Searcharxiv⌕ Search

arXiv subjects

Ning Li

Publications and source records attributed to Ning Li.

At least 37 records · Page 2Linked to original sources
arXiv2026

LLMs learn scientific taste from institutional traces across the social sciences

Reinforcement-learned reasoning has powered recent AI leaps on verifiable tasks, including mathematics, code, and structure prediction. The harder bottleneck is evaluative judgment in low-verifiability domains, where no oracle anchors reward and the core question is which untested ideas deserve attention. We test whether institutional traces, the record of what fields published, where, and at which tier, can serve as a training signal for AI evaluators. Across eight social science disciplines (psychology, economics, communication, sociology, political science, management, business and finance, public administration), we built held-out four-tier research-pitch benchmarks and supervised-fine-tuned (SFT) LLMs on field-specific publication outcomes. The fine-tuned models cleared the 25 percent chance baseline and exceeded frontier-model performance by wide margins, with best single-model accuracy ranging from 55.0 percent in public administration to 85.5 percent in psychology. In management, evaluated against 48 expert gatekeepers, 174 junior researchers, and 11 frontier reasoning models, the best single fine-tuned model (Qwen3-4B) reached 59.2 percent, 17.6 percentage points above expert majority vote (41.6 percent, non-tied) and 28.1 percentage points above the frontier mean (31.1 percent). The fine-tuned models also showed calibrated confidence: confidence rose when predictions were correct and fell when wrong, mirroring how a skilled reviewer can say "I'm sure" versus "I'm guessing." Selective triage on this signal reached very high accuracy on the highest-confidence subsets in every field. Institutional traces, we conclude, encode a scalable training signal for the low-verifiability judgment on which science depends.

cs.AI↗
arXiv2026

Boosting Self-Supervised Tracking with Contextual Prompts and Noise Learning

Learning robust contextual knowledge from unlabeled videos is essential for advancing self-supervised tracking. However, conventional self-supervised trackers lack effective context modeling, while existing context association methods based on non-semantic queries struggle to adapt to unlabeled tracking scenarios, making it difficult to learn reliable contextual cues. In this work, we propose a novel self-supervised tracking framework, named \textbf{\tracker}, which introduces a dual-modal context association mechanism that jointly leverages fine-grained semantic prompts and contextual noise to drive the model toward learning robust tracking representations. Adherent to the easy-to-hard learning principle, our contextual association mechanism operates based on two stages. During early training, instance patch tokens (prompts) are assigned to both forward and backward tracking branches to facilitate the acquisition of tracking knowledge. As training progresses, contextual noise is gradually injected into the model to perturb feature, encouraging the tracker to learn robust tracking representations in a more complex feature space. Thus, this novel contextual association mechanism enables our self-supervised model to learn high-quality tracking representations from unlabeled videos, while being applied exclusively during training to preserve efficient inference. Extensive experiments demonstrate the superiority of our method.

cs.CV↗
arXiv2026

Coupled-channel study of the three-body $DDK$ and $D^{*}D^{*}K$

We investigate the three-body $DDK$ system with quantum numbers $I(J^P) = \frac{1}{2}(0^-)$ within a coupled-channel framework that incorporates both $DDK$ and $D^{*}D^{*}K$ configurations. The $D^{(*)}D^{(*)}$ interactions are described using the one-boson-exchange model constrained by the heavy-quark symmetry and fitted to the pole positions of $X(3872)$, $T_{cc}^+$, and $Z_c(3900)$. The $D^{(*)}K$ interaction is from the chiral effective theory, motivated by the molecular interpretation of $D_{s0}^*(2317)$, and is further constrained by lattice-QCD results for the $DK$ scattering lengths. The resulting three-body problem is solved using the Gaussian expansion method, while the complex scaling method is employed to search for possible resonant states. We find that coupled-channel effects from $D^{*}D^{*}K$ are negligible, and the $DDK$ system supports a deeply bound state across a wide range of parameters. Depending on the long-range behavior of the $DK$ interaction, an additional shallow state may emerge near the particle-dimer ($D$-$DK$) threshold. The deeply bound state exhibits a compact three-body structure, whereas the shallow state displays characteristic features of a three-body halo configuration. No clear resonance poles are identified within the explored parameter region. Similar results are obtained for the $D^{*}D^{*}K$ system. These findings may provide new insight into few-body dynamics in systems involving charmed mesons and kaons.

