arXiv subjects

Yu Wang

Publications and source records attributed to Yu Wang.

At least 127 records · Page 7Linked to original sources

arXiv2026

Critic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning

Offline-to-online (O2O) reinforcement learning aims to leverage policies pretrained on static datasets while improving them through online interaction. However, directly reusing an offline-trained critic can hinder online fine-tuning: as the policy and data distribution change rapidly, value estimates inherited from offline training may become misaligned with the online environment, leading to inaccurate policy improvement and inefficient exploration. To address this problem, we introduce Critic-Free Pretraining: an efficient paradigm that completely abandons the approach of offline critic training, allowing a freshly initialized critic to adapt without inheriting biased estimates. CFP is compatible with various mainstream O2O algorithms and consistently matches or improves upon conventional O2O algorithms across a diverse set of tasks, with particularly pronounced gains on several challenging tasks.

cs.LG↗

arXiv2026

RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models

Recent studies have demonstrated the potential of reinforcement learning (RL) to improve the task performance of vision-language-action (VLA) models through interaction. However, current efforts remain fragmented, lacking a unified platform for fair comparison across architectures and algorithms, as well as an efficient system design for scalable training. Therefore, we present RLinf-VLA, a unified and efficient framework for scalable RL training of VLA models. RLinf-VLA standardizes the integration of diverse VLA architectures, RL algorithms, and heterogeneous simulators through a unified interface, enabling extensibility and reproducibility. To improve efficiency, the framework adopts a flexible resource allocation architecture for rendering, inference, and training in RL pipelines. In particular, RLinf-VLA introduces a hybrid fine-grained pipeline allocation strategy that achieves a 1.61$\times$-1.88$\times$ training speedup on ManiSkill. Using this framework, RL-trained models achieve strong performance across embodied benchmarks, including 98.11% success on 130 LIBERO tasks, 97.66% success on 25 ManiSkill tasks, and 84.63% average success across 6 RoboTwin tasks. In addition, RLinf-VLA distills a set of effective practices for RL-based VLA training. We envision RLinf-VLA as a foundational framework for efficient, unified, and reproducible research in embodied intelligence.

cs.RO↗

arXiv2026

CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) relies on evidence ranking to determine what information is exposed to the generator, yet existing retrieval and reranking methods primarily estimate query--document relevance. Relevance, however, is not equivalent to generator-side usefulness: a relevant passage may introduce ambiguity or distraction, whereas a lower-ranked passage may stabilize the generator's answer. We present CAR (Confidence-Aware Reranking), a training-free rank-correction framework that uses query-only answer stability as a control and measures each candidate by the change it induces in sampled-answer semantic stability. This controlled contrast estimates a document's marginal contribution to generator behavior without treating semantic stability as relevance or calibrated correctness. CAR converts these confidence changes into coarse precedence constraints and returns the feasible ranking with minimum Kendall distance from the baseline, preserving existing pairwise preferences unless generator-side evidence supports reversing them. Experiments on NQ, HotpotQA and FEVER across sparse and dense retrievers, seven ranking methods and three generator families show robust improvements. In the BM25-centered main analysis, CAR achieves a \textbf{+5.53\% mean relative NDCG@5 gain}; on the fixed NQ-answerable downstream evaluation, it improves token-level F1 by \textbf{+0.43 points}, with ranking and generation gains strongly aligned across rankers ($ρ= 0.93$). These results position CAR as a deployment-friendly, generator-aware correction layer that complements relevance while preserving informative prior rankings. CAR requires neither task-specific training nor access to model internals such as logits or hidden states, making it applicable to black-box LLMs through generated outputs alone.

cs.CL↗

arXiv2026

Uniformly Stable Minimal Weyl--Heisenberg Measurements Approaching the SIC Benchmark

