arXiv subjects

Haiyan Yin

Publications and source records attributed to Haiyan Yin.

At least 19 recordsLinked to original sources

arXiv2026

LTLDiff: Finite Linear Temporal Logic-Guided Data Generation and Diffusion Policies for Multi-agent Robotic Manipulation

Multi-agent robotic manipulation tasks require coordination among agents to satisfy task-level temporal, logical, and safety constraints. Recently, diffusion policies have been used to perform the task. However, they still suffer from desynchronization, incorrect action ordering, and coordination failures in tasks that require simultaneous or sequential multi-agent interaction. Therefore, LTLDiff is proposed as a framework that combines Finite Linear Temporal Logic (LTLf) specification learning for both the generation of demonstrations and learning via diffusion policies. Each task has a specific LTLf formula that is learned from a set of natural language instructions using a large-scale language model. To enable a fixed-dimensional vector embedding of the learned specification from the language model, LTLf uses an abstract syntax tree representation scheme. This embedding of logic serves as a condition for (i) logic-guided data collection and (ii) diffusion-based policy training, encouraging trajectories that are consistent with the desired ordering and coordination requirements. Experiments on multi-agent LTLDiff manipulation tasks demonstrate improved task success rates compared to the baseline. Together, these contributions demonstrate the effectiveness of LTLDiff for coordinated multi-agent manipulation.

cs.RO↗

arXiv2026

Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs

Understanding and reasoning about the physical world is the foundation of intelligent behavior, yet state-of-the-art vision-language models (VLMs) still fail at causal physical reasoning, often producing plausible but incorrect answers. To address this gap, we introduce CausalPhys, a benchmark of over 3,000 carefully curated video- and image-based questions spanning four domains: Perception, Anticipation, Intervention, and Goal Orientation. Each question is paired with an expert-annotated causal graph capturing object-attribute-event dependencies, enabling interpretable and fine-grained evaluation of causal understanding. Building on this, we formulate a causal-graph-grounded metric that quantitatively measures how well a model's chain-of-thought reasoning aligns with the correct causal relations, moving beyond answer-only accuracy and enabling systematic diagnosis of VLMs' causal reasoning failures. Using this metric, we conduct a comprehensive analysis of leading VLMs, revealing systematic gaps in capturing causal dependencies and underscoring the need for causality-aware learning. To address these limitations, we further propose Causal Rationale-informed Fine-Tuning (CRFT), which explicitly aligns VLM reasoning with causal structures. Extensive experiments demonstrate that CRFT substantially enhances both reasoning accuracy and interpretability across multiple model backbones. By unifying dataset curation, causal evaluation, and causality-informed learning, CausalPhys establishes a strong foundation for advancing modern VLMs toward causally grounded physical reasoning.

cs.DB↗

arXiv2026

Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks

Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing skill induction methods mitigate this by distilling experience into state-blind parameterized scripts, they fail to capture the conditional logic required for robust execution in dynamic environments. In this paper, we propose Neuro-Symbolic Skill Induction (NSI), a framework that lifts interaction traces into modular, \textit{logic-grounded} programs. By synthesizing explicit control flows and dynamic variable binding, NSI empowers agents to discover \textit{when} and \textit{why} to act. This paradigm enables the efficient generalization, allowing agents to induce skills from few-shot examples and flexibly adapt to unseen goals. Experiments on a series of agentic tasks demonstrate that NSI consistently outperforms state-of-the-art baselines, empowering agents to self-evolve into architects of logic-grounded skills.

cs.AI↗

arXiv2026

ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling

Sparse Mixture-of-Experts (MoE) models can outperform dense large language models at similar computation by activating only a small set of experts per token. However, stacking many expert modules introduces substantial parameter memory, which makes MoE models difficult to deploy in memory-constrained environments such as single-GPU devices. Offloading alleviates this issue by storing inactive experts in CPU memory and loading them on demand, but existing methods remain limited: static caches disregard input-dependent routing, and methods that train separate models to predict expert usage ahead of time are often inaccurate or require significant training cost. We propose ExpertFlow, a lightweight MoE inference system that addresses this routing dependency through three coordinated components: 1) a transformer-based routing path predictor that estimates expert usage across all MoE layers in a single forward pass, 2) a token scheduler that groups tokens with similar predicted routes to improve expert utilization, and 3) a predictive expert cache that loads only the required experts while correcting mispredictions at runtime. Together, these components enable efficient expert loading and execution, reducing GPU memory usage by up to 93.72% and improving inference throughput by up to 10x over strong offloading baselines on a single GPU.

