arXiv subjects

Yuze Li

Publications and source records attributed to Yuze Li.

14 recordsLinked to original sources

arXiv2026

Trusting AI in Competitive Markets

People's trust in AI advice diverges as they use it, deepening for some and eroding for others. We study this divergence in oligopoly pricing, where advice cannot prove itself: rivals' responses decide whether it pays off. In a laboratory experiment, 273 sellers compete across 91 three-seller markets over 30 rounds; we vary the presence of AI pricing recommendations and the gender composition of the market (female-only, male-only, or mixed). We find that the gender composition of the market shapes how sellers learn from the advice, and where prices settle as a result. In female-only markets, recommendations raise prices by 29% and profits by 39%; in male-only and mixed-gender markets, they have no significant effect. A Non-Homogeneous Hidden Markov Model reveals a composition-specific dynamic association: profitable rounds predict rising adherence to the AI in female-only markets and declining adherence otherwise, a pattern consistent with learned trust and self-serving attribution. The pattern reverses what recent evidence on gender and AI would predict. We discuss implications for platform governance and regulatory oversight, which should focus not only on the algorithm but on the human side that shapes its effects.

cs.GT↗

arXiv2026

GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction

3D Gaussian Splatting (3DGS) has emerged as a prominent paradigm for 3D reconstruction and novel view synthesis. However, it remains vulnerable to severe artifacts when trained under sparse-view constraints. While recent methods attempt to rectify artifacts in rendered views using image diffusion models, they typically rely on multi-view self-attention to retrieve information from reference images. We observe that this mechanism often fails when the rendered novel views output by 3DGS are heavily corrupted: damaged query features lead to erroneous cross-view retrieval, resulting in inconsistent rendering refinement. To address this, we propose GeoQuery, a geometry-guided diffusion framework that integrates generative priors with explicit geometric cues via a novel Geometry-guided Cross-view Attention (GCA) mechanism. First, by leveraging predicted depth maps and camera poses, we construct a geometry-induced correspondence field to sample reference features, forming a geometry-aligned proxy query that replaces the corrupted rendering features. Furthermore, we design a new cross-view feature aggregation pipeline, in which we restrict the cross-view attention to a local window around each proxy query to effectively retrieve useful features while suppressing spurious matches. GeoQuery can be seamlessly integrated into existing diffusion-based pipelines, enabling robust reconstruction even under extreme view sparsity. Extensive experiments on sparse-view novel view synthesis and rendering artifact removal demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2026

UAU-Net: Uncertainty-aware Representation Learning and Evidential Classification for Facial Action Unit Detection

Facial action unit (AU) detection remains challenging because it involves heterogeneous, AU-specific uncertainties arising at both the representation and decision stages. Recent methods have improved discriminative feature learning, but they often treat the AU representations as deterministic, overlooking uncertainty caused by visual noise, subject-dependent appearance variations, and ambiguous inter-AU relationships, all of which can substantially degrade robustness. Meanwhile, conventional point-estimation classifiers often provide poorly calibrated confidence, producing overconfident predictions, especially under the severe label imbalance typical of AU datasets. We propose UAU-Net, an Uncertainty-aware AU detection framework that explicitly models uncertainty at both stages. At the representation stage, we introduce CV-AFE, a conditional VAE (CVAE)-based AU feature extraction module that learns probabilistic AU representations by jointly estimating feature means and variances across multiple spatio-temporal scales; conditioning on AU labels further enables CV-AFE to capture uncertainty associated with inter-AU dependencies. At the decision stage, we design AB-ENN, an Asymmetric Beta Evidential Neural Network for multi-label AU detection, which parameterizes predictive uncertainty with Beta distributions and mitigates overconfidence via an asymmetric loss tailored to highly imbalanced binary labels. Extensive experiments on BP4D and DISFA show that UAU-Net achieves strong AU detection performance, and further analyses indicate that modeling uncertainty in both representation learning and evidential prediction improves robustness and reliability.

cs.CV↗

arXiv2026

Expected Sensitivity of the Light Dark Matter eXperiment to Long-Lived Dark Photons and Axion-Like Particles