Informational completeness (IC) guarantees that an inverse exists, not that it is statistically well conditioned. For minimal rank-one Weyl--Heisenberg (WH) measurements, covariance makes the nonidentity projector-Gram spectrum proportional to the fiducial's ambiguity intensities, with eigenvalues $d|χ_ϕ(u)|^2$, turning stability into an explicit worst-direction design problem; write $λ$ for its smallest nonidentity eigenvalue. Haar fiducials are IC almost surely while $\mathbb E[λ^{-1}]=\infty$, and an explicit geometric family used to establish balanced informationally complete measurements in every dimension has a normalized spectral floor bounded above by an exponentially decaying envelope. We then construct a hierarchy of minimal measurements. A cyclic family with exactly $d^2$ outcomes in every integer dimension has floors $Θ(d^{-3})$ for odd $d$ and $Θ(d^{-5})$ for even $d$; a finite-field family for $q=2^m$ obeys the uniform bound $λ\ge4/9$. Our main result treats every prime-power dimension of characteristic $p\ge5$. A balanced one-coordinate perturbation repairs the zero ambiguity axis of a cubic Alltop state, gives an attained floor uniformly bounded below by a positive constant, and confines the entire nonidentity spectrum to $[L_q,U_q]$ with $U_q/L_q\to1$. Its SIC-normalized minimum tends to one, and $λ(ϕ_q)/Λ_q^\star\to1$ for the global finite-field WH max--min optimum $Λ_q^\star$, without assuming SIC existence. The complete spectrum determines the exact finite-sample Hilbert--Schmidt error of canonical linear inversion at $I/d$, while its lower edge controls local Fisher efficiency and canonical-shadow bounds.

quant-ph↗

arXiv2026

CADET: Context-Conditioned Ads CTR Prediction With a Decoder-Only Transformer

Click-through rate (CTR) prediction is fundamental to online advertising systems. While Deep Learning Recommendation Models (DLRMs) with explicit feature interactions have long dominated this domain, recent advances in generative recommenders have shown promising results in content recommendation. However, adapting these transformer-based architectures to ads CTR prediction still presents unique challenges, including handling post-scoring contextual signals, maintaining offline-online consistency, and scaling to industrial workloads. We present CADET (Context-Conditioned Ads Decoder-Only Transformer), an end-to-end decoder-only transformer for ads CTR prediction deployed at LinkedIn. Our approach introduces several key innovations: (1) a context-conditioned decoding architecture with multi-tower prediction heads that explicitly model post-scoring signals such as ad position, resolving the chicken-and-egg problem between predicted CTR and ranking; (2) a self-gated attention mechanism that stabilizes training by adaptively regulating information flow at both representation and interaction levels; (3) a timestamp-based variant of Rotary Position Embedding (RoPE) that captures temporal relationships across timescales from seconds to months; (4) session masking strategies that prevent the model from learning dependencies on unavailable in-session events, addressing train-serve skew; and (5) production engineering techniques including tensor packing, sequence chunking, and custom Flash Attention kernels that enable efficient training and serving at scale. In online A/B testing, CADET achieves a 11.04\% CTR lift compared to the production LiRank baseline model, a hybrid ensemble of DCNv2 and sequential encoders. The system has been successfully deployed on LinkedIn's advertising platform, serving the main traffic for homefeed sponsored updates.

cs.LG↗

arXiv2026

End-to-End Fairness Optimization with Fair Decision-Focused Learning

Many real-world systems rely on predictive models to inform decisions, and fairness concerns arise in both the prediction and decision stages. We introduce end-to-end fairness optimization (E2EFO) as a unifying framework that integrates fairness across the prediction-to-decision pipeline. We focus on resource allocation with group-based fairness: the prediction task estimates allocation impacts while limiting accuracy disparity across groups, and the decision task distributes those impacts equitably by optimizing a group-based alpha-fairness measure. Within this framework, we propose fair decision-focused learning (FDFL), a training paradigm that jointly accounts for prediction accuracy, prediction fairness, and decision regret -- the loss in decision fairness due to imperfect predictions. FDFL trains the predictor by gradient descent, combining the objective gradients through multi-task learning techniques. The core computational challenge is the decision Jacobian with respect to the predictor parameters: we derive exact closed-form formulas for a tractable class of fair allocation and apply a differentiable optimization layer in the general case. We further establish a finite-sample generalization bound for the scalarized FDFL objective. Numerical experiments on a healthcare-based single resource allocation and a synthetic multiple resource allocation illustrate the value of jointly accounting for prediction fairness and decision fairness in prediction-informed decision-making.

cs.LG↗

arXiv2026

Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers

A single model scale challenges the flexibility of a production retrieval system: some settings need it faster, others need a smaller index, and the right trade-off changes with the workload. In the context of information retrieval (IR), a transformer-based model can be made smaller in three ways---using fewer layers, passing fewer tokens through the upper layers, or producing a shorter embedding---and each way saves a different compute resource. These options have been studied one at a time, each as its own method with its own code and training setup, which makes them hard to combine or adapt to a new model. We present~\ours to bring all three under one simple abstraction: a single object names any size the model can run at, and a short schedule lists the sizes to train. Training then produces one checkpoint that serves all of those sizes, and at deployment the user picks any of them. The same abstraction covers both retrievers and rerankers and both encoder and decoder models, as it works through interfaces that Hugging Face transformers already expose; a new backbone is a configuration change, not new modeling code. Prior methods---Matryoshka embeddings, early exit, 2D~Matryoshka (e.g., Starbucks), and layerwise token compression---become special cases of our unified abstraction. The same interface also enables Matryoshka~LTC (MLTC), which jointly trains several token-compression ratios in one retriever checkpoint. To validate our framework, we train 20 checkpoints across three backbones and two tasks: the quality curves are smooth, one checkpoint costs little over a model trained for a single size, and a controlled study confirms the wallclock speedups. We release the framework and all checkpoints as a resource for building elastic retrieval systems.

