Searcharxiv⌕ Search

arXiv subjects

Yuxuan Li

Publications and source records attributed to Yuxuan Li.

At least 19 recordsLinked to original sources

SARVIA: Fast-Adapting the Strong SAR Foundation Models That Are Already in Your MLLMs

Synthetic aperture radar (SAR) foundation models provide transferable representations for diverse perception tasks in all-weather Earth observation. However, their development often relies on costly large-scale SAR pretraining, raising the question of whether such extensive domain-specific pretraining is necessary. We find that modern multimodal large language models (MLLMs) already provide visual encoders that can outperform dedicated SAR foundation models as downstream initializations. This motivates a new paradigm: reuse general visual capabilities and devote domain training to brief specialization. We therefore introduce SARVIA, an adaptive post-pretraining method that specializes modern MLLMs using self-supervised visual questions with computable answers. These questions are constructed from unlabeled observations through general image tasks that capture spatial relations and SAR-specific tasks that exploit native measurements and SAR--optical correspondence. A shared answer-prediction objective jointly trains low-rank adapters across visual and language components, with loss-driven task sampling. We then export the adapted visual encoder as a standalone backbone. With 600 adaptation steps and 2 GPU-hours, SARVIA outperforms the compared foundation models on all six SAR detection and segmentation benchmarks. Compared with dedicated SAR pretraining, SARVIA reduces domain-training costs by orders of magnitude while improving visual transfer across architectures and scales. This new paradigm shifts the emphasis from repeated, costly pretraining to a reusable specialization process that can benefit from advances in open MLLMs. Dataset and code: https://github.com/zcablii/SARVIA.

cs.CV↗

Think2Listen: Evidence-Centric Learning For Agentic Audio Understanding With LALMS

Recent advances in large audio-language models (LALMs) have broadened audio understanding across speech, sound, and music, with tool-based agents further supporting these tasks by invoking predefined audio tools. However, a persistent gap remains between perceiving acoustic content and using it as evidence for reasoning: recognizing what is audible does not ensure that a model can identify which cues resolve an uncertain decision. To bridge this gap, we propose Think2Listen, an evidence-centric learning framework for agentic audio understanding. Guided by evidence before commitment, Think2Listen couples iterative reasoning with a targeted LALM interaction to actively seek acoustic cues that distinguish competing hypotheses and revise candidate judgments based on the observations returned. It learns what to ask, how to use evidence, and when to stop, using observation-induced changes in candidate-state to inform training credit. Extensive evaluations on two benchmarks spanning seven audio categories demonstrate that Think2Listen achieves (I) enhanced multi-step audio reasoning, with gains in overall accuracy of 5.08%--17.67% over competing audio agents; and (II) improved audio understanding and reasoning across speech, sound, and music, boosting overall accuracy by 2.29%--13.10% over the corresponding baselines. The source code is available at https://github.com/JinWang79/Think2Listen.

cs.SD↗

A Crowd-Audited Atlas of Implicit Bias in LLM-Powered Agents

Prior work has shown that large language models (LLMs) express implicit biases in high-publicity, one-off decision scenarios such as hiring and intelligence assessment. However, as people increasingly employ autonomous, LLM-powered AI agents that make decisions on their behalf in doing day-to-day tasks, it is of critical importance that we understand how implicit biases, based on sociodemographic assumptions, emerge across a broad milieu of workaday decision scenarios. We used the 17 domains of daily activity in the American Time Use Survey (ATUS) to generate an atlas of 506 decision scenarios in which LLMs --- endowed with personas representing different races, gender identities, and political ideologies --- expressed significant implicit bias. Next, in a crowdsourced audit, 500 participants made 8,010 binary choices about which implicitly biased decision scenarios most deserved further review. We found that participants prioritized decision scenarios that had broad relevance (e.g., about food choices), were high stakes (e.g., about health), and where all members of a simulated sociodemographic group made unanimous decisions (because it was a clear indication of stereotyping). They were less swayed by the magnitude of an observed disparity or the specific ATUS domain the decision scenario represented. When examining the rationale behind their prioritization choices, we found that participants often interpreted disparities as traits of demographic groups and judged whether those traits seemed plausible, often based on their own internalized stereotypes. We discuss implications for building personalized AI agents, digital twins, social simulations, and for using crowdsourced bias audits.