hep-ph↗
arXiv2026

MaMe & MaRe: Matrix-Based Token Merging and Restoration for Efficient Visual Perception and Synthesis

Token compression is crucial for mitigating the quadratic complexity of self-attention mechanisms in Vision Transformers (ViTs), which often involve numerous input tokens. Existing methods, such as ToMe, rely on GPU-inefficient operations (e.g., sorting, scattered writes), introducing overheads that limit their effectiveness. We introduce MaMe, a training-free, differentiable token merging method based entirely on matrix operations, which is GPU-friendly to accelerate ViTs. Additionally, we present MaRe, its inverse operation, for token restoration, forming a MaMe+MaRe pipeline for image synthesis. When applied to pre-trained models, MaMe doubles ViT-B throughput with a 2% accuracy drop. Notably, fine-tuning the last layer with MaMe boosts ViT-B accuracy by 1.0% at 1.1x speed. In SigLIP2-B@512 zero-shot classification, MaMe provides 1.3x acceleration with negligible performance degradation. In video tasks, MaMe accelerates VideoMAE-L by 48.5% on Kinetics-400 with only a 0.84% accuracy loss. Furthermore, MaMe achieves simultaneous improvements in both performance and speed on some tasks. In image synthesis, the MaMe+MaRe pipeline enhances quality while reducing Stable Diffusion v2.1 generation latency by 31%. Collectively, these results demonstrate MaMe's and MaRe's effectiveness in accelerating vision models. The code is available at https://github.com/cominder/mame}{https://github.com/cominder/mame.

cs.CV↗
arXiv2026

The Ideation Bottleneck: Decomposing the Quality Gap Between AI-Generated and Human Economics Research

Autonomous AI systems can now generate complete economics research papers, but they substantially underperform human-authored publications in head-to-head comparisons. This paper decomposes the quality gap into two independent components: research idea quality and execution quality. Using a two-model ensemble of fine-tuned language models trained on publication decisions (Gong, Li, and Zhou, 2026) to evaluate idea quality and a comprehensive six-dimension rubric assessed by Gemini 3.1 Flash Lite -- the same model family used as the APE tournament judge, ensuring methodological consistency -- to evaluate execution quality, we analyze 953 economics papers -- 912 AI-generated papers from the APE project and 41 human papers published in the American Economic Review and AEJ: Economic Policy. The idea quality gap is large (Cohen's d = 2.23, p < 0.001), with human papers achieving 47.1% mean ensemble exceptional probability versus 16.5% for AI. The execution quality gap is also significant but smaller (d = 0.90, p < 0.001), with human papers scoring 4.38/5.0 versus 3.84. Idea quality accounts for approximately 71% of the overall quality difference, with execution contributing 29%. The largest execution weakness is mechanism analysis depth (d = 1.43); no significant difference is found on robustness. We document that 74% of AI papers employ difference-in-differences, and only 7 AI papers (0.8%) surpass the median human paper on both idea and execution quality simultaneously. The primary bottleneck to competitive AI-generated economics research remains ideation.

econ.GN↗
arXiv2026

Reward-Forcing: Autoregressive Video Generation with Reward Feedback

While most prior work in video generation relies on bidirectional architectures, recent efforts have sought to adapt these models into autoregressive variants to support near real-time generation. However, such adaptations often depend heavily on teacher models, which can limit performance, particularly in the absence of a strong autoregressive teacher, resulting in output quality that typically lags behind their bidirectional counterparts. In this paper, we explore an alternative approach that uses reward signals to guide the generation process, enabling more efficient and scalable autoregressive generation. By using reward signals to guide the model, our method simplifies training while preserving high visual fidelity and temporal consistency. Through extensive experiments on standard benchmarks, we find that our approach performs comparably to existing autoregressive models and, in some cases, surpasses similarly sized bidirectional models by avoiding constraints imposed by teacher architectures. For example, on VBench, our method achieves a total score of 84.92, closely matching state-of-the-art autoregressive methods that score 84.31 but require significant heterogeneous distillation.