cs.CL↗

arXiv2026

Fermionic Lattice Supersolidity in the Attractive Three-Color Fermi-Hubbard Model

The recent experimental realization of the half-filled three-color Fermi-Hubbard model on a square optical lattice provides a novel platform for exploring exotic states of matter beyond conventional SU(2) systems. In this Letter, we investigate the three-color Fermi-Hubbard model with color-dependent attractive interactions using determinant quantum Monte Carlo simulations. We find that, at quantum degenerate temperatures, a lattice Fermi supersolid state emerges from the interplay between a moderately-to-strongly interacting two-color subsystem and a weakly coupled third-color environment. This supersolid state, characterized by the coexistence of charge-density-wave and color-superfluid orders, is highly promising for experimental detection with current techniques. Our results demonstrate that the attractive three-color Fermi-Hubbard model on a square optical lattice offers an experimentally accessible system for exploring the supersolidity of ultracold lattice fermions, requiring only a simple lattice geometry and easily tunable onsite interactions.

cond-mat.str-el↗

arXiv2026

Noncommutative maximal differential transforms associated to averaging operators

In this paper, we establish the noncommutative maximal weak type $(1,1)$ and strong type $(p,p)$ estimates for the family of operators $(T_N)_N$, defined by $$T_Nf=\sum_{k=N_1}^{N_2}ν_{k}(M_{k}-\mathsf{E}_k)f,$$ where $M_k$ denotes the dyadic Hardy--Littlewood average operator, $\mathsf{E}_{k}$ is the conditional expectation with respect to the dyadic cubes of side-length $2^{-k}$, $N=(N_1,N_2)$ with $N_1<N_2$ and $(ν_{k})\in\ell_{\infty}$. The main novelty of our approach is the development of a noncommutative Cotlar-type inequality for non-smooth kernels, a result that is new even in classical harmonic analysis. As an application, we obtain the boundedness theory of the noncommutative maximal differential transforms for averaging operators.

math.FA↗

arXiv2026

MoCA: Multi-modal Cross-masked Autoencoder for Time Series in Digital Health

Wearable devices enable continuous multi-modal physiological and behavioral monitoring, yet analysis of these data streams faces fundamental challenges including the lack of gold-standard labels and incomplete sensor data. While self-supervised learning approaches have shown promise for addressing these issues, existing multi-modal extensions present opportunities to better leverage the rich temporal and cross-modal correlations inherent in simultaneously recorded wearable sensor data. We propose the Multi-modal Cross-masked Autoencoder (MoCA), a self-supervised learning framework that combines transformer architecture with masked autoencoder (MAE) methodology, using a principled cross-modality masking scheme that explicitly leverages correlation structures between sensor modalities. MoCA demonstrates strong performance boosts across reconstruction and downstream classification tasks on diverse benchmark datasets. We further establish theoretical guarantees by establishing a fundamental connection between multi-modal MAE loss and kernelized canonical correlation analysis through a Reproducing Kernel Hilbert Space framework, providing principled guidance for correlation-aware masking strategy design. Our approach offers a novel solution for leveraging unlabeled multi-modal wearable data while handling missing modalities, with broad applications across digital health domains.

stat.ML↗

arXiv2026

CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering

Reverse engineering (RE) is central to software security, particularly for cryptographic programs that handle sensitive data and are highly prone to vulnerabilities. It supports critical tasks such as vulnerability discovery and malware analysis. Despite its importance, RE remains labor-intensive and requires substantial expertise, making large language models (LLMs) a potential solution for automating the process. However, their capabilities for RE remain systematically underexplored. To address this gap, we study the cryptographic binary RE capabilities of LLMs and introduce CREBench, a benchmark comprising 432 challenges built from 48 standard cryptographic algorithms, 3 insecure crypto key usage scenarios, and 3 difficulty levels. Each challenge follows a Capture-the-Flag (CTF) RE challenge, requiring the model to analyze the underlying cryptographic logic and recover the correct input. We design an evaluation framework comprising four sub-tasks, from algorithm identification to correct flag recovery. We evaluate eight frontier LLMs on CREBench. GPT-5.4, the best-performing model, achieves 64.03 out of 100 and recovers the flag in 59\% of challenges. We also establish a strong human expert baseline of 92.19 points, showing that humans maintain an advantage in cryptographic RE tasks. Our code and dataset are available at https://github.com/wangyu-ovo/CREBench.