cs.AI↗

arXiv2026

Aligning LLMs with Graph Neural Solvers for Combinatorial Optimization

Recent research has demonstrated the effectiveness of large language models (LLMs) in solving combinatorial optimization problems (COPs) by representing tasks and instances in natural language. However, purely language-based approaches struggle to accurately capture complex relational structures inherent in many COPs, rendering them less effective at addressing medium-sized or larger instances. To address these limitations, we propose AlignOPT, a novel approach that aligns LLMs with graph neural solvers to learn a more generalizable neural COP heuristic. Specifically, AlignOPT leverages the semantic understanding capabilities of LLMs to encode textual descriptions of COPs and their instances, while concurrently exploiting graph neural solvers to explicitly model the underlying graph structures of COP instances. Our approach facilitates a robust integration and alignment between linguistic semantics and structural representations, enabling more accurate and scalable COP solutions. Experimental results demonstrate that AlignOPT achieves state-of-the-art results across diverse COPs, underscoring its effectiveness in aligning semantic and structural representations. In particular, AlignOPT demonstrates strong generalization, effectively extending to previously unseen COP instances.

cs.AI↗

arXiv2026

Bridging Synthetic and Real Routing Problems via LLM-Guided Instance Generation and Progressive Adaptation

Recent advances in Neural Combinatorial Optimization (NCO) methods have significantly improved the capability of neural solvers to handle synthetic routing instances. Nonetheless, existing neural solvers typically struggle to generalize effectively from synthetic, uniformly-distributed training data to real-world VRP scenarios, including widely recognized benchmark instances from TSPLib and CVRPLib. To bridge this generalization gap, we present Evolutionary Realistic Instance Synthesis (EvoReal), which leverages an evolutionary module guided by large language models (LLMs) to generate synthetic instances characterized by diverse and realistic structural patterns. Specifically, the evolutionary module produces synthetic instances whose structural attributes statistically mimics those observed in authentic real-world instances. Subsequently, pre-trained NCO models are progressively refined, firstly aligning them with these structurally enriched synthetic distributions and then further adapting them through direct fine-tuning on actual benchmark instances. Extensive experimental evaluations demonstrate that EvoReal markedly improves the generalization capabilities of state-of-the-art neural solvers, yielding a notable reduced performance gap compared to the optimal solutions on the TSPLib (1.05%) and CVRPLib (2.71%) benchmarks across a broad spectrum of problem scales.

cs.AI↗

arXiv2025

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals

Large Language Models (LLMs), when paired with prompt-based tasks, have significantly reduced data annotation costs and reliance on human annotators. However, evaluating the quality of their annotations remains challenging in dynamic, unsupervised environments where oracle feedback is scarce and conventional methods fail. To address this challenge, we propose a novel agentic annotation paradigm, where a student model collaborates with a noisy teacher (the LLM) to assess and refine annotation quality without relying on oracle feedback. The student model, acting as an unsupervised feedback mechanism, employs a user preference-based majority voting strategy to evaluate the consistency of the LLM outputs. To systematically measure the reliability of LLM-generated annotations, we introduce the Consistent and Inconsistent (CAI) Ratio, a novel unsupervised evaluation metric. The CAI Ratio not only quantifies the annotation quality of the noisy teacher under limited user preferences but also plays a critical role in model selection, enabling the identification of robust LLMs in dynamic, unsupervised environments. Applied to ten open-domain NLP datasets across four LLMs, the CAI Ratio demonstrates a strong positive correlation with LLM accuracy, establishing it as an essential tool for unsupervised evaluation and model selection in real-world settings.

cs.CL↗

arXiv2025

MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming

Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven construction. We introduce MermaidFlow, a framework that redefines the agentic search space through safety-constrained graph evolution. At its core, MermaidFlow represent workflows as a verifiable intermediate representation using Mermaid, a structured and human-interpretable graph language. We formulate domain-aware evolutionary operators, i.e., crossover, mutation, insertion, and deletion, to preserve semantic correctness while promoting structural diversity, enabling efficient exploration of a high-quality, statically verifiable workflow space. Without modifying task settings or evaluation protocols, MermaidFlow achieves consistent improvements in success rates and faster convergence to executable plans on the agent reasoning benchmark. The experimental results demonstrate that safety-constrained graph evolution offers a scalable, modular foundation for robust and interpretable agentic reasoning systems.

cs.LG↗

arXiv2025

Mastering Continual Reinforcement Learning through Fine-Grained Sparse Network Allocation and Dormant Neuron Exploration