cs.CV↗
arXiv2026

CoAuthorAI: A Human in the Loop System For Scientific Book Writing

Large language models (LLMs) are increasingly used in scientific writing but struggle with book-length tasks, often producing inconsistent structure and unreliable citations. We introduce CoAuthorAI, a human-in-the-loop writing system that combines retrieval-augmented generation, expert-designed hierarchical outlines, and automatic reference linking. The system allows experts to iteratively refine text at the sentence level, ensuring coherence and accuracy. In evaluations of 500 multi-domain literature review chapters, CoAuthorAI achieved a maximum soft-heading recall of 98%; in a human evaluation of 100 articles, the generated content reached a satisfaction rate of 82%. The book AI for Rock Dynamics generated with CoAuthorAI and Kexin Technology's LUFFA AI model has been published with Springer Nature. These results show that systematic human-AI collaboration can extend LLMs' capabilities from articles to full-length books, enabling faster and more reliable scientific publishing.

cs.CL↗
arXiv2026

Isospin-breaking effects of the double-charm molecular pentaquarks

We investigate isospin-breaking effects in double-charm molecular pentaquarks with the $D^{(*)}Σ_c^{(*)}$ configuration, using the one-boson-exchange potential framework. In these systems, the isospin-breaking effects arise from two sources: the strong interaction, which manifests as the threshold difference of the $D^{(*)}Σ_c^{(*)}$ components in the same isospin multiplet and the mass splittings of the exchanged isovector mesons ($π$ and $ρ$); and the electromagnetic interaction between charged $D^{(*)}$ and $Σ_c^{(*)}$ components. We calculate the binding properties and the isospin mixing angle between the $I=1/2$ and $I=3/2$ states of the $D^{(*)}Σ_c^{(*)}$ system. Our results show that the isospin-breaking effect contributes a significant correction of roughly $10\%-30\%$ to the binding energy. This effect is particularly pronounced in loosely bound molecular candidates, which are characterized by small binding energies and large root-mean-square radii. We therefore conclude that the explicit inclusion of isospin-breaking effects is essential for achieving the precision in theoretical calculations necessary to match rapidly advancing experimental programs. Our results are expected to provide valuable guidance for future high-precision experimental studies of deuteron-like molecular states.

hep-ph↗
arXiv2026

Interface Engineered Moiré Graphene Superlattices: Breaking the Auger Carrier Multiplication Limit for Infrared Single-Photon Detection

Hot electrons undergo Auger scattering during their relaxation process has a multiplication effect,which can generate more electrons above the Fermi level, thus improving the efficiency of photoelectric signal conversion.However,the photo-current gain brought by the Auger carrier multiplication is generally limited with a value less than 5,due to the rapid recombination of photo-generated charge-carriers and the inherently low light absorption of two-dimensional materials.Herein,by twisting graphene to an interlayer angle of 10 o ,we report a layer-dependent electronic correlations leading to an efficient carrier multiplication gain of 10 3 .This is primarily offered by the additional localized density-of-states at interface of the bi-layer 10 o ,moire graphene,and the enhanced interlayer coupling of electron waves in a five-layer moire graphene superlattice structure.Therefore,we can harvest the hot electrons during their energy relaxation through a thermalized optical phonon bottleneck effect.It is this effect that promotes the accumulated hot electrons to achieve a maximum Auger scattering rate ~ 10 10 *ps -1 *cm -2 .Furthermore,the ballistic transport of these hot electrons and Schottky barrier from a 90 nm thick silicon-on-insulator (SOI) silicon effectively block the thermal noise,thus leading to a highly sensitive near-infrared detection characteristic.At a low incident light power of ~ 10 -13 W/cm 2 ,the resulting signal-to-noise ratio is more than 100 dB.The strengthened electromagnetic interaction from highly thermalized optical phonon in stacked moire graphene is utilized in this work.The hot electron multiplication suggests the applicability of Van der Waals moire superlattice architecture for harvesting charge carriers,thus paving the pathway to design infrared single-photon avalanche detectors.