cs.CR↗

arXiv2026

Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders

Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT). However, when processing multilingual speech inputs, a single speech encoder shared across all languages suffers from the curse of multilinguality: languages at different resource levels compete for limited representation capacity, leading to strong high-resource performance but substantial degradation on low-resource speech. To address this problem and improve multilingual consistency, we propose MSRT, a novel framework built around a resource-aware Mixture of Speech Encoders (MoSE). MoSE uses an explicit language router to assign each utterance to an appropriate expert encoder. A frozen expert preserves high-resource language capabilities, while a trainable expert adapts to and specializes in medium- and low-resource languages. We further introduce a five-stage curriculum learning strategy that substantially reduces data dependence, requiring only 10 hours of paired S2TT data per language for effective alignment. We conduct extensive experiments on 45 languages, systematically evaluating all $45 \times 44$ translation directions. Our 4B-parameter model achieves state-of-the-art performance, outperforming substantially larger baselines. Empirical analyses show that MoSE improves high-, medium-, and low-resource languages simultaneously, with the largest gains on low-resource speech, thereby breaking the curse of multilinguality without compromising high-resource performance. To support future multilingual S2TT research, we release our code and models.

cs.CL↗

arXiv2026

Exact Model-Free Policy Iteration for Co-safe LTL Planning

This work studies model-free reinforcement learning for co-safe linear temporal logic (sc-LTL) objectives in finite Markov decision processes, which can be reduced to maximal reachability objectives via the standard product construction. For this problem, direct sample-based bootstrap methods (e.g., TD or Q-learning) may fail to converge to optimal policies due to the noncontractive nature and nonuniqueness of solutions to the Bellman equation. We develop a new two-step model-free reinforcement learning method that first uses a discounted surrogate to identify a clamp set that resolves this nonuniqueness, and then applies undiscounted policy evaluation and greedy policy improvement with guarantees of finding an optimal solution. We prove almost-sure convergence of the policy evaluation step and finite termination of the policy iteration algorithm at an optimal policy. These theoretical results are validated through numerical experiments on a stochastic grid world.

eess.SY↗

arXiv2026

Optimal Constrained sc-LTL Planning in MDPs via Switching Policies

We study the synthesis of optimal policies for planning problems on Markov decision processes with both objectives and safety constraints specified in co-safe linear temporal logic (sc-LTL). Our problems are inherently non-Markovian due to the complexity of the sc-LTL specification and may require policy randomization to balance the objective and constraint. We propose a novel approach that reduces the constrained sc-LTL planning problem to a constrained reachability problem on an extended model. We then show that a class of switching policies constructed from stationary policies for the individual sc-LTL specifications is sufficient for optimality for the constrained reachability problem. Our finding enables a tractable linear program to compute the optimal policy. A grid world case study demonstrates that our switching policies can achieve the optimal trade-off between the objective and the safety constraint and validates both optimality and tractability.

cs.RO↗

arXiv2026

VirtualCrime: Evaluating the Criminal Potential and Agentic Behaviors of Large Language Models via Sandbox Simulation

Large language models (LLMs) have shown strong capabilities in multi-step decision-making, and are increasingly integrated into real-world agentic applications. While existing safety evaluations focus on static interactions or refusal rates, it remains largely underexplored what level of threat these models pose once an adversary successfully assigns them a malicious role. To evaluate this agentic misuse risk, we propose VirtualCrime, a dynamic multi-agent sandbox framework that elicits and measures multi-step criminal behavior from LLMs. We design 40 diverse crime tasks within this framework, covering 11 realistic maps and 14 objectives such as theft, robbery, and kidnapping. We evaluate 8 strong LLMs and find that: (1) even with robust safety alignment, all evaluated models exhibit alarming agentic capabilities to generate and execute detailed multi-step criminal plans when placed in an adversarial red-teaming setting; (2) models frequently suffer from behavioral alignment failures, exhibiting a high propensity for over-harm by escalating to violent means far beyond what the task requires; (3) their most sophisticated criminal behaviors concentrate in social deception and team coordination rather than technical exploitation. Our work highlights a critical gap in current safety paradigms, emphasizing the urgent need for behavioral alignment in autonomous agent deployments.