Continual Reinforcement Learning (CRL) is essential for developing agents that can learn, adapt, and accumulate knowledge over time. However, a fundamental challenge persists as agents must strike a delicate balance between plasticity, which enables rapid skill acquisition, and stability, which ensures long-term knowledge retention while preventing catastrophic forgetting. In this paper, we introduce SSDE, a novel structure-based approach that enhances plasticity through a fine-grained allocation strategy with Structured Sparsity and Dormant-guided Exploration. SSDE decomposes the parameter space into forward-transfer (frozen) parameters and task-specific (trainable) parameters. Crucially, these parameters are allocated by an efficient co-allocation scheme under sparse coding, ensuring sufficient trainable capacity for new tasks while promoting efficient forward transfer through frozen parameters. However, structure-based methods often suffer from rigidity due to the accumulation of non-trainable parameters, limiting exploration and adaptability. To address this, we further introduce a sensitivity-guided neuron reactivation mechanism that systematically identifies and resets dormant neurons, which exhibit minimal influence in the sparse policy network during inference. This approach effectively enhance exploration while preserving structural efficiency. Extensive experiments on the CW10-v1 Continual World benchmark demonstrate that SSDE achieves state-of-the-art performance, reaching a success rate of 95%, surpassing prior methods significantly in both plasticity and stability trade-offs (code is available at: https://github.com/chengqiArchy/SSDE).

cs.LG↗

arXiv2024

The stability of sheath to the nonisentropic Euler-Poisson system with fluid-boundary interaction

In the present paper, we define the sheath by a monotone stationary solution to the nonisentropic Euler-Poisson system under a condition known as the Bohm criterion and consider a situation in which charged particles accumulate on the boundary due to the flux from the inner region. Under this fluid-boundary interactive setting, we prove the large time asymptotic stability of the sheath provided that the initial perturbation is sufficiently small in some weighted Sobolev spaces. Moreover, the convergence rate of the solution toward the sheath is obtained. The proof is based on the weighted energy method.

math.AP↗

arXiv2023

CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration

We study the problem of model-free reinforcement learning, which is often solved following the principle of Generalized Policy Iteration (GPI). While GPI is typically an interplay between policy evaluation and policy improvement, most conventional model-free methods assume the independence of the granularity and other details of the GPI steps, despite of the inherent connections between them. In this paper, we present a method that regularizes the inconsistency between policy evaluation and policy improvement, leading to a conflict averse GPI solution with reduced functional approximation error. To this end, we formulate a novel learning paradigm where taking the policy evaluation step is equivalent to some compensation of performing policy improvement, and thus effectively alleviates the gradient conflict between the two GPI steps. We also show that the form of our proposed solution is equivalent to performing entropy-regularized policy improvement and therefore prevents the policy from being trapped into suboptimal solutions. We conduct extensive experiments to evaluate our method on the Arcade Learning Environment (ALE). Empirical results show that our method outperforms several strong baselines in major evaluation domains.

cs.LG↗

arXiv2022

Crowd-level Abnormal Behavior Detection via Multi-scale Motion Consistency Learning

Detecting abnormal crowd motion emerging from complex interactions of individuals is paramount to ensure the safety of crowds. Crowd-level abnormal behaviors (CABs), e.g., counter flow and crowd turbulence, are proven to be the crucial causes of many crowd disasters. In the recent decade, video anomaly detection (VAD) techniques have achieved remarkable success in detecting individual-level abnormal behaviors (e.g., sudden running, fighting and stealing), but research on VAD for CABs is rather limited. Unlike individual-level anomaly, CABs usually do not exhibit salient difference from the normal behaviors when observed locally, and the scale of CABs could vary from one scenario to another. In this paper, we present a systematic study to tackle the important problem of VAD for CABs with a novel crowd motion learning framework, multi-scale motion consistency network (MSMC-Net). MSMC-Net first captures the spatial and temporal crowd motion consistency information in a graph representation. Then, it simultaneously trains multiple feature graphs constructed at different scales to capture rich crowd patterns. An attention network is used to adaptively fuse the multi-scale features for better CAB detection. For the empirical study, we consider three large-scale crowd event datasets, UMN, Hajj and Love Parade. Experimental results show that MSMC-Net could substantially improve the state-of-the-art performance on all the datasets.

cs.CV↗

arXiv2020

A half-space problem on the full Euler-Poisson system

This paper is concerned with the initial-boundary value problem on the full Euler-Poisson system for ions over a half line. We establish the existence of stationary solutions under the Bohm criterion similar to the isentropic case and further obtain the large time asymptotic stability of small-amplitude stationary solutions provided that the initial perturbation is sufficiently small in some weighted Sobolev spaces. Moreover, the convergence rate of the solution toward the stationary solution is obtained. The proof is based on the energy method. A key point is to capture the positivity of the temporal energy dissipation functional and boundary terms with suitable space weight functions either algebraic or exponential depending on whether or not the incoming far-field velocity is critical.