cs.CY↗

The $λ>0$ case for $Δu=λ-c e^u$ type equation on high dimensional spheres

Motivated by prescribed Chern scalar curvature problems in complex geometry, we study the equation $Δ_{\mathbb S^{N-1}}V+λ(e^V-1)=0$ with $λ>0$ on spheres. For $N\ge4$ and $λ>2(N-2)$ with $λ\ne2N$, we prove the existence of a nonconstant smooth solution that is axially symmetric and symmetric about the equator.

math.DG↗

ForgeSystem: An Architecture for Demand-Specific Artefact Production with AI Agents

General-purpose software serves many different demands, but this flexibility costs performance and efficiency on any specific demand. Software tailored to a specific demand avoids these losses, yet developing it requires substantial time and effort from human experts. AI agents offer an alternative: they can design, implement and test artefacts tailored to individual demands. We call this production paradigm Forge. Forging for a demand is economically justified when the cumulative benefit of specialisation exceeds the total cost of construction, verification and maintenance. To make Forge a repeatable production process, we propose ForgeSystem, which consists of a control layer, a forge loop and a recursive self-improvement (RSI) loop. The control layer selects which artefact serves each demand and decides which demands to forge, when to forge them and from which starting point; the forge loop iterates between production and verification until a candidate artefact passes verification; and the RSI loop draws on accumulated production records to supply starting points, refine the harness and train models. We implement ForgeSystem for training frameworks, decoding megakernels and individual computational kernels. Forged training engines reach 1.047-1.332x the model-FLOPs utilisation of their reference frameworks, forged megakernels achieve a geometric-mean decoding speedup of 1.21x over SGLang across thirteen configurations, and forged kernels match or exceed expert libraries in eighteen of twenty-two configurations, while satisfying task-specific quality requirements. Controlled comparisons show that explicit quality requirements steer agents towards optimisations that preserve training quality. We also discuss a gradual transition to Forge through service routing, and how demand-specific production may shift value accumulation and trust towards production systems.

cs.SE↗

Cross-Asset Knowledge Transfer for Early Fault Detection of Data-Scarce Assets Without Target Fault Data

Reliability management of industrial fleets depends on early fault warnings, yet lifecycle data across similar assets are highly imbalanced. A few assets accumulate run-to-failure histories, while newly installed or rarely failing assets provide only normal-condition data. This paper asks how diagnostic knowledge can be transferred from a data-rich source asset to a data-scarce target asset when no fault data have been observed on the target. We formulate cross-asset early fault detection as a zero-shot domain adaptation problem, in which zero-shot refers to the absence of target fault samples, and propose a framework that requires only normal data from the target. The framework comprises (1) a statistical process control step that labels the source asset run-to-failure data with an exponentially weighted moving average chart, reducing manual annotation to verifying flagged segments, (2) an Adapted Domain-Adversarial Neural Network (ADANN) that combines domain-adversarial training and a Maximum Mean Discrepancy penalty with an Adapted Classification-Domain (ACD) loss, which anchors the classifier normal region to the target own normal data, and (3) an ahead-of-time labeling scheme with a prediction horizon that targets incipient faults. Under an exact-classification assumption, a theoretical analysis characterizes the domain-adversarial term for a normal-only target and the alignment state in which source fault features remain separated from target normal features. On a public run-to-failure bearing dataset, ADANN attains the highest mean F1-score among four transfer baselines, with a nominally significant precision gain over the strongest baseline, and its robustness is examined under synthetic noise.

cs.LG↗

Causal Machine Learning for Multilevel Studies with Unmeasured Cluster-Level Covariates via Variational Autoencoders

Unmeasured confounders are a key obstacle to accurately estimating treatment effects in observational studies, and in multilevel data, they often arise at the cluster level. Flexible machine learning methods cannot directly resolve such unmeasured confounding. To address this, we propose the variational autoencoder-augmented R-learner (VAE-R), which leverages variational autoencoders (VAEs) to infer unmeasured cluster-level covariates from the within-cluster dependence of outcome and treatment residuals, and uses the resulting adjustments to estimate the conditional average treatment effect (CATE) and the average treatment effect (ATE). The VAE decoder is specified through an offset likelihood so that the latent variables capture only the cluster-level variation left unexplained by measured covariates. VAE-R accommodates unmeasured cluster-level confounders in observational studies and unmeasured cluster-level predictors of the outcome in multisite randomized trials. We also provide data-driven strategies for selecting the two hyperparameters of the VAE, the latent dimension size and the Kullback-Leibler weight. Our simulation study shows that VAE-R nearly eliminates the bias of the ordinary R-learner's CATE and ATE estimates in multilevel observational data and improves their precision in multisite randomized trials. Finally, we illustrate VAE-R with two datasets, one from a multilevel observational study and the other from a multisite randomized trial.

