emulate the deep-sea environment. Baseline measurements show low and stable electronic noise. Gain calibrations based on single-photoelectron spectra demonstrate that all PMTs can be tuned to a common nominal gain and remain stable over multi-day operation. Transit-time-spread measurements yield values below 1.8~ns (FWHM), consistent with manufacturer specifications. These results indicate that the CW-based HV system provides the stability and timing precision required for deep-sea multi-PMT optical modules.

hep-ex↗

Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction

Generalized robots must learn from diverse, large-scale human-object interactions (HOI) to operate robustly in the real world. Monocular internet videos offer a nearly limitless and readily available source of data, capturing an unparalleled diversity of human activities, objects, and environments. However, accurately and scalably extracting 4D interaction data from these in-the-wild videos remains a significant and unsolved challenge. To overcome the annotation bottleneck, we introduce an efficient sparse contact annotation paradigm. To scale this process, we develop InterPoint, a multi-modal predictor that drives a human-in-the-loop data engine. Building upon these efficiently acquired annotations, we introduce 4DHOISolver, a novel optimization framework that constrains the ill-posed 4D HOI reconstruction problem, maintaining high spatio-temporal coherence and physical plausibility. Leveraging this framework, we introduce Open4DHOI, a new large-scale 4D HOI dataset featuring a diverse catalog of 135 object types and 133 actions. Furthermore, we demonstrate the effectiveness of our reconstructions by enabling an RL-based agent to imitate the recovered motions. Data and code will be publicly available at https://github.com/wenboran2002/open4dhoi_code.

cs.CV↗

CaTFormer: Causal Temporal Transformer with Dynamic Contextual Fusion for Driving Intention Prediction

Accurate prediction of driving intention is key to enhancing the safety and interactive efficiency of human-machine co-driving systems. It serves as a cornerstone for achieving high-level autonomous driving. However, current approaches remain inadequate for accurately modeling the complex spatiotemporal interdependencies and the unpredictable variability of human driving behavior. To address these challenges, we propose CaTFormer, a causal Temporal Transformer that explicitly models causal interactions between driver behavior and environmental context for robust intention prediction. Specifically, CaTFormer introduces a novel Reciprocal Delayed Fusion (RDF) mechanism for precise temporal alignment of interior and exterior feature streams, a Counterfactual Residual Encoding (CRE) module that systematically eliminates spurious correlations to reveal authentic causal dependencies, and an innovative Feature Synthesis Network (FSN) that adaptively synthesizes these purified representations into coherent temporal representations. Experimental results demonstrate that CaTFormer attains state-of-the-art performance on the Brain4Cars dataset. It effectively captures complex causal temporal dependencies and enhances both the accuracy and transparency of driving intention prediction.

cs.CV↗

Rectify Evaluation Preference: Improving LLMs' Critique on Math Reasoning via Perplexity-aware Reinforcement Learning

To improve Multi-step Mathematical Reasoning (MsMR) of Large Language Models (LLMs), it is crucial to obtain scalable supervision from the corpus by automatically critiquing mistakes in the reasoning process of MsMR and rendering a final verdict of the problem-solution. Most existing methods rely on crafting high-quality supervised fine-tuning demonstrations for critiquing capability enhancement and pay little attention to delving into the underlying reason for the poor critiquing performance of LLMs. In this paper, we orthogonally quantify and investigate the potential reason -- imbalanced evaluation preference, and conduct a statistical preference analysis. Motivated by the analysis of the reason, a novel perplexity-aware reinforcement learning algorithm is proposed to rectify the evaluation preference, elevating the critiquing capability. Specifically, to probe into LLMs' critiquing characteristics, a One-to-many Problem-Solution (OPS) benchmark is meticulously constructed to quantify the behavior difference of LLMs when evaluating the problem solutions generated by itself and others. Then, to investigate the behavior difference in depth, we conduct a statistical preference analysis oriented on perplexity and find an intriguing phenomenon -- ``LLMs incline to judge solutions with lower perplexity as correct'', which is dubbed as \textit{imbalanced evaluation preference}. To rectify this preference, we regard perplexity as the baton in the algorithm of Group Relative Policy Optimization, supporting the LLMs to explore trajectories that judge lower perplexity as wrong and higher perplexity as correct. Extensive experimental results on our built OPS and existing available critic benchmarks demonstrate the validity of our method.

cs.CL↗

GEWDiff: Geometric Enhanced Wavelet-based Diffusion Model for Hyperspectral Image Super-resolution