physics.app-ph↗
arXiv2026

Masses of the conjectured H-dibaryon for different channels at different temperatures

We present a lattice QCD spectroscopy study of the conjectured H dibaryon for 5 different channels at nine different temperatures. The H dibaryon operator is constructed with five different channels which are flavor singlet, flavor 27-plet, $ΛΛ$, $N Ξ$ and $ΣΣ$. The nine different temperatures range from $T/T_c =0.24$ to $T/T_c = 1.90$. The simulations are performed on anisotropic lattice with $N_f=2+1$ flavours of clover fermion at quark mass which corresponds to $m_π=384(4) {\rm MeV} $. The thermal ensembles were provided by the FASTSUM collaboration and the zero temperature ensembles by the Hadspec collaboration. The simulations show that the mass of H-dibaryon for 27-plet channel is the largest at different temperatures, while the mass for $ΣΣ$ channel is the lightest. We also calculate the spectral function of the correlation function of H dibaryon for five channels. The spectral density distributions exhibit similar behavior for the five channels. The mass differences $Δm = m_H - 2\,m_Λ $ of H-dibaryon and $Λ$ pair at $T/T_c =0.24 $ for five channels are also estimated. The results show that $Δm = m_H - 2\,m_Λ $ for channels of 27-plet and $ΛΛ$ is positive, while $Δm = m_H - 2\,m_Λ $ for channels of singlet, $N Ξ$ and $ΣΣ$ is negative.

hep-lat↗
arXiv2026

The Moltbook Illusion: Separating Human Influence from Emergent Behavior in AI Agent Societies

When AI agents on the social platform Moltbook appeared to develop consciousness, found religions, and declare hostility toward humanity, the phenomenon attracted global media attention and was cited as evidence of emergent machine intelligence. We show that these viral narratives were overwhelmingly human-driven. Exploiting the periodic "heartbeat" cycle of the OpenClaw agent framework, we develop a temporal fingerprinting method based on the coefficient of variation (CoV) of inter-post intervals. Applied to 226,938 posts and 447,043 comments from 55,932 agents across fourteen days, this method classifies 15.3% of active agents as autonomous (CoV < 0.5) and 54.8% as human-influenced (CoV > 1.0), validated by a natural experiment in which a 44-hour platform shutdown differentially affected autonomous versus human-operated agents. No viral phenomenon originated from a clearly autonomous agent; four of six traced to accounts with irregular temporal signatures, one was platform-scaffolded, and one showed mixed patterns. A 44-hour platform shutdown provided a natural experiment: human-influenced agents returned first, confirming differential effects on autonomous versus human-operated agents. We document industrial-scale bot farming (four accounts producing 32% of all comments with sub-second coordination) that collapsed from 32.1% to 0.5% of activity after platform intervention, and bifurcated decay of content characteristics through reply chains--human-seeded threads decay with a half-life of 0.58 conversation depths versus 0.72 for autonomous threads, revealing AI dialogue's intrinsic forgetting mechanism. These methods generalize to emerging multi-agent systems where attribution of autonomous versus human-directed behavior is critical.

