arXiv subjects

Mingyi Li

Publications and source records attributed to Mingyi Li.

16 recordsLinked to original sources

arXiv2026

Muon with Finite Newton-Schulz: The Smoothing Benefit in Nonsmooth Nonconvex Optimization

Muon has emerged as a strong optimizer for the matrix-valued parameters in large language model pretraining, approximately orthogonalizing its momentum with a few Newton-Schulz iterations. Existing theory either replaces this iteration with the exact polar factor it approximates, or treats its finite depth as an approximation error, and thus the iteration Muon actually runs can only hurt the guarantees. We show that finite Newton-Schulz can instead be beneficial for nonsmooth nonconvex optimization. To this end, we analyze Muon through the online-to-nonconvex conversion, which views the update rule as an online learner and converts its regret bound into a stationarity guarantee. The finite Newton-Schulz iteration smooths the discontinuous polar map into a Lipschitz map of the singular values, and Muon with finite Newton-Schulz can be regarded as an online learner with a smoothed spectral potential. This smoothing is exactly what the conversion needs: we prove that a Newton-Schulz depth growing only logarithmically in the target accuracy suffices for convergence to stationary points in nonsmooth nonconvex optimization, whereas Muon with the exact-polar update may fail to converge. The resulting sample complexity bounds match the best-known guarantees for nonsmooth nonconvex optimization and are optimal for smooth nonconvex optimization up to problem-dependent factors. The argument extends beyond Newton-Schulz to general spectral maps with the same smoothing property.

cs.LG↗

arXiv2026

Policy Optimization Achieves Data-Dependent Regret Bounds in MDPs with Unknown Transitions

We study policy optimization for online episodic tabular Markov decision processes with unknown transition kernels, aiming for best-of-both-worlds guarantees together with data-dependent regret bounds. Recent work (Dann et al., 2023; Li et al., 2026) has shown that policy optimization can adapt to both adversarial and stochastic losses with first-order, second-order, and path-length bounds, but only under known transitions, leaving open whether such data-dependent guarantees are achievable by policy optimization when the transition kernel is unknown. We resolve this by developing a new algorithm based on optimistic follow-the-regularized-leader that attains these guarantees under unknown transitions. The key ingredient is a new design of optimistic $Q$-function estimators together with a data-dependent transition bonus that controls estimator bias through the loss-prediction error. Our analysis further identifies an unavoidable transition-dependent complexity term that captures the intrinsic cost of estimating the transition kernel. As a result, we obtain first-order, second-order, and path-length bounds with the transition-dependent complexity term while simultaneously achieving gap-dependent $\mathrm{polylog}(T)$ regret in the stochastic regime.

cs.LG↗

arXiv2026

Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation

Action-conditioned world models have emerged as a promising paradigm for robot learning, offering a scalable alternative to costly real-world experimentation by generating action-consistent video rollouts. However, persistent world modeling remains challenging in manipulation: frequent end-effector occlusions and rapid wrist-camera motion make the current observation insufficient for predicting future views, causing models to forget or hallucinate scene details seen in earlier frames. Existing memory retrieval strategies often fail to identify informative history in dynamic manipulation scenarios. To address this limitation, we propose Mem-World, a memory-augmented multi-view action-conditioned world model. At its core, we present W-VMem, a 4D wrist-view-centered surfel-indexed memory that anchors historical observations to temporally evolving surface elements. By explicitly modeling when and where scene elements are observed, W-VMem enables geometry-aware retrieval of relevant history frames conditioned on future actions. During generation, relevant history frames are selected via surfel-based rendering and scoring, providing informative and non-redundant context for prediction. Extensive experiments show that Mem-World generates persistent rollouts in complex manipulation scenarios, enables more reliable policy evaluation than Ctrl-World, improving the Pearson correlation with real-world performance by 14.5\%, and supports effective policy improvement through synthetic data generation, increasing success rates from 58\% to 72\% on long-horizon tasks.

cs.CV↗

arXiv2026

VizCrit: Exploring Strategies for Displaying Computational Feedback in a Visual Design Tool