Improving the quality of hyperspectral images (HSIs), such as through super-resolution, is a crucial research area. However, generative modeling for HSIs presents several challenges. Due to their high spectral dimensionality, HSIs are too memory-intensive for direct input into conventional diffusion models. Furthermore, general generative models lack an understanding of the topological and geometric structures of ground objects in remote sensing imagery. In addition, most diffusion models optimize loss functions at the noise level, leading to a non-intuitive convergence behavior and suboptimal generation quality for complex data. To address these challenges, we propose a Geometric Enhanced Wavelet-based Diffusion Model (GEWDiff), a novel framework for reconstructing hyperspectral images at 4-times super-resolution. A wavelet-based encoder-decoder is introduced that efficiently compresses HSIs into a latent space while preserving spectral-spatial information. To avoid distortion during generation, we incorporate a geometry-enhanced diffusion process that preserves the geometric features. Furthermore, a multi-level loss function was designed to guide the diffusion process, promoting stable convergence and improved reconstruction fidelity. Our model demonstrated state-of-the-art results across multiple dimensions, including fidelity, spectral accuracy, visual realism, and clarity.

cs.CV↗

Beyond Global Emotion: Fine-Grained Emotional Speech Synthesis with Dynamic Word-Level Modulation

Emotional text-to-speech (E-TTS) is central to creating natural and trustworthy human-computer interaction. Existing systems typically rely on sentence-level control through predefined labels, reference audio, or natural language prompts. While effective for global emotion expression, these approaches fail to capture dynamic shifts within a sentence. To address this limitation, we introduce Emo-FiLM, a fine-grained emotion modeling framework for LLM-based TTS. Emo-FiLM aligns frame-level features from emotion2vec to words to obtain word-level emotion annotations, and maps them through a Feature-wise Linear Modulation (FiLM) layer, enabling word-level emotion control by directly modulating text embeddings. To support evaluation, we construct the Fine-grained Emotion Dynamics Dataset (FEDD) with detailed annotations of emotional transitions. Experiments show that Emo-FiLM outperforms existing approaches on both global and fine-grained tasks, demonstrating its effectiveness and generality for expressive speech synthesis.

cs.CL↗

FRAME: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy

Large language models (LLMs) have significantly advanced human language understanding and generation, with pretraining data quality and organization being crucial to their performance. Multi-stage pretraining is a promising approach, but existing methods often lack quantitative criteria for data partitioning and instead rely on intuitive heuristics. In this paper, we propose the novel Four-quadRAnt Multi-stage prEtraining strategy (FRAME), guided by the established principle of organizing the pretraining process into four stages to achieve significant loss reductions four times. This principle is grounded in two key findings: first, training on high Perplexity (PPL) data followed by low PPL data, and second, training on low PPL difference (PD) data followed by high PD data, both causing the loss to drop significantly twice and performance enhancements. By partitioning data into four quadrants and strategically organizing them, FRAME achieves a remarkable 16.8% average improvement over random across MMLU and CMMLU for the 3B model, effectively boosting LLM performance.

cs.CL↗

Enhancing LLMs via High-Knowledge Data Selection

The performance of Large Language Models (LLMs) is intrinsically linked to the quality of its training data. Although several studies have proposed methods for high-quality data selection, they do not consider the importance of knowledge richness in text corpora. In this paper, we propose a novel and gradient-free High-Knowledge Scorer (HKS) to select high-quality data from the dimension of knowledge, to alleviate the problem of knowledge scarcity in the pre-trained corpus. We propose a comprehensive multi-domain knowledge element pool and introduce knowledge density and coverage as metrics to assess the knowledge content of the text. Based on this, we propose a comprehensive knowledge scorer to select data with intensive knowledge, which can also be utilized for domain-specific high-knowledge data selection by restricting knowledge elements to the specific domain. We train models on a high-knowledge bilingual dataset, and experimental results demonstrate that our scorer improves the model's performance in knowledge-intensive and general comprehension tasks, and is effective in enhancing both the generic and domain-specific capabilities of the model.

cs.CL↗

From Temporal to Spatial: Designing Spatialized Interactions with Segmented-audios in Immersive Environments for Active Engagement with Performing Arts Intangible Cultural Heritage

Performance artforms like Peking opera face transmission challenges due to the extensive passive listening required to understand their nuance. To create engaging forms of experiencing auditory Intangible Cultural Heritage (ICH), we designed a spatial interaction-based segmented-audio (SISA) Virtual Reality system that transforms passive ICH experiences into active ones. We undertook: (1) a co-design workshop with seven stakeholders to establish design requirements, (2) prototyping with five participants to validate design elements, and (3) user testing with 16 participants exploring Peking Opera. We designed transformations of temporal music into spatial interactions by cutting sounds into short audio segments, applying t-SNE algorithm to cluster audio segments spatially. Users navigate through these sounds by their similarity in audio property. Analysis revealed two distinct interaction patterns (Progressive and Adaptive), and demonstrated SISA's efficacy in facilitating active auditory ICH engagement. Our work illuminates the design process for enriching traditional performance artform using spatially-tuned forms of listening.

cs.HC↗