The Light Dark Matter eXperiment (LDMX) is an electron-beam fixed-target experiment primarily designed to achieve world-leading, model-independent sensitivity to sub-GeV dark matter particles. LDMX aims to identify dark sector particle production through the detection of events with substantial missing energy and momentum, a signature of invisible particles escaping detection. Beyond this primary objective, LDMX offers a complementary search strategy for long-lived, visibly decaying particles, such as dark photons and axion-like particles. We present the first detailed evaluation of the ability of LDMX to identify visibly decaying, long-lived particles that couple to electrons using a detailed simulation, based on the Geant4-toolkit, that incorporates realistic detection efficiencies and background levels. We demonstrate that LDMX can achieve a sensitivity that is competitive with other experiments that are currently running. The models explored in this paper are distinct and complementary to those probed in the LDMX flagship missing-momentum analysis. Through searching for both invisible dark matter and visibly decaying long-lived signatures, LDMX will significantly advance the search for light dark matter and provide a broad exploration of the sub-GeV dark sector.

hep-ex↗

arXiv2026

On the Fragility of AI Agent Collusion

Recent work shows that pricing with symmetric LLM agents leads to algorithmic collusion. We show that collusion is fragile under the heterogeneity typical of real deployments. In a stylized repeated-pricing model, heterogeneity in patience or data access reduces the set of collusive equilibria. Experiments with open-source LLM agents (totaling over 2,000 compute hours) align with these predictions: patience heterogeneity reduces price lift from 22% to 10% above competitive levels; asymmetric data access, to 7%. Increasing the number of competing LLMs breaks up collusion; so does cross-algorithm heterogeneity, that is, setting LLMs against Q-learning agents. But model-size differences (e.g., 32B vs. 14B weights) do not; they generate leader-follower dynamics that stabilize collusion. We discuss antitrust implications, such as enforcement actions restricting data-sharing and policies promoting algorithmic diversity.

cs.GT↗

arXiv2026

pqRPKI: A Practical RPKI Architecture for the Post-Quantum Era

The Resource Public Key Infrastructure (RPKI) secures Internet routing by binding IP prefixes to authorized Autonomous Systems, yet its RSA foundations are vulnerable to quantum adversaries. A naive swap to post-quantum (PQ) signatures (eg Falcon) is a poor fit for RPKI's bulk model: every relying party (RP) repeatedly fetches and validates the entire global repository, so larger keys and signatures inflate bandwidth and CPU cost, especially during a long dual-stack transition. We present pqRPKI , a post-quantum RPKI framework that pairs a multi-layer Merkle Tree Ladder (MTL) with RPKI objects, customized to relocate per-object verification material from certificates into the Manifest. To update RPKI for Merkle tree based schemes, pqRPKI redesign the RPKI manifest and delegation chain, introduces a ladder-guided sync and bulk-verification workflow that lets validators localize diffs top-down and rebuild trees bottom-up. pqRPKI also preserves current RPKI objects and encodings, supports both hosted and delegated operation, and provides an additive migration path that coexists with today's trust anchors for dual-stack deployment with little size overhead. Implemented as a working publication point (PP) and RPs, we show that pqRPKI reduces repository footprint to 546.8 MB on average (65.5%/83.1% smaller than Falcon/ML-DSA), cuts full-cycle validation to 102.7 s, and achieves 118.3 s end-to-end PP to Router time, enabling sub-2-minute operating cadences with full-repository validation each cycle. Dual-stack deployment with RSA only adds just 3.4% size overhead versus today's RPKI repositories.

cs.NI↗

arXiv2026

Let Your Image Move with Your Motion! -- Implicit Multi-Object Multi-Motion Transfer