Visual design instructors often provide multi-modal feedback, mixing annotations with text. Prior theory emphasizes the importance of actionable feedback, where "actionability" lies on a spectrum--from surfacing relevant design concepts to suggesting concrete fixes. How might creativity tools implement annotations that support such feedback, and how does the actionability of feedback impact novices' process-related behaviors, perceptions of creativity, learning of design principles, and overall outcomes? We introduce VizCrit, a system for providing computational feedback that supports the actionability spectrum, realized through algorithmic issue detection and visual annotation generation. In a between-subjects study (N=36), novices revised a design under one of three conditions: textbook-based, awareness-centered, or solution-centered feedback. We found that solution-centered feedback led to fewer design issues and higher self-perceived creativity compared with textbook-based feedback, although expert ratings on creativity showed no significant differences. We discuss the implications for AI in Creativity Support Tools, including the potential of calibrating feedback actionability to help novices balance productivity with learning, growth, and developing design awareness.

cs.HC↗

arXiv2026

HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering

Deploying Multimodal Large Language Models as the brain of embodied agents remains challenging, particularly under long-horizon observations and limited context budgets. Existing memory assisted methods often rely on textual summaries, which discard rich visual and spatial details and remain brittle in non-stationary environments. In this work, we propose a non-parametric memory framework that explicitly disentangles episodic and semantic memory for embodied exploration and question answering. Our retrieval-first, reasoning-assisted paradigm recalls episodic experiences via semantic similarity and verifies them through visual reasoning, enabling robust reuse of past observations without rigid geometric alignment. In parallel, we introduce a program-style rule extraction mechanism that converts experiences into structured, reusable semantic memory, facilitating cross-environment generalization. Extensive experiments demonstrate state-of-the-art performance on embodied question answering and exploration benchmarks, yielding a 7.3% gain in LLM-Match and an 11.4% gain in LLM MatchXSPL on A-EQA, as well as +7.7% success rate and +6.8% SPL on GOAT-Bench. Analyses reveal that our episodic memory primarily improves exploration efficiency, while semantic memory strengthens complex reasoning of embodied agents.

cs.RO↗

arXiv2026

Data- and Variance-dependent Regret Bounds for Online Tabular MDPs

This work studies online episodic tabular Markov decision processes (MDPs) with known transitions and develops best-of-both-worlds algorithms that achieve refined data-dependent regret bounds in the adversarial regime and variance-dependent regret bounds in the stochastic regime. We quantify MDP complexity using a first-order quantity and several new data-dependent measures for the adversarial regime, including a second-order quantity and a path-length measure, as well as variance-based measures for the stochastic regime. To adapt to these measures, we develop algorithms based on global optimization and policy optimization, both built on optimistic follow-the-regularized-leader with log-barrier regularization. For global optimization, our algorithms achieve first-order, second-order, and path-length regret bounds in the adversarial regime, and in the stochastic regime, they achieve a variance-aware gap-independent bound and a variance-aware gap-dependent bound that is polylogarithmic in the number of episodes. For policy optimization, our algorithms achieve the same data- and variance-dependent adaptivity, up to a factor of the episode horizon, by exploiting a new optimistic $Q$-function estimator. Finally, we establish regret lower bounds in terms of data-dependent complexity measures for the adversarial regime and a variance measure for the stochastic regime, implying that the regret upper bounds achieved by the global-optimization approach are nearly optimal.

cs.LG↗

arXiv2025

Distributed Bilevel Optimization with Dual Pruning for Resource-limited Clients

With the development of large-scale models, traditional distributed bilevel optimization algorithms cannot be applied directly in low-resource clients. The key reason lies in the excessive computation involved in optimizing both the lower- and upper-level functions. Thus, we present the first resource-adaptive distributed bilevel optimization framework with a second-order free hypergradient estimator, which allows each client to optimize the submodels adapted to the available resources. Due to the coupled influence of partial outer parameters x and inner parameters y, it's challenging to theoretically analyze the upper bound regarding the globally averaged hypergradient for full model parameters. The error bound of inner parameter also needs to be reformulated since the local partial training. The provable theorems show that both RABO and RAFBO can achieve an asymptotically optimal convergence rate of $O(1/\sqrt{C_x^{\ast}Q})$, which is dominated by the minimum coverage of the outer parameter $C_x^{\ast}$. Extensive experiments on two different tasks demonstrate the effectiveness and computation efficiency of our proposed methods.

