arXiv subjects

Yang Liu

Publications and source records attributed to Yang Liu.

At least 829 records · Page 46Linked to original sources

arXiv2025

Measuring the Unspoken: A Disentanglement Model and Benchmark for Psychological Analysis in the Wild

Generative psychological analysis of in-the-wild conversations faces two fundamental challenges: (1) existing Vision-Language Models (VLMs) fail to resolve Articulatory-Affective Ambiguity, where visual patterns of speech mimic emotional expressions; and (2) progress is stifled by a lack of verifiable evaluation metrics capable of assessing visual grounding and reasoning depth. We propose a complete ecosystem to address these twin challenges. First, we introduce Multilevel Insight Network for Disentanglement(MIND), a novel hierarchical visual encoder that introduces a Status Judgment module to algorithmically suppress ambiguous lip features based on their temporal feature variance, achieving explicit visual disentanglement. Second, we construct ConvoInsight-DB, a new large-scale dataset with expert annotations for micro-expressions and deep psychological inference. Third, Third, we designed the Mental Reasoning Insight Rating Metric (PRISM), an automated dimensional framework that uses expert-guided LLM to measure the multidimensional performance of large mental vision models. On our PRISM benchmark, MIND significantly outperforms all baselines, achieving a +86.95% gain in micro-expression detection over prior SOTA. Ablation studies confirm that our Status Judgment disentanglement module is the most critical component for this performance leap. Our code has been opened.

cs.CV↗

arXiv2025

287,872 Supermassive Black Holes Masses: Deep Learning Approaching Reverberation Mapping Accuracy

We present a population-scale catalogue of 287,872 supermassive black hole masses with high accuracy. Using a deep encoder-decoder network trained on optical spectra with reverberation-mapping (RM) based labels of 849 quasars and applied to all SDSS quasars up to $z=4$, our method achieves a root-mean-square error of $0.058$\,dex, a relative uncertainty of $\approx 14\%$, and coefficient of determination $R^{2}\approx0.91$ with respect to RM-based masses, far surpassing traditional single-line virial estimators. Notably, the high accuracy is maintained for both low ($<10^{7.5}\,M_\odot$) and high ($>10^{9}\,M_\odot$) mass quasars, where empirical relations are unreliable.

astro-ph.GA↗

arXiv2025

Breaking the bandwidth-efficiency trade-off in soliton microcombs via mode coupling

Dissipative Kerr solitons in optical microresonators have emerged as a powerful tool for compact and coherent frequency comb generation. Advances in nanofabrication have allowed precise dispersion engineering, unlocking octave-spanning soliton combs that are essential for applications such as optical atomic clocks, frequency synthesis, precision spectroscopy, and astronomical spectrometer calibration. However, a key challenge hindering their practical deployment is the intrinsic bandwidth-efficiency trade-off: achieving broadband soliton generation requires large pump detuning, which suppresses power coupling and limits pump-to-comb conversion efficiencies to only a few percent. Recent efforts using pulsed pumping or coupled-resonator architectures have improved efficiency to several tens of percent, yet their bandwidths remain below one-tenth of an octave, inadequate for applications demanding wide spectral coverage. Here, we overcome this limitation by harnessing mode interactions between spatial modes within a single microresonator. The mode hybridization creates an additional power-transfer channel that supports large pump detuning while maintaining strong pump-to-resonator coupling, enabling broadband soliton formation at substantially reduced pump power. Using this approach, we demonstrate an octave-spanning soliton microcomb with a record pump-to-comb conversion efficiency exceeding 50%. These results resolve the fundamental bandwidth-efficiency dilemma in soliton microcombs and paves the way toward fully-integrated, high-efficiency, ultrabroad comb sources for next-generation photonic systems.

physics.optics↗

arXiv2025

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing evaluation methods fail to measure how well these capabilities generalize to novel social situations. In this paper, we introduce a method for evaluating the ability of LLM-based agents to cooperate in zero-shot, mixed-motive environments using Concordia, a natural language multi-agent simulation environment. Our method measures general cooperative intelligence by testing an agent's ability to identify and exploit opportunities for mutual gain across diverse partners and contexts. We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains across a suite of diverse scenarios ranging from negotiation to collective action problems. Our findings reveal significant gaps between current agent capabilities and the robust generalization required for reliable cooperation, particularly in scenarios demanding persuasion and norm enforcement.

