Search arXiv⌕ Search

arXiv subjects

Yang Yu

Publications and source records attributed to Yang Yu.

At least 55 records · Page 3Linked to original sources
arXiv2026

MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources

Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented large language models (LLMs). Existing approaches typically rely on large-scale supervised datasets, costly reasoning annotations, and expensive intermediate step verification, resulting in substantial training overhead. To address these challenges, we propose MiniOpt, a reinforcement learning framework that learns to solve optimization problems through an "reasoning-to-model-and-solve" paradigm. MiniOpt decomposes optimization reasoning into structured optimization modeling and executable solver generation. Building upon this paradigm, we introduce OptReward, a reward function with hierarchical score structure that jointly evaluates formulation and solution, enabling effective policy learning without expert demonstrations. We further develop an optimization-oriented policy optimization strategy that improves exploration efficiency and stabilizes reinforcement learning for compact models. Extensive experiments show that MiniOpt-3B exhibits strong optimization generalization across various optimization types, problem scenarios, and task domains. For models with fewer than 10B parameters, MiniOpt series achieves the highest average solving accuracy (SA). For models with more than 10B parameters, MiniOpt still shows competitive performance. These results suggest that optimization-oriented reward design and reinforcement learning provide an effective pathway for developing compact optimization-specialized language models with strong optimization generalization capabilities. The code is available at https://github.com/Hsiang-1/MiniOpt.

cs.LG↗
arXiv2026

Offline Multi-agent Continual Cooperation via Skill Partition and Reuse

Extracting skills from multi-agent offline dataset improves learning efficiency via sharing task-invariant coordination skills among tasks. In settings where tasks occur sequentially and the space of skills grows exponentially, existing approaches that rely on heuristically designed and fixed-sized skill libraries struggle to resolve the problem of distributional shift and interference, facing catastrophic forgetting and plasticity loss. To address this problem and endow agents with the ability to continually discover and reuse coordination skills in open-environment, we propose COMAD, a principled framework for Continual Offline Multi-agent Skill Discovery via Skill Partition and Reuse. We first discover skills from mixed multi-agent behavior data with an auto-encoder to transform coordination knowledge into reusable coordination skills. Then we construct a skill-augmented policy learning objective with multi-head architectures, explicitly guiding the advantage function with reusable skills identified via a density-based reusability estimator. Theoretical analysis shows our method approximates the optimum of a continual skill discovery problem. Empirical results across diverse MARL benchmarks show that COMAD continually expands its skill library to mitigate interference, achieving superior forward and backward transfer for task streams compared to multiple baselines.

cs.AI↗
arXiv2026

Efficient Multimodal Clinical Question Answering for Pulmonary Embolism Risk Assessment

Pulmonary embolism (PE) is a high risk cardiopulmonary condition whose management requires both timely diagnosis and reliable assessment of future clinical risk. Because PE care routinely combines computed tomography pulmonary angiography (CTPA), radiology interpretation, and longitudinal electronic health record (EHR) evidence, it provides a clinically meaningful setting for evaluating compact multimodal language models. In this work, we build a benchmark using efficient multimodal large language models (MLLMs) on INSPECT, a multimodal PE dataset containing 23,248 CTPA studies from 19,402 patients. We formulate eight diagnostic and prognostic tasks as structured clinical question answering problems and evaluate on typical efficient MLLMs under CTPA-Only, EHR-Only, and CTPA+EHR settings with zero-shot and few-shot prompting. Results show that Gemma4 E4B and Gemma4 E2B perform more strongly when EHR evidence is available, especially under CTPA+EHR input. Task level analysis further shows that PE diagnosis achieves higher performance than prognostic tasks, particularly readmission prediction. These observations suggest that compact multimodal models have the great potential in early stage PE risk detection and explanation.