stat.ME↗

Spin-Density-Driven Hybrid Spin Splitting in Collinear Compensated Magnets

Nonrelativistic spin splitting in collinear compensated magnets is constrained by spin-group symmetry, with distinct alternating and Zeeman-type splitting typically associated with altermagnets and fully compensated ferrimagnets, respectively. From a spin-density perspective, we propose a class of hybrid compensated magnets in which alternating-like and Zeeman-type spin splitting coexist within a single collinear compensated state. Using a minimal two-sector model, we demonstrate that this coexistence arises from competition between directional sublattice dispersion and the sector-dependent energy biases arising from the same structural inequivalence. First-principles calculations provide a proof of concept in a crossed bilayer of unequal-width Janus graphene nanoribbons, where the structurally inequivalent ribbons retain approximately symmetry-related spin-density distributions. The valence and conduction sectors support direction-selective spin transport and energy-selective spin-polarized states, respectively. These results connect the spatial organization of spin density with the electronic response to structural inequivalence, providing a design principle for hybrid spin splitting in compensated magnets.

cond-mat.mtrl-sci↗

ForgeKernel: Self-Evolving Kernels Catching and Surpassing Experts and Agents

Purpose-built kernel agents can write high-performance GPU kernels, but existing systems generally lack cross-run knowledge accumulation and architectural evolution. Each run starts from the same initial knowledge, and later iterations largely optimize within an architecture fixed early in the search. We present ForgeKernel, a kernel-generation system that accumulates and reuses knowledge across runs while enabling continued evolution of kernel architectures. It analyzes the hardware behavior of a high-performance reference and distills validated architectural decisions into reusable knowledge of hardware mechanisms rather than imitating source code. It then seals a kernel that passes correctness and performance validation and uses it as the reference for the next optimization run, enabling architectural decisions to be revisited. Across 27 operators and 29 input configurations on NVIDIA Hopper and Blackwell GPUs, ForgeKernel matches or beats its expert reference on 25 configurations, with a geometric-mean performance gain of 10%. On Ascend 910C, it outperforms the per-operator public best on the public case set of all 8 level-4 operators in the CANN-Bench Season 1 final leaderboard, with a geometric-mean gain of 25.1%, while its full-suite submission ranks first on the A3 leaderboard. As of 2026-10-30, public submissions generated by ForgeKernel rank first on all three CANN-Bench 2.0 solution leaderboards (Ascend 910C, 950DT, and 950PR) and on the SOL-ExecBench FlashInfer-Bench track.

cs.DC↗

SatOps-Decision: Low-Latency Discriminative Decisions for Onboard Satellite Communication Operations

We propose SatOps-Decision, a method for low-latency decisions in satellite communication operations. To the best of our knowledge, it is the first application of Jev-style general-purpose discriminative decision models to satellite operations, and the accompanying benchmark is the first dedicated to this approach. The learned scorer, a locally adapted Laya encoder with its native decision head, selects among supplied operational answers in a single forward pass. The benchmark combines authored operational contracts, controlled state changes and independently checked labels in an auditable construction. Evaluation prioritizes complete-request latency and raw decision accuracy; all main accuracy comparisons use the same 1,024 held-out questions, separate from training and development. SatOps-Decision's local scorer has a median latency of 90.3 ms per decision, versus 493.9 ms for Qwen3.5-0.8B generation and 388.4 ms for OneJev1.6-0.8B: $5.47\times$ and $4.30\times$ speedups based on median request times in the measured FP32/MPS implementations. Its mean raw accuracy is 85.3%, versus 42.5% for frozen Laya, 40.7% for Qwen generation and 58.6% for OneJev. As cloud accuracy references, original Jev 1.14/1.13 reach 87.4/81.9%.

cs.LG↗

MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents

Long-horizon agents performing multi-step Web tasks must reuse earlier page observations and interactions to support subsequent actions. However, preserving relevant history does not ensure that it exposes the relations needed for the current decision. We call this gap representation mismatch. To this end, we propose MemPrism, a task-conditioned relational memory framework that separates persistent experience storage from decision-time working memory. MemPrism records interactions as the event stream and dynamically constructs relational views according to the current task context. A lightweight view policy selects the relation structure, evidence range, outcome condition, and granularity, while a deterministic composer and renderer transform historical facts into a temporary optical working-memory view for a frozen task policy. Experiments on long-horizon embodied and web-agent benchmarks show that MemPrism consistently improves the task performance, especially as trajectories become longer, while reducing memory token consumption. Furthermore, the learned view policy transfers across different VLMs without additional adaptation, demonstrating the effectiveness of task-conditioned relational views as a general memory interface for agents.