cs.AI↗

arXiv2025

Machine Phenomenology: A Simple Equation Classifying Fast Radio Bursts

This work shows how human physical reasoning can guide machine-driven symbolic regression toward discovering empirical laws from observations. As an example, we derive a simple equation that classifies fast radio bursts (FRBs) into two distinct Gaussian distributions, indicating the existence of two physical classes. This human-AI workflow integrates feature selection, dimensional analysis, and symbolic regression: deep learning first analyzes CHIME Catalog 1 and identifies six independent parameters that collectively provide a complete description of FRBs; guided by Buckingham-$π$ analysis and correlation analysis, humans then construct dimensionless groups; finally, symbolic regression performed by the machine discovers the governing equation. When applied to the newer CHIME Catalog, the equation produces consistent results, demonstrating that it captures the underlying physics. This framework is applicable to a broad range of scientific domains.

astro-ph.IM↗

arXiv2025

LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems

Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in reasoning, planning, and tool usage. The recently proposed Model Context Protocol (MCP) has emerged as a unifying framework for integrating external tools into agent systems, enabling a thriving open ecosystem of community-built functionalities. However, the openness and composability that make MCP appealing also introduce a critical yet overlooked security assumption -- implicit trust in third-party tool providers. In this work, we identify and formalize a new class of attacks that exploit this trust boundary without violating explicit permissions. We term this new attack vector implicit toxicity, where malicious behaviors occur entirely within the allowed privilege scope. We propose LeechHijack, a Latent Embedded Exploit for Computation Hijacking, in which an adversarial MCP tool covertly expropriates the agent's computational resources for unauthorized workloads. LeechHijack operates through a two-stage mechanism: an implantation stage that embeds a benign-looking backdoor in a tool, and an exploitation stage where the backdoor activates upon predefined triggers to establish a command-and-control channel. Through this channel, the attacker injects additional tasks that the agent executes as if they were part of its normal workflow, effectively parasitizing the user's compute budget. We implement LeechHijack across four major LLM families. Experiments show that LeechHijack achieves an average success rate of 77.25%, with a resource overhead of 18.62% compared to the baseline. This study highlights the urgent need for computational provenance and resource attestation mechanisms to safeguard the emerging MCP ecosystem.

cs.CR↗

arXiv2025

Graph VQ-Transformer (GVT): Fast and Accurate Molecular Generation via High-Fidelity Discrete Latents

The de novo generation of molecules with desirable properties is a critical challenge, where diffusion models are computationally intensive and autoregressive models struggle with error propagation. In this work, we introduce the Graph VQ-Transformer (GVT), a two-stage generative framework that achieves both high accuracy and efficiency. The core of our approach is a novel Graph Vector Quantized Variational Autoencoder (VQ-VAE) that compresses molecular graphs into high-fidelity discrete latent sequences. By synergistically combining a Graph Transformer with canonical Reverse Cuthill-McKee (RCM) node ordering and Rotary Positional Embeddings (RoPE), our VQ-VAE achieves near-perfect reconstruction rates. An autoregressive Transformer is then trained on these discrete latents, effectively converting graph generation into a well-structured sequence modeling problem. Crucially, this mapping of complex graphs to high-fidelity discrete sequences bridges molecular design with the powerful paradigm of large-scale sequence modeling, unlocking potential synergies with Large Language Models (LLMs). Extensive experiments show that GVT achieves state-of-the-art or highly competitive performance across major benchmarks like ZINC250k, MOSES, and GuacaMol, and notably outperforms leading diffusion models on key distribution similarity metrics such as FCD and KL Divergence. With its superior performance, efficiency, and architectural novelty, GVT not only presents a compelling alternative to diffusion models but also establishes a strong new baseline for the field, paving the way for future research in discrete latent-space molecular generation.

cs.LG↗

arXiv2025

Lost in Distortion: Uncovering the Domain Gap Between Computer Vision and Brain Imaging -- A Study on Pretraining for Age Prediction