cs.AI↗
arXiv2026

Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Value Flow Mechanism

Adversarial imitation learning (AIL) achieves high-quality imitation by mitigating compounding errors inherent to behavioral cloning (BC), yet its adversarial optimization frequently leads to training instability. A class of non-adversarial Q-based imitation learning (IL) methods, exemplified by IQ-Learn, has emerged to address this instability and is widely believed to outperform BC by leveraging online environment interactions. In this paper, we revisit IQ-Learn and prove that it in fact reduces to BC: it admits an imitation gap lower bound with quadratic dependence on the horizon and therefore remains susceptible to compounding errors. Our theoretical analysis reveals why online interactions fail to help: IQ-Learn uniformly suppresses Q-values for all actions at states not covered by demonstrations, preventing generalization beyond demonstrations. To address this fundamental limitation, we introduce Dual Q-DM, a new Q-based IL method built on Bellman constraints. Crucially, Bellman constraints drive value flow: Q-values propagate from demonstrated to unvisited states through environment dynamics, enabling generalization beyond demonstrations. We prove that Dual Q-DM is equivalent to AIL and can recover expert actions at unvisited states, thereby mitigating compounding errors. To the best of our knowledge, Dual Q-DM is the first non-adversarial IL method that is theoretically guaranteed to eliminate compounding errors. Experimental results further corroborate our theoretical findings.

cs.LG↗
arXiv2026

Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning

Adversarial imitation learning (AIL) achieves high-quality imitation compared to behavioral cloning (BC), but demands substantial online environment interaction. Recent empirical work has explored initializing AIL algorithms with BC pretrained policies to address this limitation, yet a rigorous theoretical understanding of pretraining's role in AIL remains elusive. This paper provides a systematic theoretical analysis and introduces principled pretraining algorithms for accelerating AIL. We begin by analyzing AIL with policy pretraining alone, identifying reward error as the dominant source of suboptimality. This reveals a critical and previously overlooked gap: the absence of reward pretraining. Motivated by this finding, we develop a principled policy-reward co-pretraining approach grounded in a reward shaping analysis. Our analysis uncovers a fundamental connection between expert policies and shaping rewards, which naturally gives rise to CoPT-AIL, an approach that jointly pretrains both policy and reward through a single BC procedure. We prove that CoPT-AIL achieves an improved imitation gap bound over standard AIL, establishing the first theoretical guarantee for the benefits of pretraining in AIL. Experimental results confirm CoPT-AIL's superior performance over existing AIL methods.

cs.LG↗
arXiv2026

Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization

Protein language models (PLMs) have emerged as powerful tools for controllable biomolecular design, yet their post-training adaptation typically relies on costly wet-lab validation or curated preference datasets. To overcome this supervision bottleneck, we introduce unsupervised reward optimization of PLMs, a comprehensive framework for steerable protein generation without ground-truth labels. Our key insight is that task-agnostic rewards, which combine intrinsic model uncertainty with extrinsic semantic consistency informed by protein representation models, exhibit strong correlation with controllability measures across base models and temperature regimes. Building upon this discovery, we propose two offline algorithms: Soft Reward Optimization (SRO) and Binarized Reward Optimization (BRO), which effectively maximize the classical RLHF objective induced by these proxy rewards. Extensive experiments on compositional out-of-distribution prompts demonstrate that both methods significantly outperform competitive baselines (DPO, KTO), while approaching oracle performance across multiple sampling temperatures, model scales and protein families. Moreover, PLMs fine-tuned with unsupervised rewards can achieve consistently higher coverage compared to their base model in pass@k evaluations. By enabling self-improvement of PLMs through their own generated experience, our framework provides a scalable pathway toward controllable biomolecular design in settings where labeled preferences or experimental feedback are scarce or unavailable.

cs.LG↗
arXiv2026

Planning with Unified Multimodal Models

With the powerful reasoning capabilities of large language models (LLMs) and vision-language models (VLMs), many recent works have explored using them for decision-making. However, most of these approaches rely solely on language-based reasoning, which limits their ability to reason and make informed decisions. Recently, a promising new direction has emerged with unified multimodal models (UMMs), which support both multimodal inputs and outputs. We believe such models have greater potential for decision-making by enabling reasoning through generated visual content. To this end, we propose Uni-Plan, a planning framework built on UMMs. Within this framework, a single model simultaneously serves as the policy, dynamics model, and value function. In addition, to avoid hallucinations in dynamics predictions, we present a novel approach self-discriminated filtering, where the generative model serves as a self-discriminator to filter out invalid dynamics predictions. Experiments on embodied decision-making tasks show that Uni-Plan substantially improves success rates compared to VLM-based methods, while also showing strong data scalability, requiring no expert demonstrations and achieving better performance under the same training-data size. This work lays a foundation for future research in reasoning and decision-making with UMMs.