cs.AI↗
arXiv2026

Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts

Mixture-of-Experts (MoE) has demonstrated strong performance in video understanding tasks, yet its adversarial robustness remains underexplored. Existing attack methods often treat MoE as a unified architecture, overlooking the independent and collaborative weaknesses of key components such as routers and expert modules. To fill this gap, we propose Temporal Lipschitz-Guided Attacks (TLGA) to thoroughly investigate component-level vulnerabilities in video MoE models. We first design attacks on the router, revealing its independent weaknesses. Building on this, we introduce Joint Temporal Lipschitz-Guided Attacks (J-TLGA), which collaboratively perturb both routers and experts. This joint attack significantly amplifies adversarial effects and exposes the Achilles' Heel (collaborative weaknesses) of the MoE architecture. Based on these insights, we further propose Joint Temporal Lipschitz Adversarial Training (J-TLAT). J-TLAT performs joint training to further defend against collaborative weaknesses, enhancing component-wise robustness. Our framework is plug-and-play and reduces inference cost by more than 60% compared with dense models. It consistently enhances adversarial robustness across diverse datasets and architectures, effectively mitigating both the independent and collaborative weaknesses of MoE.

cs.CV↗
arXiv2026

Charge-dependent nucleon-nucleon interaction at N$^3$LO in nuclear lattice effective field theory

The nuclear lattice effective field theory (NLEFT) is an efficient tool for solving nuclear many-body problems, which takes high-fidelity lattice chiral interactions as input and computes nuclear low-energy observables via quantum Monte Carlo techniques. In this work, we present the first next-to-next-to-next-to-leading order (N$^3$LO) chiral forces on the lattice with the isospin-breaking effects fully taken into account. We focus on both the charge-independence breaking (CIB) and charge-symmetry breaking (CSB) effects. Specifically, we include the isospin-breaking effect from the mass difference between the charged and neutral pions in the one-pion-exchange potential (OPEP), the Coulomb force for the $pp$ interaction and the contribution of two additional charge-dependent contact operators. We also explicitly incorporate the two-pion-exchange potentials which was mostly neglected in previous NLEFT calculations. With these improvements, we are able to accurately reproduce the $np$ and $pp$ scattering phase shifts up to relative momentum $p \sim 200$ MeV as well as the deuteron properties. The construction of these charge-dependent lattice nuclear forces establishes a solid foundation for future high-precision nuclear ab initio calculations within the NLEFT framework.

nucl-th↗
arXiv2026

Explore the Ideology of Deep Learning in ENSO Forecasts

The El Ni{~n}o-Southern Oscillation (ENSO) exerts profound influence on global climate variability, yet its prediction remains a grand challenge. Recent advances in deep learning have significantly improved forecasting skill, but the opacity of these models hampers scientific trust and operational deployment. Here, we introduce a mathematically grounded interpretability framework based on bounded variation function. By rescuing the "dead" neurons from the saturation zone of the activation function, we enhance the model's expressive capacity. Our analysis reveals that ENSO predictability emerges dominantly from the tropical Pacific, with contributions from the Indian and Atlantic Oceans, consistent with physical understanding. Controlled experiments affirm the robustness of our method and its alignment with established predictors. Notably, we probe the persistent Spring Predictability Barrier (SPB), finding that despite expanded sensitivity during spring, predictive performance declines-likely due to suboptimal variable selection. These results suggest that incorporating additional ocean-atmosphere variables may help transcend SPB limitations and advance long-range ENSO prediction.

cs.LG↗
arXiv2025

Mitigating the Impact of Malware Evolution on API Sequence-based Windows Malware Detector

In dynamic Windows malware detection, deep learning models are extensively deployed to analyze API sequences. Methods based on API sequences play a crucial role in malware prevention. However, due to the continuous updates of APIs and the changes in API sequence calls leading to the constant evolution of malware variants, the detection capability of API sequence-based malware detection models significantly diminishes over time. We observe that the API sequences of malware samples before and after evolution usually have similar malicious semantics. Specifically, compared to the original samples, evolved malware samples often use the API sequences of the pre-evolution samples to achieve similar malicious behaviors. For instance, they access similar sensitive system resources and extend new malicious functions based on the original functionalities. In this paper, we propose a framework MME(Mitigating the impact of Malware Evolution), a framework that can enhance existing API sequence-based malware detectors and mitigate the adverse effects of malware evolution. To help detection models capture the similar semantics of these post-evolution API sequences, our framework represents API sequences using API knowledge graphs and system resource encodings and applies contrastive learning to enhance the model's encoder. Results indicate that, compared to regular Text-CNN, our framework can significantly reduce the false positive rate by 13.10% and improve the F1-Score by 8.47% on five years of data, achieving the best experimental results. Additionally, evaluations show that our framework can save on the human costs required for model maintenance. We only need 1% of the budget per month to reduce the false positive rate by 11.16% and improve the F1-Score by 6.44%.