cs.CR↗

arXiv2026

A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents

Research in artificial intelligence is shifting from model innovations and benchmark scores towards problem definition and rigorous real-world evaluation. As the field enters the "second half," the central challenge becomes real utility in long-horizon, dynamic, and user-dependent settings such as agentic coding, deep research, and computer use, where LLM-based agents face context explosion beyond fixed context windows and must continuously accumulate, manage, and selectively reuse information across extended interactions. Memory, with hundreds of papers released in 2025, therefore emerges as the critical solution to fill this utility gap. Beyond passive storage, memory is increasingly the substrate through which agents self-evolve: short-term memory gates which experiences are perceived and abstracted during execution, while long-term memory consolidates them into reusable knowledge and skills, forming the loop through which agents improve from their own experience. In this survey, we provide a unified view of foundation agent memory along three dimensions: memory substrate (internal parametric state and external retrieval-augmented stores), cognitive mechanism (sensory, working, episodic, semantic, and procedural), and memory subject (user-centric personalization and agent-centric experience). We then analyze how memory is operated under single- and multi-agent topologies and highlight learning policies over memory operations, showing how memory management itself is becoming a trainable capability spanning reinforcement-learned context curation, experience consolidation at decision time, and the emerging ecosystem of portable, shareable agent skills. Finally, we review evaluation benchmarks and metrics for memory utility, and outline open challenges and future directions.

cs.CL↗

arXiv2026

Accelerated quantum Monte Carlo simulations of the attractive Hubbard model on the kagome lattice

The recent discovery of several families of kagome materials and experimental realization of optical kagome lattices have stimulated growing numerical studies of interaction-driven correlated states on the kagome lattice. Among the available numerical approaches, determinant quantum Monte Carlo (DQMC) is a powerful method for investigating such strongly correlated states. However, the accessible system sizes of existing DQMC simulations remain limited, preventing reliable finite-size scaling analyses. Here we develop a general acceleration scheme based on fast Fourier transform (FFT) for propagator multiplications on composite lattices and combine it with the delay-update algorithm, enabling simulations on system sizes twice as large as those of previous DQMC studies, allowing reliable finite-size scaling analyses of the attractive kagome-lattice Hubbard model. Our large-scale simulations reveal the interaction-driven zero-temperature superfluid quantum criticality at the Dirac filling and provide reliable estimates of the associated critical exponents. Besides, we find no evidence that the previously proposed triangle-rule charge-density-wave order survives in the thermodynamic limit, suggesting that it is likely a finite-size effect. Moreover, for system sizes accessible in current two-dimensional optical lattice experiments, the combined FFT and delay-update scheme exhibits an effective computational cost scaling as $N^{2.49}$, substantially below the $\mathcal{O}(N^3)$ computational cost of conventional DQMC simulations.

cond-mat.str-el↗

arXiv2026

Machine Learning-Guided Screening of Advantageous Solvents for Solid Polymer Electrolytes in Lithium Metal Batteries

Trace residual solvents in solid polymer electrolytes (SPEs) significantly affect electrolyte and interface properties, where optimal selection enhances ionic conductivity and transference numbers. However, solvent complexity hinders general screening methods. We establish a universal criterion linking electronic (HOMO, LUMO) and macroscopic properties (dielectric constant, dipole moment, polarizability) via machine learning on an approximately 10,000-solvent dataset from high-throughput DFT. Two solvents, N-methoxy-N-methyl-2,2,2-trifluoroacetamide and 2,2,2-trifluoro-N,N-dimethylacetamide, were identified. Experimental incorporation of trace N-methoxy-N-methyl-2,2,2-trifluoroacetamide into a poly(vinylidene fluoride-co-hexafluoropropylene) matrix achieves a 4.5 V window, 5.5x10^-4 S cm^-1 conductivity (30 C), and 0.78 Li+ transference number. The cell retains 86.7% capacity over 500 cycles (LiFePO4) and 98.7% after 200 cycles at 2C (LiNi0.9Co0.05Mn0.05O2), outperforming 2,2,2-trifluoro-N,N-dimethylacetamide, dimethylformamide, N-methyl-2-pyrrolidone, and dimethyl sulfoxide. This synergy enables balanced ion transport, wide stability, and cycling durability, advancing safer, high-energy lithium metal batteries. Our integrated approach establishes a solvent screening paradigm for rational SPE design, accelerating next-generation battery development.

cond-mat.mtrl-sci↗