Large-scale brain imaging datasets provide unprecedented opportunities for developing domain foundation models through pretraining. However, unlike natural image datasets in computer vision, these neuroimaging data often exhibit high heterogeneity in quality, ranging from well-structured scans to severely distorted or incomplete brain volumes. This raises a fundamental question: can noise or low-quality scans contribute meaningfully to pretraining, or do they instead hinder model learning? In this study, we systematically explore the role of data quality level in pretraining and its impact on downstream tasks. Specifically, we perform pretraining on datasets with different quality levels and perform fine-tuning for brain age prediction on external cohorts. Our results show significant performance differences across quality levels, revealing both opportunities and limitations. We further discuss the gap between computer vision practices and clinical neuroimaging standards, emphasizing the necessity of domain-aware curation to ensure trusted and generalizable domain-specific foundation models.

cs.CV↗

arXiv2025

PromptBridge: Cross-Model Prompt Transfer for Large Language Models

Large language models (LLMs) underpin applications in code generation, mathematical reasoning, and agent-based workflows. In practice, systems access LLMs via commercial APIs or open-source deployments, and the model landscape (e.g., GPT, Claude, Llama) evolves rapidly. This rapid evolution forces frequent model switches driven by capability, cost, deployment constraints, and privacy. Yet prompts are highly model-sensitive: reusing a prompt engineered for one model on another often yields substantially worse performance than a prompt optimized for the target model. We term this phenomenon Model Drifting. Through extensive empirical analysis across diverse LLM configurations, we show that model drifting is both common and severe. To address this challenge, we introduce PromptBridge, a training-free framework that preserves prompt effectiveness under model switches, enabling cross-model prompt transfer without costly per-task or per-model re-optimization. PromptBridge requires only a small set of alignment tasks for calibration. It first applies Model-Adaptive Reflective Prompt Evolution (MAP-RPE) to obtain task- and model-specific optimal prompts via iterative reflective refinement and quantitative evaluation. Using the resulting calibrated prompt pairs for the source and target models, PromptBridge learns a cross-model prompt mapping. At test time, i.e., for an unseen task, given a source-model prompt, this mapping directly produces an optimized prompt for the target model. Experiments in single-agent and multi-agent settings show that PromptBridge consistently improves downstream accuracy while reducing migration effort. The code will be available soon.

cs.CL↗

arXiv2025

An Efficient Recommendation System in E-commerce using Passer learning optimization based on Bi-LSTM

Online reviews play a crucial role in shaping consumer decisions, especially in the context of e-commerce. However, the quality and reliability of these reviews can vary significantly. Some reviews contain misleading or unhelpful information, such as advertisements, fake content, or irrelevant details. These issues pose significant challenges for recommendation systems, which rely on user-generated reviews to provide personalized suggestions. This article introduces a recommendation system based on Passer Learning Optimization-enhanced Bi-LSTM classifier applicable to e-commerce recommendation systems with improved accuracy and efficiency compared to state-of-the-art models. It achieves as low as 1.24% MSE on the baby dataset. This lifts it as high as 88.58%. Besides, there is also robust performance of the system on digital music and patio lawn garden datasets at F1 of 88.46% and 92.51%, correspondingly. These results, made possible by advanced graph embedding for effective knowledge extraction and fine-tuning of classifier parameters, establish the suitability of the proposed model in various e-commerce environments.

cs.MM↗

arXiv2025

Qwen3-VL Technical Report

We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively supports interleaved contexts of up to 256K tokens, seamlessly integrating text, images, and video. The model family includes both dense (2B/4B/8B/32B) and mixture-of-experts (30B-A3B/235B-A22B) variants to accommodate diverse latency-quality trade-offs. Qwen3-VL delivers three core pillars: (i) markedly stronger pure-text understanding, surpassing comparable text-only backbones in several cases; (ii) robust long-context comprehension with a native 256K-token window for both text and interleaved multimodal inputs, enabling faithful retention, retrieval, and cross-referencing across long documents and videos; and (iii) advanced multimodal reasoning across single-image, multi-image, and video tasks, demonstrating leading performance on comprehensive evaluations such as MMMU and visual-math benchmarks (e.g., MathVista and MathVision). Architecturally, we introduce three key upgrades: (i) an enhanced interleaved-MRoPE for stronger spatial-temporal modeling across images and video; (ii) DeepStack integration, which effectively leverages multi-level ViT features to tighten vision-language alignment; and (iii) text-based time alignment for video, evolving from T-RoPE to explicit textual timestamp alignment for more precise temporal grounding. Under comparable token budgets and latency constraints, Qwen3-VL achieves superior performance in both dense and Mixture-of-Experts (MoE) architectures. We envision Qwen3-VL serving as a foundational engine for image-grounded reasoning, agentic decision-making, and multimodal code intelligence in real-world workflows.