Motion transfer has emerged as a promising direction for controllable video generation, yet existing methods largely focus on single-object scenarios and struggle when multiple objects require distinct motion patterns. In this work, we present FlexiMMT, the first implicit image-to-video (I2V) motion transfer framework that explicitly enables multi-object, multi-motion transfer. Given a static multi-object image and multiple reference videos, FlexiMMT independently extracts motion representations and accurately assigns them to different objects, supporting flexible recombination and arbitrary motion-to-object mappings. To address the core challenge of cross-object motion entanglement, we introduce a Motion Decoupled Mask Attention Mechanism that uses object-specific masks to constrain attention, ensuring that motion and text tokens only influence their designated regions. We further propose a Differentiated Mask Propagation Mechanism that derives object-specific masks directly from diffusion attention and progressively propagates them across frames efficiently. Extensive experiments demonstrate that FlexiMMT achieves precise, compositional, and state-of-the-art performance in I2V-based multi-object multi-motion transfer. Our project page is: https://ethan-li123.github.io/FlexiMMT_page/

cs.CV↗

arXiv2025

Eliminate Branches by Melding IR Instructions

Branch mispredictions cause catastrophic performance penalties in modern processors, leading to performance loss. While hardware predictors and profile-guided techniques exist, data-dependent branches with irregular patterns remain challenging. Traditional if-conversion eliminates branches via software predication but faces limitations on architectures like x86. It often fails on paths containing memory instructions or incurs excessive instruction overhead by fully speculating large branch bodies. This paper presents Melding IR Instructions (MERIT), a compiler transformation that eliminates branches by aligning and melding similar operations from divergent paths at the IR instruction level. By observing that divergent paths often perform structurally similar operations with different operands, MERIT adapts sequence alignment to discover merging opportunities and employs safe operand-level guarding to ensure semantic correctness without hardware predication. Implemented as an LLVM pass and evaluated on 102 programs from four benchmark suites, MERIT achieves a geometric mean speedup of 10.9% with peak improvements of 32x compared to hardware branch predictor, demonstrating the effectiveness with reduced static instruction overhead.

cs.PL↗

arXiv2025

LDMX -- The Light Dark Matter eXperiment

The Light Dark Matter eXperiment (LDMX) is an electron fixed-target experiment optimized to search for sub-GeV dark matter production through the missing momentum signature. LDMX is designed to operate in End Station A at SLAC, using an 8 GeV electron beam accelerated alongside the LCLS-II drive beam. The design of the apparatus is strongly motivated by the performance requirements of a high-rate missing momentum search and leverages detector technologies and designs from other experiments along with existing facilities at SLAC. LDMX will improve on previous results by up to three orders of magnitude, enabling broad sensitivity to dark sector scenarios including the dark matter interaction strengths motivated by freeze-out of MeV-GeV mass dark matter to the observed relic abundance. With hermetic forward coverage, LDMX also has sensitivity to visible signatures of dark sectors and provides a unique probe of electron-nuclear interactions important to interpreting data from accelerator-based neutrino experiments. This report encompasses the technical design of the LDMX Detector, its simulated performance, and the physics capabilities of the experiment.

hep-ex↗

arXiv2025

TRACE: Time SeRies PArameter EffiCient FinE-tuning

We propose an efficient fine-tuning method for time series foundation models, termed TRACE: Time Series Parameter Efficient Fine-tuning. While pretrained time series foundation models are gaining popularity, they face the following challenges: (1) Unlike natural language tasks, time series data vary in frequency, channel numbers, historical/prediction lengths. For long-term forecasting tasks in particular, tailored fine-tuning can significantly enhance performance.(2) Existing parameter-efficient tuning methods like LoRA remain applicable but require adaptation to temporal characteristics. To address these challenges, our TRACE framework introduces two key innovations: (1) Gated DSIC (Gated Dynamic Simulation Importance Calculation), an unbiased LoRA module importance selection mechanism that ensures conditional parameter consistency before and after masking. Experiments demonstrate that Gated DSIC outperforms common fine-tuning. (2) Reconstructed prediction heads for long-term forecasting tasks, which achieve comparable or superior performance to linear probing heads while drastically reducing parameter counts. Extensive experiments on long-/short-term forecasting, anomaly detection and natural language tasks across diverse datasets, coupled with ablation studies, validate the effectiveness of our method.