cs.CV↗
arXiv2026

Efficient Implementation of a Single-Qutrit Gate Set via Coherent Control

Qutrits offer the potential for enhanced quantum computation by exploiting an enlarged Hilbert space. However, the synthesis of high-fidelity and fast qutrit gates, particularly for single qutrits, remains an ongoing challenge, as it involves overcoming intrinsic constraints in quantum platforms. Here, we develop a novel framework for the efficient implementation of a single-qutrit gate set via coherent control, leveraging SU(3) dynamics while obviating platform-specific constraints such as those arising from the selection rule. As a proof-of-principle demonstration, we realize 35-ns qutrit Hadamard and X gates using a superconducting transmon, achieving an average fidelity of 99.5\%, as verified by randomized benchmarking. We further demonstrate two paradigmatic quantum circuits, which can be naturally extended to scalable qudit algorithms for phase estimation and parity check. In addition, we propose an SU(3)-based decomposition strategy for an arbitrary single-qutrit gate and numerically demonstrate its substantial efficiency improvement over conventional SU(2)-based protocols. By addressing the challenge of efficiently implementing single-qutrit gates, our protocol paves the way for realizing high-performance qutrit processors in diverse quantum platforms.

quant-ph↗
arXiv2026

Continual Quadruped Robots Coordination via Semantic Skill Discovery

Multi-quadruped coordination has attracted increasing attention due to its enhanced payload capacity, broader contact coverage, and improved adaptability to challenging tasks. Existing methods for multi-quadruped manipulation typically focus on predefined or closed task families, often relying on multi-agent reinforcement learning (MARL) to train task-specific coordination policies. However, such methods struggle in open-ended continual learning settings, where tasks arrive sequentially and robots are expected to acquire new coordination skills while reusing previously learned ones without catastrophic forgetting. To address this challenge, we propose Conquer, a semantic skill-library framework that formulates continual multi-quadruped coordination as a retrieve-adapt-update process. First, to accommodate varying team sizes across tasks, we design a team-structured Self-Allies-Goal (SAG) backbone that supports variable-cardinality robot teams by explicitly modeling each robot's own state, teammate context, and task goal. For each incoming task, Conquer constructs a task-level semantic descriptor from pre-execution information and retrieves a relevant skill from the library for adaptation. After successful execution, Conquer updates the skill library by extracting trajectory-level semantic descriptors and organizing them according to semantic distance, thereby enabling continual skill accumulation and cross-task knowledge transfer. Simulation experiments show that Conquer achieves a final average success rate of 95.6%, demonstrating strong forward transfer and negligible catastrophic forgetting. Real-world rollouts on Unitree Go2 teams further validate the deployment feasibility of Conquer for practical multi-quadruped coordination. Simulation and real-robot demonstration videos are available at: https://conquer-project.pages.dev/.

cs.RO↗
arXiv2026

Hybrid Hamiltonian-diagrammatic quantum impurity solver

Quantum impurity models, which describe the coupling between interacting orbitals and a non-interacting bath, play a central role in the physics of strongly correlated electron systems. Solving a quantum impurity model in general requires the use of non-perturbative numerical methods. Hamiltonian-based approaches, which rely on an explicit bath discretization, are typically limited to a small number of bath sites or small entanglement, and diagrammatic methods suffer from sign problems, slow convergence, or diagram truncation approximations. Here we show that these two classes of methods can be combined: augmenting diagrammatic methods with a small auxiliary bath can reduce the residual problem to a regime where low-order perturbation theory is highly accurate and rapidly converging. In a simple benchmark, the precision of the hybrid approach surpasses bold-line calculations by several orders of magnitude; for a strongly interacting two-orbital model with a severe sign problem, convergence is achieved at three orders of magnitude lower computational cost than competing methods; and convergence to the unknown exact result is rapidly accelerated in a difficult realistic problem. Our results establish a practical route to high-precision quantum impurity solutions in correlated quantum systems.