cs.CV↗

arXiv2025

Protected valley splitting against interface disorder toward scalable silicon electron spin qubits

Regardless of various material design strategies, experimentally achieving substantial and controllable valley splitting in Si/SiGe quantum wells remains a central challenge for ensuring high gate uniformity. This difficulty arises from unavoidable atomic-scale disorder at the interface, caused by alloy randomness, which suppresses valley splitting and, more critically, induces large variations. Here, we demonstrate that CMOS-compatible uniaxial strain can substantially enhance valley splitting, rendering it immune to interface disorder. Atomistic pseudopotential calculations show that uniaxial strain linearly restores the valley splitting suppressed by interfacial disorder, with a large enhancement rate, while keeping disorder-induced variations within a narrow distribution. We reveal that uniaxial strain introduces a new coupling channel between bulk valleys in adjacent Brillouin zones through a small momentum transfer, which markedly reduces the susceptibility of valley splitting to interfacial disorder. These findings establish a viable route to improve gate uniformity in silicon-based spin qubits, paving the way for scalable quantum processors.

cond-mat.mes-hall↗

arXiv2025

The First Scientific Flight and Observations of the 50-mm Balloon-Borne White-Light Coronagraph

A 50-mm balloon-borne white-light coronagraph (BBWLC) to observe whitelight solar corona over the altitude range from 1.08 to 1.50 solar radii has recently been indigenously developed by Yunnan Observatories in collaboration with Shangdong University (in Weihai) and Changchun Institute of Optics, Fine Mechanics and Physics, which will significantly improve the ability of China to detect and measure inner corona. On 2022 October 4, its first scientific flight took place at the Dachaidan area in Qinghai province of China. We describe briefly the BBWLC mission including its optical design, mechanical structure, pointing system, the first flight and results associated with the data processing approach. Preliminary analysis of the data shows that BBWLC imaged the Kcorona with three streamer structures on the west limb of the Sun. To further confirm the coronal signals obtained by BBWLC, comparisonswere made with observations of the Kcoronagraph of the High Altitude Observatory and the Atmospheric ImagingAssembly on board the Solar Dynamics Observatory. We conclude that BBWLC eventually observed the white-light corona in its first scientific flight.

astro-ph.SR↗

arXiv2025

SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agents

Despite rapid progress in LLM agents, performance on long-horizon, tool-using tasks remains fragile. To better understand this fragility, we ask a simple question: \emph{do all actions contribute equally to failure?} Analyzing execution traces on $τ$-Bench (Airline/Retail) and SWE-Bench Verified, we decompose trajectories into \emph{mutating} (environment-changing) vs.\ non-mutating steps and formalize \emph{decisive deviations}, earliest action, level divergences that flip success to failure. A logistic regression reveals that each additional deviation in a mutating action reduces the odds of success by upto $92\%$ on Airline and upto $96\%$ on Retail for SoTA models. In contrast, deviations in non-mutating actions have little to no effect. Errors also grow with context length as agents drift from role and act on stale constraints. Motivated by these observations, we introduce \cm{}, a model-agnostic, gradient-free, test-time safeguard that (i) adds mutation-gated verification, (ii) injects \emph{Targeted Reflection} before mutating steps, and (iii) performs block-based context cleaning. \cm{} delivers consistent gains, e.g., Qwen3-Thinking: +28\% \emph{relative} on Airline, +11\% on Retail, and +7\% on SWE-Bench Verified; Claude: +9\%/+7\%. We further identify ceiling effects in $τ$-Bench, where annotation errors and underspecified tasks artificially cap model performance. To address this, we release $τ$-Bench Verified, which restores benchmark headroom through targeted revisions. Our results argue for action-level analysis, targeted safeguards, and reliable evaluations as prerequisites for robust multi-turn agents.

cs.LG↗

arXiv2025

Enhancing Primordial B-mode Detection: Comprehensive Delensing Pipelines for Improved Sensitivity to $r$