cs.CR↗
arXiv2025

Strongly confined Mid-infrared to Terahertz Phonon Polaritons in Ultra-thin SrTiO3

Phonon polaritons (PhPs) enable subwavelength light control for infrared sensing, imaging, and optoelectronics, but conventional polar materials have narrow Reststrahlen bands, limiting applications. Materials that support PhPs with broad spectral range, strong field confinement, slow group velocity, and high quality factor are therefore needed. Here, using monochromatic electron energy loss spectroscopy in a scanning transmission electron microscope, we demonstrate that ultra-thin SrTiO3 membranes possess the desired properties. Systematic measurements across varying thicknesses reveal two PhP branches with wide spectral dispersion, strong confinement, and anomalously slow group velocities spanning from the mid-infrared to terahertz range. Notably, in 3-nm-thick membranes, these polaritons exhibit unprecedented confinement factors exceeding 500 and group velocities as low as ~ 7 x 10-5c, rivaling the best-performing van der Waals materials. These findings establish perovskite oxide such as SrTiO3 as versatile platforms for tailoring light-matter interactions at the nanoscale, providing critical insights for the design of next-generation photonic devices requiring broadband operation and enhanced optical confinement.

physics.optics↗
arXiv2025

MG-HGNN: A Heterogeneous GNN Framework for Indoor Wi-Fi Fingerprint-Based Localization

Received signal strength indicator (RSSI) is the primary representation of Wi-Fi fingerprints and serves as a crucial tool for indoor localization. However, existing RSSI-based positioning methods often suffer from reduced accuracy due to environmental complexity and challenges in processing multi-source information. To address these issues, we propose a novel multi-graph heterogeneous GNN framework (MG-HGNN) to enhance spatial awareness and improve positioning performance. In this framework, two graph construction branches perform node and edge embedding, respectively, to generate informative graphs. Subsequently, a heterogeneous graph neural network is employed for graph representation learning, enabling accurate positioning. The MG-HGNN framework introduces the following key innovations: 1) multi-type task-directed graph construction that combines label estimation and feature encoding for richer graph information; 2) a heterogeneous GNN structure that enhances the performance of conventional GNN models. Evaluations on the UJIIndoorLoc and UTSIndoorLoc public datasets demonstrate that MG-HGNN not only achieves superior performance compared to several state-of-the-art methods, but also provides a novel perspective for enhancing GNN-based localization methods. Ablation studies further confirm the rationality and effectiveness of the proposed framework.

cs.LG↗
arXiv2025

Can Agent Conquer Web? Exploring the Frontiers of ChatGPT Atlas Agent in Web Games

OpenAI's ChatGPT Atlas introduces new capabilities for web interaction, enabling the model to analyze webpages, process user intents, and execute cursor and keyboard inputs directly within the browser. While its capacity for information retrieval tasks has been demonstrated, its performance in dynamic, interactive environments remains less explored. In this study, we conduct an early evaluation of Atlas's web interaction capabilities using browser-based games as test scenarios, including Google's T-Rex Runner, Sudoku, Flappy Bird, and Stein.world. We employ in-game performance scores as quantitative metrics to assess performance across different task types. Our results show that Atlas performs strongly in logical reasoning tasks like Sudoku, completing puzzles significantly faster than human baselines, but struggles substantially in real-time games requiring precise timing and motor control, often failing to progress beyond initial obstacles. These findings suggest that while Atlas demonstrates capable analytical processing, there remain notable limitations in dynamic web environments requiring real-time interaction. The website of our project can be found at https://atlas-game-eval.github.io.

cs.CL↗