cond-mat.str-el↗
arXiv2026

Autonomous Aerial Manipulation via Contextual Contrastive Meta Reinforcement Learning

Unmanned aerial vehicles (UAVs) are increasingly being deployed in logistics, service robotics, and other real-world applications, creating a growing demand for autonomous payload acquisition and delivery. Existing approaches typically assume pre-attached payloads or rely on specialized grippers, leaving versatile end-to-end aerial delivery largely unresolved, where different payloads induce highly variable flight dynamics, requiring a single policy to adapt online without manual calibration or explicit system identification. To this end, we study \textbf{A}utonomous \textbf{A}erial Manipulation via \textbf{Co}ntextual \textbf{Co}ntrastive Meta Reinforcement Learning (\textbf{\textit{Aco2}}), a fully autonomous aerial delivery setting in which a quadrotor equipped with a lightweight hook continuously picks up, transports, and delivers diverse handle-equipped objects between randomized locations, all without human intervention. First, we design a contextual observation encoder that infers a compact latent context from recent interaction history, enabling the policy to adapt online to payload-dependent dynamics. To further improve the quality of this context, we introduce a contrastive objective that structures the context embedding around task-relevant variations, improving generalization across diverse payloads without requiring explicit system identification. Trained entirely in simulation with extensive domain randomization, \textit{Aco2} can be directly deployed on a physical quadrotor without real-world fine-tuning.

cs.LG↗
arXiv2026

Towards Automated Kernel Generation in the Era of LLMs

The performance of modern AI systems is fundamentally constrained by the quality of their underlying GPU kernels, which translate high-level algorithmic semantics into low-level hardware operations. Achieving near-optimal kernels requires expert-level understanding of hardware architectures and programming models, making kernel engineering a critical but notoriously time-consuming and non-scalable process. Recent advances in large language models and LLM-based agents have opened new possibilities for automating kernel generation and optimization. LLMs are well-suited to compress expert-level kernel knowledge that is difficult to formalize, while agentic systems further enable scalable optimization by casting kernel development as an iterative, feedback-driven loop. Rapid progress has been made in this area. However, the field remains fragmented and lacks a systematic perspective for LLM-driven kernel generation. This survey addresses this gap by providing a structured overview of existing approaches, spanning LLM-based approaches and agentic optimization workflows, and systematically organizing the datasets and benchmarks that underpin learning and evaluation in this domain. Moreover, key open challenges and future research directions are further outlined, aiming to establish a comprehensive reference for the next generation of automated kernel optimization. To keep track of this field, we maintain an open-source GitHub repository at https://github.com/flagos-ai/awesome-LLM-driven-kernel-generation.

cs.LG↗
arXiv2026

Cooperative Long Rope Skipping via Multi-Agent Reinforcement Learning

Humans exhibit remarkable motor agility, enabling a wide range of dynamic skills such as running and jumping, which highlights the great potential of humanoid robots for athletic locomotion. Among athletic sports, long rope skipping requires two rope turners to cooperatively swing the rope while adapting to a player under different jumping rhythms, making it a meaningful yet challenging task for humanoid robots. Although existing methods for humanoid sports have achieved success in single-agent and interaction-free settings, such as running, dancing, and parkour, task scenarios that require precise coordination among multiple participants remain largely unexplored. To this end, we propose Marope, a multi-agent reinforcement learning (MARL) framework for cooperative long rope skipping with multiple humanoid robots. Specifically, Marope adopts a hierarchical reinforcement learning framework for policy training. At the lower level, it learns decentralized rope manipulation policies through MARL, while at the upper level, a centralized scheduling policy is trained to coordinate the execution of the lower-level policies. To improve generalization across different player behavioral styles, Marope further incorporates diverse jumping policies into cooperative game training. We evaluate our approach on Unitree G1 humanoid robots in both simulation and real-world settings. Experimental results demonstrate that Marope outperforms various baselines, achieving more efficient and stable rope manipulation as well as more robust and adaptable cooperation with varied players.