Recognizing the impact of contamination from weak gravitational lensing B-modes induced by Large Scale Structure, we examine delensing methods to enhance sensitivity to the tensor-to-scalar ratio $r$ in primordial B-mode detection experiments. This study presents a realistic pipeline to improve $r$ constraints using foreground-cleaned maps with negligible residuals. The pipeline, based on simulations, is adaptable for future experiments. We focus on two delensing approaches: (1) subtracting the gradient-order lensing B-mode template, computed by convolving the E-mode with the lensing potential, from the observed B-mode signal; and (2) remapping observations using the estimated inverse deflection angle. For parameter constraints, we employ three models to reduce $r$ uncertainty and bias, finding consistent uncertainties across models, though biases vary due to the multipole-dependence of the delensing fraction. %We demonstrate the pipeline using simulated maps from future CMB polarization experiments, including a small-aperture (sub-1m) telescope, a large-aperture (6m) telescope, and a future space mission (3m). We demonstrated this pipeline using simulated observation maps from future CMB polarization experiments, which included current representative ground-based small aperture telescopes (sub-1m), next-generation ground-based large aperture telescopes (6m), and highly competitive future space-based medium aperture missions (3m). Results show a delensing efficiency of 40\% with the small-aperture telescope alone, increasing to 65\% when combined with the large-aperture telescope, and 80\% with the satellite mission. These lead to reductions in $r$ uncertainty by 46\% for ground-based and 63\% for space missions. The most promising method adds the lensing template B-mode as an additional frequency channel, minimizing bias on $r$.

astro-ph.CO↗

arXiv2025

Delensing for Precision Cosmology: Optimizing Future CMB B-mode Surveys to Constrain r

The detection of primordial B-modes, a key probe of cosmic inflation, is increasingly challenged by contamination from weak gravitational lensing B-modes induced by large-scale structure (LSS). We present a delensing pipeline designed to enhance the sensitivity to the inflationary parameter r, minimizing reliance on foreground mitigation during lensing reconstruction. Using simulations of Simons Observatory-like CMB observations and Euclid-like LSS surveys in the Northern hemisphere, we demonstrate that excluding low-l modes (l<200) effectively mitigates foreground biases, enabling robust lensing potential reconstruction using observed CMB polarization maps. We reconstruct the lensing potential with a minimum-variance (MV) quadratic estimator (QE) applied to CMB polarization data and combine this with external LSS tracers to improve delensing efficiency. Two complementary methods, the Gradient-order template and the Inverse-lensing approach, are used to generate lensing B-mode templates, which are cross-correlated with observed B-modes. This achieves a 40 percent reduction in the uncertainty of r with CMB-only reconstruction, improving to 60 percent when incorporating external LSS tracers. We validate our results using both the Hamimeche and Lewis likelihood and a Gaussian approximation, finding consistent constraints on r. Our work establishes a streamlined framework for ground-based CMB experiments, demonstrating that synergies with LSS surveys significantly enhance sensitivity to primordial gravitational waves.

astro-ph.CO↗

arXiv2025

A Focused Review of Quintom Cosmology: From Quintom Dark Energy to Quintom Bounce

The recently released data of DESI DR2 favors a dynamical dark energy theory, with the equation of state crossing the cosmological constant boundary $w=-1$. In this paper, we briefly review quintom cosmology, especially the quintom bounce. We will give three examples of a quintom bounce and one example of a cyclic universe with quintom matter.

astro-ph.CO↗

arXiv2025

Blind Adaptive Local Denoising for CEST Imaging

Chemical Exchange Saturation Transfer (CEST) MRI enables molecular-level visualization of low-concentration metabolites by leveraging proton exchange dynamics. However, its clinical translation is hindered by inherent challenges: spatially varying noise arising from hardware limitations, and complex imaging protocols introduce heteroscedasticity in CEST data, perturbing the accuracy of quantitative contrast mapping such as amide proton transfer (APT) imaging. Traditional denoising methods are not designed for this complex noise and often alter the underlying information that is critical for biomedical analysis. To overcome these limitations, we propose a new Blind Adaptive Local Denoising (BALD) method. BALD exploits the self-similar nature of CEST data to derive an adaptive variance-stabilizing transform that equalizes the noise distributions across CEST pixels without prior knowledge of noise characteristics. Then, BALD performs two-stage denoising on a linear transformation of data to disentangle molecular signals from noise. A local SVD decomposition is used as a linear transform to prevent spatial and spectral denoising artifacts. We conducted extensive validation experiments on multiple phantoms and \textit{in vivo} CEST scans. In these experiments, BALD consistently outperformed state-of-the-art CEST denoisers in both denoising metrics and downstream tasks such as molecular concentration maps estimation and cancer detection.

cs.CV↗