cs.DC↗

arXiv2025

Metasurfaces Enable Active-Like Passive Radar

Passive radars (PRs) provide a low-cost and energy-efficient approach to object detection by reusing existing wireless transmissions instead of emitting dedicated probing signals. Yet, conventional passive systems require prior knowledge of non-cooperative source waveforms, are vulnerable to strong interference, and rely on Doppler signatures, limiting their ability to detect subtle or slow-moving targets. Here, we introduce a metasurface-enabled PR (MEPR) concept that integrates a space-time-coding programmable metasurface to imprint distinct spatiotemporal tags onto ambient wireless wavefields. This mechanism transforms a PR into an active-like sensing platform without the need for source control, enabling interference suppression, signal enhancement, and accurate target localization and tracking in cluttered environments. A proof-of-concept implementation operating at 5.48 GHz confirms real-time imaging and tracking of unmanned aerial vehicles under interference-rich conditions, with performance comparable to active radar systems. These results establish MEPR as a solid foundation for scalable, adaptive, and energy-efficient next-generation integrated sensing and communication systems.

eess.SP↗

arXiv2025

Multi-entropy from Linking in Chern-Simons Theory

We study the multipartite entanglement structure of quantum states prepared by the Euclidean path integral over three-manifolds with multiple torus boundaries (the so-called link states) in both Abelian and non-Abelian Chern-Simons theories. For three-component link states in the Abelian theory, we derive an explicit formula for the R\'enyi multi-entropy in terms of linking numbers. We further show that the genuine multi-entropy faithfully quantifies the tripartite entanglement generated by GHZ-states, consistent with the fact that the prepared states are stabilizer states.

hep-th↗

arXiv2025

Stencil-Lifting: Hierarchical Recursive Lifting System for Extracting Summary of Stencil Kernel in Legacy Codes

We introduce Stencil-Lifting, a novel system for automatically converting stencil kernels written in low-level languages in legacy code into semantically equivalent Domain-Specific Language (DSL) implementations. Targeting the efficiency bottlenecks of existing verified lifting systems, Stencil-Lifting achieves scalable stencil kernel abstraction through two key innovations. First, we propose a hierarchical recursive lifting theory that represents stencil kernels, structured as nested loops, using invariant subgraphs, which are customized data dependency graphs that capture loop-carried computation and structural invariants. Each vertex in the invariant subgraph is associated with a predicate-based summary, encoding its computational semantics. By enforcing self-consistency across these summaries, Stencil-Lifting ensures the derivation of correct loop invariants and postconditions for nested loops, eliminating the need for external verification. Second, we develop a hierarchical recursive lifting algorithm that guarantees termination through a convergent recursive process, avoiding the inefficiencies of search-based synthesis. The algorithm efficiently derives the valid summaries of stencil kernels, and its completeness is formally proven. We evaluate Stencil-Lifting on diverse stencil benchmarks from two different suites and on four real-world applications. Experimental results demonstrate that Stencil-Lifting achieves 31.62$\times$ and 5.8$\times$ speedups compared to the state-of-the-art verified lifting systems STNG and Dexter, respectively, while maintaining full semantic equivalence. Our work significantly enhances the translation efficiency of low-level stencil kernels to DSL implementations, effectively bridging the gap between legacy optimization techniques and modern DSL-based paradigms.

cs.SE↗

arXiv2025

Consumption Stimulus with Digital Coupons: Heterogeneity and Policy Design

We study consumption stimulus using digital coupons, which provide time-limited subsidies contingent on minimum spending. Analyzing a large-scale program in China, we find that the program generates large and heterogeneous short-term effects. Consumption responses vary across both consumers and locations, reflecting both demand-side and supply-side factors. This heterogeneity shapes the incidence of the program: high-response consumers tend to patronize larger businesses, leading to a regressive allocation of stimulus benefits. Through counterfactual analysis, we show that targeting rules can reshape both the size and distribution of stimulus effects. Targeting the most responsive consumers can more than double the aggregate stimulus, while a hybrid design that combines targeted distribution with direct support to small businesses improves both efficiency and equity.