math.AP↗

arXiv2020

Reinforcement Learning with Efficient Active Feature Acquisition

Solving real-life sequential decision making problems under partial observability involves an exploration-exploitation problem. To be successful, an agent needs to efficiently gather valuable information about the state of the world for making rewarding decisions. However, in real-life, acquiring valuable information is often highly costly, e.g., in the medical domain, information acquisition might correspond to performing a medical test on a patient. This poses a significant challenge for the agent to perform optimally for the task while reducing the cost for information acquisition. In this paper, we propose a model-based reinforcement learning framework that learns an active feature acquisition policy to solve the exploration-exploitation problem during its execution. Key to the success is a novel sequential variational auto-encoder that learns high-quality representations from partially observed states, which are then used by the policy to maximize the task reward in a cost efficient manner. We demonstrate the efficacy of our proposed framework in a control domain as well as using a medical simulator. In both tasks, our proposed method outperforms conventional baselines and results in policies with greater cost efficiency.

cs.LG↗

arXiv2020

Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation

Training generative models that can generate high-quality text with sufficient diversity is an important open problem for Natural Language Generation (NLG) community. Recently, generative adversarial models have been applied extensively on text generation tasks, where the adversarially trained generators alleviate the exposure bias experienced by conventional maximum likelihood approaches and result in promising generation quality. However, due to the notorious defect of mode collapse for adversarial training, the adversarially trained generators face a quality-diversity trade-off, i.e., the generator models tend to sacrifice generation diversity severely for increasing generation quality. In this paper, we propose a novel approach which aims to improve the performance of adversarial text generation via efficiently decelerating mode collapse of the adversarial training. To this end, we introduce a cooperative training paradigm, where a language model is cooperatively trained with the generator and we utilize the language model to efficiently shape the data distribution of the generator against mode collapse. Moreover, instead of engaging the cooperative update for the generator in a principled way, we formulate a meta learning mechanism, where the cooperative update to the generator serves as a high level meta task, with an intuition of ensuring the parameters of the generator after the adversarial update would stay resistant against mode collapse. In the experiment, we demonstrate our proposed approach can efficiently slow down the pace of mode collapse for the adversarial text generators. Overall, our proposed method is able to outperform the baseline approaches with significant margins in terms of both generation quality and diversity in the testified domains.

cs.CL↗

arXiv2018

Convergence rate of solutions toward stationary solutions to the isentropic micropolar fluid model in a half line

In this paper, we study the asymptotic behavior of solutions to the initial boundary value problem for the one-dimensional compressible isentropic micropolar fluid model in a half line \mathbb{R}_{+}:=(0,\infty). We mainly investigates the unique existence, the asymptotic stability and convergence rates of stationary solutions to the outflow problem for this model. We obtain the convergence rates of global solutions towards corresponding stationary solutions if the initial perturbation belongs to the weighted Sobolev space. The proof is based on the weighted energy method by taking into account the effect of the microrotational velocity on the viscous compressible fluid.

math.AP↗

arXiv2018

Hashing over Predicted Future Frames for Informed Exploration of Deep Reinforcement Learning

In deep reinforcement learning (RL) tasks, an efficient exploration mechanism should be able to encourage an agent to take actions that lead to less frequent states which may yield higher accumulative future return. However, both knowing about the future and evaluating the frequentness of states are non-trivial tasks, especially for deep RL domains, where a state is represented by high-dimensional image frames. In this paper, we propose a novel informed exploration framework for deep RL, where we build the capability for an RL agent to predict over the future transitions and evaluate the frequentness for the predicted future frames in a meaningful manner. To this end, we train a deep prediction model to predict future frames given a state-action pair, and a convolutional autoencoder model to hash over the seen frames. In addition, to utilize the counts derived from the seen frames to evaluate the frequentness for the predicted frames, we tackle the challenge of matching the predicted future frames and their corresponding seen frames at the latent feature level. In this way, we derive a reliable metric for evaluating the novelty of the future direction pointed by each action, and hence inform the agent to explore the least frequent one.

cs.LG↗

arXiv2017

Convergence to diffusion waves for solutions of Euler equations with time-depending damping on quadrant

This paper is concerned with the asymptotic behavior of the solution to the Euler equations with time-depending damping on quadrant $(x,t)\in \mathbb{R}^+\times\mathbb{R}^+$, \begin{equation}\notag \partial_t v - \partial_x u=0, \qquad \partial_t u + \partial_x p(v) =\displaystyle -\fracα{(1+t)^λ} u, \end{equation} with null-Dirichlet boundary condition or null-Neumann boundary condition on $u$. We show that the corresponding initial-boundary value problem admits a unique global smooth solution which tends time-asymptotically to the nonlinear diffusion wave. Compared with the previous work about Euler equations with constant coefficient damping, studied by Nishihara and Yang (1999, J. Differential Equations, 156, 439-458), and Jiang and Zhu (2009, Discrete Contin. Dyn. Syst., 23, 887-918), we obtain a general result when the initial perturbation belongs to the same space. In addition, our main novelty lies in the facts that the cut-off points of the convergence rates are different from our previous result about the Cauchy problem. Our proof is based on the classical energy method and the analyses of the nonlinear diffusion wave.

math.AP↗