cs.AI↗

JustGoal: With Only a Goal, the AI Baseline Is Above the Expert Kernels

A small number of GPU kernels often determines the efficiency of large language model training and inference. High-performance kernel development typically relies on expert knowledge through manual implementation, collaboration with general-purpose models, or specialized agents equipped with domain knowledge, evaluation methods, and search workflows. We investigate how much value this knowledge provides as foundation models become stronger. We introduce JustGoal, a goal-only baseline in which a general-purpose agent receives only the optimization objective and constraints, without kernel-specific infrastructure, knowledge bases, or predefined workflows, and builds its own evaluation loop. On NVIDIA B200 GPUs, JustGoal outperforms open-source libraries on 8 of 10 operators, achieving per-operator geometric mean speedups of 1.14x to 2.34x. It also surpasses the fastest publicly released specialized-agent kernel on 5 of 9 operators with available comparisons. In a controlled same-model comparison using Fable 5.1 on single shapes, the KDA-0.5 harness reaches 0.95x of JustGoal's performance, while single-mechanism ablations show no consistent benefit from domain knowledge or predefined workflows. These results indicate that specialized machinery should be justified by clear gains over a same-model, same-scope goal-only baseline and reevaluated whenever the foundation model changes.

cs.DC↗

A Heart Means Recursion: Exploring Visual Meaning and Communication in VLMs

Do vision-language models (VLMs) share our ability to communicate visually? We share preliminary findings, starting from a surprising observation: simple visual symbols like a red heart can strongly influence model behavior on seemingly unrelated tasks, such as steering models towards recursive solutions on simple coding problems. Notably, this steering effect is largely implicit, as models' direct interpretations and thinking traces about visual symbols diverge substantially from their observed behavior. In visual communication between models, this leads to a generation--interpretation gap: while models tend to send shape primitives that they (and humans) find intuitive, these visual cues often fail to steer other models. In further communication games involving abstract concepts and stories, models can creatively use visuals to transmit meaning to one another, although some communications remain non-intuitive to humans. These findings reveal that VLMs might be capable of rich, creative, and visually-grounded communication, but their interpretation and production of visual meaning diverges from human conventions in surprising ways. Together this work highlights both the promise and challenges of visual communication between humans and VLMs.

cs.AI↗

TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems

User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints due to fixed-dimensional vectors. As an emerging alternative for discrete user representation, LLM-generated natural-language user profiles often capture language semantics rather than sequential patterns in user behaviors. Meanwhile, Semantic ID (SID) is effective for item representation, yet existing discrete user representations remain largely confined to quantizing already-pooled user vectors, clustering historical watches, or predicting coarse topic clusters solely for candidate retrieval. We propose TokenMinds, an industrial system that extends the PLUM framework from SID-based item retrieval to generative sequential user modeling. Built on an encoder-decoder architecture adapted from pretrained LLMs, TokenMinds introduces a dual-output design: the encoder outputs a dense user embedding capturing a holistic user state, while the decoder generates discrete SID-based user tokens representing multi-faceted future interests. Grounded in item semantics, these tokens preserve distinct interests that a single pooled vector would average away. Additionally, a shared SID vocabulary across long- and short-form videos unifies cross-scenario behaviors into a single model, cutting upstream training and serving compute by 50% and 31%. Furthermore, leveraging the text vocabulary inherited from the pretrained LLM, TokenMinds interleaves textual search queries directly with watch histories to capture explicit user intent. We validate TokenMinds through offline evaluations and live A/B experiments across YouTube's primary ranking surfaces, serving billions of users asynchronously: SID-based user tokens are effective on their own, yield additive gains alongside dense embeddings, and together outperform the previous-generation, non-LLM user model in production.

cs.IR↗

Model Capacity Frontier: A Development Framework for LLM-Supported Social Simulation