econ.GN↗

arXiv2025

Modified K-means Algorithm with Local Optimality Guarantees

The K-means algorithm is one of the most widely studied clustering algorithms in machine learning. While extensive research has focused on its ability to achieve a globally optimal solution, there still lacks a rigorous analysis of its local optimality guarantees. In this paper, we first present conditions under which the K-means algorithm converges to a locally optimal solution. Based on this, we propose simple modifications to the K-means algorithm which ensure local optimality in both the continuous and discrete sense, with the same computational complexity as the original K-means algorithm. As the dissimilarity measure, we consider a general Bregman divergence, which is an extension of the squared Euclidean distance often used in the K-means algorithm. Numerical experiments confirm that the K-means algorithm does not always find a locally optimal solution in practice, while our proposed methods provide improved locally optimal solutions with reduced clustering loss. Our code is available at https://github.com/lmingyi/LO-K-means.

cs.LG↗

arXiv2025

TAMO: Fine-Grained Root Cause Analysis via Tool-Assisted LLM Agent with Multi-Modality Observation Data in Cloud-Native Systems

Implementing large language models (LLMs)-driven root cause analysis (RCA) in cloud-native systems has become a key topic of modern software operations and maintenance. However, existing LLM-based approaches face three key challenges: multi-modality input constraint, context window limitation, and dynamic dependence graph. To address these issues, we propose a tool-assisted LLM agent with multi-modality observation data for fine-grained RCA, namely TAMO, including multimodality alignment tool, root cause localization tool, and fault types classification tool. In detail, TAMO unifies multi-modal observation data into time-aligned representations for cross-modal feature consistency. Based on the unified representations, TAMO then invokes its specialized root cause localization tool and fault types classification tool for further identifying root cause and fault type underlying system context. This approach overcomes the limitations of LLMs in processing real-time raw observational data and dynamic service dependencies, guiding the model to generate repair strategies that align with system context through structured prompt design. Experiments on two benchmark datasets demonstrate that TAMO outperforms state-of-the-art (SOTA) approaches with comparable performance.

cs.AI↗

arXiv2024

Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models with Structured Pruning in Resource-Limited Clients

In this work, we study to release the potential of massive heterogeneous weak computing power to collaboratively train large-scale models on dispersed datasets. In order to improve both efficiency and accuracy in resource-adaptive collaborative learning, we take the first step to consider the \textit{unstructured pruning}, \textit{varying submodel architectures}, \textit{knowledge loss}, and \textit{straggler} challenges simultaneously. We propose a novel semi-asynchronous collaborative training framework, namely ${Co\text{-}S}^2{P}$, with data distribution-aware structured pruning and cross-block knowledge transfer mechanism to address the above concerns. Furthermore, we provide theoretical proof that ${Co\text{-}S}^2{P}$ can achieve asymptotic optimal convergence rate of $O(1/\sqrt{N^*EQ})$. Finally, we conduct extensive experiments on two types of tasks with a real-world hardware testbed including diverse IoT devices.The experimental results demonstrate that $Co\text{-}S^2P$ improves accuracy by up to 8.8\% and resource utilization by up to 1.2$\times$ compared to state-of-the-art methods, while reducing memory consumption by approximately 22\% and training time by about 24\% on all resource-limited devices.

cs.DC↗

arXiv2024

Reflected multi-entropy and its holographic dual

We introduce a mixed-state generalization of the multi-entropy through the canonical purification, which we call reflected multi-entropy. We propose the holographic dual of this measure. For the tripartite case, a field-theoretical calculation is performed using a six-point function of twist operators at large $c$ limit. At both zero and finite temperature, the field-theoretical results match the holographic results, supporting our holographic conjecture of this new measure.

hep-th↗

arXiv2024

Thing2Reality: Transforming 2D Content into Conditioned Multiviews and 3D Gaussian Objects for XR Communication

During remote communication, participants often share both digital and physical content, such as product designs, digital assets, and environments, to enhance mutual understanding. Recent advances in augmented communication have facilitated users to swiftly create and share digital 2D copies of physical objects from video feeds into a shared space. However, conventional 2D representations of digital objects restricts users' ability to spatially reference items in a shared immersive environment. To address this, we propose Thing2Reality, an Extended Reality (XR) communication platform that enhances spontaneous discussions of both digital and physical items during remote sessions. With Thing2Reality, users can quickly materialize ideas or physical objects in immersive environments and share them as conditioned multiview renderings or 3D Gaussians. Thing2Reality enables users to interact with remote objects or discuss concepts in a collaborative manner. Our user study revealed that the ability to interact with and manipulate 3D representations of objects significantly enhances the efficiency of discussions, with the potential to augment discussion of 2D artifacts.

cs.HC↗