cs.LG↗

arXiv2023

Towards Persistent Memory based Stateful Serverless Computing for Big Data Applications

The Function-as-a-service (FaaS) computing model has recently seen significant growth especially for highly scalable, event-driven applications. The easy-to-deploy and cost-efficient fine-grained billing of FaaS is highly attractive to big data applications. However, the stateless nature of serverless platforms poses major challenges when supporting stateful I/O intensive workloads such as a lack of native support for stateful execution, state sharing, and inter-function communication. In this paper, we explore the feasibility of performing stateful big data analytics on serverless platforms and improving I/O throughput of functions by using modern storage technologies such as Intel Optane DC Persistent Memory (PMEM). To this end, we propose Marvel, an end-to-end architecture built on top of the popular serverless platform, Apache OpenWhisk and Apache Hadoop. Marvel makes two main contributions: (1) enable stateful function execution on OpenWhisk by maintaining state information in an in-memory caching layer; and (2) provide access to PMEM backed HDFS storage for faster I/O performance. Our evaluation shows that Marvel reduces the overall execution time of big data applications by up to 86.6% compared to current MapReduce implementations on AWS Lambda.

cs.DC↗

arXiv2023

Understanding and Optimizing Serverless Workloads in CXL-Enabled Tiered Memory

Recent Serverless workloads tend to be largescaled/CPU-memory intensive, such as DL, graph applications, that require dynamic memory-to-compute resources provisioning. Meanwhile, recent solutions seek to design page management strategies for multi-tiered memory systems, to efficiently run heavy workloads. Compute Express Link (CXL) is an ideal platform for serverless workloads runtime that offers a holistic memory namespace thanks to its cache coherent feature and large memory capacity. However, naively offloading Serverless applications to CXL brings substantial latencies. In this work, we first quantify CXL impacts on various Serverless applications. Second, we argue the opportunity of provisioning DRAM and CXL in a fine-grained, application-specific manner to Serverless workloads, by creating a shim layer to identify, and naively place hot regions to DRAM, while leaving cold/warm regions to CXL. Based on the observation, we finally propose the prototype of Porter, a middleware in-between modern Serverless architecture and CXL-enabled tiered memory system, to efficiently utilize memory resources, while saving costs.

cs.DC↗

arXiv2022

Just ClozE! A Novel Framework for Evaluating the Factual Consistency Faster in Abstractive Summarization

The issue of factual consistency in abstractive summarization has received extensive attention in recent years, and the evaluation of factual consistency between summary and document has become an important and urgent task. Most of the current evaluation metrics are adopted from the question answering (QA) or natural language inference (NLI) task. However, the application of QA-based metrics is extremely time-consuming in practice while NLI-based metrics are lack of interpretability. In this paper, we propose a cloze-based evaluation framework called ClozE and show the great potential of the cloze-based metric. It inherits strong interpretability from QA, while maintaining the speed of NLI- level reasoning. We demonstrate that ClozE can reduce the evaluation time by nearly 96% relative to QA-based metrics while retaining their interpretability and performance through experiments on six human-annotated datasets and a meta-evaluation benchmark GO FIGURE (Gabriel et al., 2021). Finally, we discuss three important facets of ClozE in practice, which further shows better overall performance of ClozE compared to other metrics.

cs.CL↗

arXiv2022

Towards cost-effective and resource-aware aggregation at Edge for Federated Learning

Federated Learning (FL) is a machine learning approach that addresses privacy and data transfer costs by computing data at the source. It's particularly popular for Edge and IoT applications where the aggregator server of FL is in resource-capped edge data centers for reducing communication costs. Existing cloud-based aggregator solutions are resource-inefficient and expensive at the Edge, leading to low scalability and high latency. To address these challenges, this study compares prior and new aggregation methodologies under the changing demands of IoT and Edge applications. This work is the first to propose an adaptive FL aggregator at the Edge, enabling users to manage the cost and efficiency trade-off. An extensive comparative analysis demonstrates that the design improves scalability by up to 4X, time efficiency by 8X, and reduces costs by more than 2X compared to extant cloud-based static methodologies.

cs.LG↗