Large language model (LLM) agents are increasingly incorporated into agent-based models (ABMs) on the premise that richer, context-sensitive human behavior can improve empirical fidelity. However, LLM-supported ABMs introduce an open-ended design space in which subtle modeling and configuration choices, such as prompt design and environment coupling, can substantially alter outcomes. Developing LLM-supported ABMs to simulate human collective behavior therefore requires navigating configuration sensitivity while identifying the limitations of the current model architecture. In this paper, we introduce the Model Capacity Frontier (MCF), a framework that characterizes the empirical performance attainable by a specified architecture across its admissible configurations. In multi-objective settings, this capacity is represented by an estimated Pareto frontier obtained through systematic configuration exploration. We demonstrate MCF in crowd simulation of university commencement events with approximately 12,000 agents, using empirical movement data on temporal occupancy, spatial distribution, and flow direction. We first characterize the capacity of a conventional crowd model and then evaluate successive LLM-supported architectural extensions. In the process, MCF reveals which dimensions of attainable performance expand and which remain limited, providing empirical targets for refinement and re-evaluation. Initial LLM integration improves flow direction but degrades temporal occupancy and spatial distribution; subsequent architectural refinement of the LLM layer improves temporal occupancy and recovers spatial performance, while retaining much of the earlier gain in flow direction. Our case study shows how MCF guides the systematic architectural development of LLM-supported ABMs in configuration-sensitive, open-ended design spaces.

cs.MA↗

DuplexLedger: Benchmarking Transactional Memory in Full-Duplex Speech Agents

Full-duplex speech agents must update persistent memory while listening and speaking, yet it remains unclear which events should be stored, revised, or excluded. Existing benchmarks isolate interaction timing from memory outcomes, obscuring the state transitions behind a correct answer. We introduce DuplexLedger, a bilingual benchmark of 1,094 persistent sessions aligning four full-duplex scenarios with event-level Write/Update/Ignore/Retain supervision, explicit pre/post memory states, and 6,564 same-session questions and checks. Evaluating five full-duplex models reveals an interaction-memory gap: no system combines strong boundary control with coherent final-state memory, and the best final-state fact coverage is 2.01%. We propose ACT-Mem, an 8.92M-parameter sidecar comprising an event controller, a versioned transactional ledger, and a typed retriever coupled with a frozen MiniCPM-o 4.5 backbone. On 219 held-out sessions, ACT-Mem increases latest-value accuracy from 4.11% to 8.68% while reducing stale assertions and distractor adoption. It improves interaction boundaries but slows interruption stopping. These results motivate selective, auditable full-duplex memory rather than indiscriminate transcript retention. Code is available at https://github.com/lyx-researcher/DuplexLedger.

cs.AI↗

Better Retrieval, Limited Clustering Gains: A Controlled Study of Multilingual Company Entity Resolution

Company name retrieval and final entity clustering can respond differently to encoder adaptation. We study this dependency through a controlled pipeline: train multilingual E5 encoders with matched positive examples and random or hard negatives, select checkpoints on development data, retrieve within equal country-specific edge budgets, and apply unchanged pair classifiers and guarded Union-Find clus- tering. Evaluation uses a subsequently collected GLEIF snapshot; a stratified, assisted human audit and a post-hoc temperature sweep examine label and parameter sensitivity. On 3,633 names with source-silver labels, adapted retrieval raises direct pair recall from 53.74% to 76.98%, whereas cluster recall moves from 32.54% to 33.33%. Most newly retrieved positives fail the existing classifier threshold. The study contributes a controlled comparison and pair-level diagnosis of this loss between retrieval and confirma-tion. It shows why evaluating a replacement retriever requires measuring the resulting entity partition, while leaving joint matcher retraining and independent gold-label evaluation for future work.

cs.AI↗

Benefit-Targeted Routing and Bounded Revision for LLM-Based Evidence Screening in Manufacturing Supplier Discovery

An evidence-review system must allocate additional model judgments and control their use. We study these software decisions on 6,164 frozen manufacturing source-task pairs. Benefit-targeted routing learns recovered agreement minus newly introduced disagreement. On the original 300-case test, 60 consultations yield 202/231 agreements with two human references versus 189/218 for a logistic-risk router. An additional 300 cases were independently annotated twice using equal frozen evidence. Without retraining the historical policies, the corresponding counts are 164/190 versus 163/193; the differences do not resolve an advantage. Strict scalar-Ridge controls share preprocessing, regularization and fitting, and remain inconclusive. Quotation and requested-state replacement gates retain rejected cases and budget costs; their joint gate rejects one original and two additional consultations without changing primary outcomes. Evidence ablations, fusion and bounded updates supply further controls. A completed 200-pair identity audit yields 97.45 percent weighted merge precision after eight author adjudications. This audits a provisional map, while prospective company-disjoint performance remains untested.

cs.AI↗