cs.RO↗
arXiv2026

Money Burning Improves Mediated Communication

Can wasteful money burning improve strategic communication? We show that it can, but only with intermediate commitment. In mediated communication with report-contingent burning, the mediator can use costly messages to discipline deviations and make persuasive messages credible. Under transparent motives, increasing the burning budget strictly raises the Sender's payoff once the budget is large enough, unless mediated communication with money burning collapses to cheap talk. With an unbounded budget, the value equals a robust Bayesian persuasion payoff, or equivalently the payoff of a cautious Sender. The framework clarifies commitment through smart contracts and Web 3.0 mediation.

econ.TH↗
arXiv2026

Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention

Recently, reinforcement learning (RL) has become a common choice in enhancing the reasoning capabilities of vision-language models (VLMs). Considering existing RL-based finetuning methods, entropy intervention turns out to be an effective way to benefit exploratory ability, thereby improving policy performance. Notably, most existing studies intervene in entropy by simply controlling the update of specific tokens during policy optimization of RL. They ignore the entropy intervention during the RL sampling that can boost the performance of GRPO by improving the diversity of responses. In this paper, we propose Selective-adversarial Entropy Intervention, namely SaEI, which enhances policy entropy by distorting the visual input with the token-selective adversarial objective coming from the entropy of sampled responses. Specifically, we first propose entropy-guided adversarial sampling (EgAS) that formulates the entropy of sampled responses as an adversarial objective. Then, the corresponding adversarial gradient can be used to attack the visual input for producing adversarial samples, allowing the policy model to explore a larger answer space during RL sampling. Then, we propose token-selective entropy computation (TsEC) to maximize the effectiveness of adversarial attack in EgAS without distorting factual knowledge within VLMs. Extensive experiments on both in-domain and out-of-domain datasets show that our proposed method can greatly improve policy exploration via entropy intervention, to boost reasoning capabilities. Code will be released once the paper is accepted.

cs.AI↗
arXiv2026

LEARNT: A Practical Estimator for Cardinality of LIKE Queries with Formal Accuracy Guarantees

We study the problem of cardinality estimation for LIKE queries on string data, focusing on the most common patterns in real workloads: prefix, suffix, and substring queries. We propose LEARNT, a LIKE query Estimator with Accuracy, Robustness, Negligible overhead, Tunability, and Theoretical guarantees. LEARNT formulates estimation as a bucket-classification problem, and upon correct classification, it yields formal bounds on Q-error for the queries with non-empty answer. It employs a memory-efficient bucketed layered-filter architecture with Bloom filters and compact auxiliary tables, together with optimizations that exploit query skew to reduce storage. For the queries that have empty answer, LEARNT incorporates dedicated filter-based and prefix-walk strategies, providing probabilistic guarantees on correct identification. Furthermore, to support arbitrarily long query strings, we extend LEARNT with Markov modeling scheme that composes short-query statistics into estimates for longer queries. A theoretical framework guides parameter selection to minimize storage under accuracy and robustness constraints. Extensive experiments on four real-world datasets show that LEARNT consistently outperforms state-of-the-art methods such as CLIQUE and LPLM, achieving 1.3-1.7x lower mean Q-error, significantly lower tail errors, and up to 70x faster construction with comparable memory usage.

cs.DB↗
arXiv2026

Probing Tensor Singularities and Their Euler-Class Descendants via Non-Abelian Quantum Geometry Measurement

We report the theoretical prediction and experimental observation of a new class of four-dimensional (4D) tensor singularities and their three-dimensional (3D) Euler-class descendants, protected by chiral and spacetime inversion symmetries on a superconducting circuit platform. The 4D point-like singularity/monopole, characterized by the Dixmier-Douady class of a real bundle gerbe associated with tensor gauge fields, is observed to evolve into a nodal ring carrying an additional first Euler class charge under symmetry-preserving perturbations. Dimensional reduction reveals 3D Euler and Euler curvature dipoles, exhibiting nontrivial Euler topology and a topological sum rule that ensures zero-energy flat bands inherit nontrivial topology even without interactions. Crucially, these high-dimensional degenerate systems are mapped and reconstructed using a hybrid analog-digital protocol designed for non-Abelian quantum geometry measurement within a superconducting qubit array. Our work not only expands the family of topological monopoles but also establishes a robust experimental framework for exploring high-order gauge theory and real-bundle topology across diverse quantum platforms.

quant-ph↗