Searcharxiv⌕ Search

arXiv subjects

Yuhong Dai

Publications and source records attributed to Yuhong Dai.

11 recordsLinked to original sources

Optimal last-iterate rates for the projected decentralized stochastic subgradient method

We study the projected decentralized stochastic subgradient (PDSG) method for minimizing the average of convex, possibly nonsmooth local objectives over a common closed convex constraint set and a fixed connected undirected network. We focus on the finite-time expected suboptimality of the last local iterate generated at each node, which is the actual output locally available without time averaging or network averaging. Under the standard stepsizes $α_t=α/\sqrt{t}$ and $α_t=2/(μt)$, we establish $\mathcal{O}(\log T/\sqrt{T})$ and $\mathcal{O}(\log T/T)$ last-local-iterate rates for PDSG when each local objective is convex and the aggregate objective is strongly convex, respectively. To eliminate the logarithmic loss, we introduce a general horizon-dependent stepsize framework, termed cooldown stepsize, that combines a base stepsize with segmentwise scaling over a multistage partition and includes the dyadic construction (Jain et al, SIAM J. Optim., 2021) as a special case. For adapting to decentralized settings, we propose a long-range variation condition to make the stepsize schedule compatible with network contraction. Under this cooldown stepsize, we obtain $\mathcal{O}(1/\sqrt{T})$ and $\mathcal{O}(1/T)$ last-local-iterate rates for PDSG in both problem classes, matching the optimal centralized dependence on $T$. Experiments on a lower-bound instance and constrained hinge-loss problems illustrate the predicted terminal behavior of local iterates and the control of consensus error under the cooldown stepsize.

math.OC↗

Single-Loop Stochastic Projected Damped Extragradient Methods for Nonconvex--(Strongly) Concave Minimax Optimization

We develop single-loop stochastic projected damped extragradient methods for nonconvex--(strongly) concave minimax optimization, with complexity guarantees for both game stationarity (GS) and optimization stationarity (OS). Our approach combines a stochastic projected damped extragradient (SPDE) method with a recursive variance-reduced variant, VR-SPDE, both of which retain a single-loop structure. Under an unbiased stochastic gradient oracle with uniformly bounded variance, SPDE finds an $\varepsilon$-game-stationary point with stochastic first-order oracle (SFO) complexities of $O(κ\varepsilon^{-4})$ and $O(\varepsilon^{-5})$ in the nonconvex--strongly concave and nonconvex--concave settings, respectively, where $κ=L/μ$. Under an additional mean-square Lipschitz condition on the stochastic gradients, VR-SPDE improves these GS complexities to $O(κ^{3/2}\varepsilon^{-3})$ and $O(\varepsilon^{-9/2})$, respectively. For an $\varepsilon$-optimization-stationary point, SPDE achieves SFO complexities of $O(κ\varepsilon^{-4})$ and $O(\varepsilon^{-6})$, while VR-SPDE achieves $O(κ^{3/2}\varepsilon^{-3})$ and $O(\varepsilon^{-6})$, in the two settings, respectively. These OS guarantees match the best-known bounds achieved by multi-loop methods while preserving a single-loop implementation. To the best of our knowledge, our results provide the best-known SFO complexity guarantees among single-loop stochastic first-order methods for the respective stationarity criteria and problem classes.

math.OC↗

GUI-GenBench: Evaluating Image Generation Models as Interactive GUI Environments

An image generation model used as a graphical user interface (GUI) environment must produce not only a plausible screen but also the correct response to an action. Existing visual-generation benchmarks do not directly assess this combination of functional correctness and temporal consistency in GUIs. We introduce GUI-GenBench, a benchmark of 700 curated samples across five task suites: single-step transitions, multi-step planning, fictional-app generation, real-app trajectories, and coordinate-based grounding. We also introduce GUI-Score, a VLM-based metric that assesses Goal Achievement, Interaction Logic, Content Consistency, UI Plausibility, and Visual Quality. Evaluating 12 image generation models on Chinese and English subsets, we find that strong single-step performance does not consistently extend to coherent multi-step trajectories or accurate grounding. The highest aggregate GUI-Scores are 69.62 on the Chinese subset and 63.16 on the English subset. Qualitative analysis further identifies failures in text rendering, icon interpretation, and coordinate-conditioned transitions. Together, these results distinguish visual plausibility from functional reliability and identify limitations that must be addressed before generated GUIs can serve as dependable interaction environments.

cs.AI↗

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning. However, existing CoT-based T2I methods largely rely on abstract natural-language planning, which lacks the precision required for complex spatial layouts, structured visual elements, and dense textual content. In this work, we propose CoCo (Code-as-CoT), a code-driven reasoning framework that represents the reasoning process as executable code, enabling explicit and verifiable intermediate planning for image generation. Given a text prompt, CoCo first generates executable code that specifies the structural layout of the scene. The code is then executed in a sandboxed environment to render a deterministic draft image. Subsequently, the model refines this draft through fine-grained image editing to produce the final high-fidelity result. To support this training paradigm, we construct CoCo-10K, a curated dataset containing structured draft-final image pairs designed to teach both structured draft construction and corrective visual refinement. Empirical evaluations on StructT2IBench, OneIG-Bench, and LongText-Bench show that CoCo achieves improvements of 68.83%, 54.8%, and 41.23%, respectively, over direct generation, while also outperforming other CoT-enhanced generation methods. These results demonstrate that executable code is an effective and reliable reasoning paradigm for precise, controllable, and structured text-to-image generation.

cs.AI↗

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

Proactive and real-time interactive experiences are essential for human-like AI companions, yet face three key challenges: (1) achieving low-latency inference under continuous streaming inputs, (2) autonomously deciding when to respond, and (3) controlling both quality and quantity of generated content to meet real-time constraints. In this work, we instantiate AI companions through two gaming scenarios, commentator and guide, selected for their suitability for automatic evaluation. We introduce the Live Gaming Benchmark, a large-scale dataset with three representative scenarios: solo commentary, co-commentary, and user guidance, and present Proact-VL, a general framework that shapes multimodal language models into proactive, real-time interactive agents capable of human-like environment perception and interaction. Extensive experiments show Proact-VL achieves superior response latency and quality while maintaining strong video understanding capabilities, demonstrating its practicality for real-time interactive applications.

cs.CV↗

MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs

Large language models (LLMs) are increasingly deployed as interactive agents, yet their capacity for social and strategic reasoning over extended interaction remains poorly understood. Existing evaluations rely on static vignettes or single-game benchmarks that cannot capture the sustained, multi-faceted reasoning that real-world multi-agent settings demand. We introduce Mindgames, a multi-game arena and evaluation platform for LLM agents that operationalizes complementary reasoning demands relevant to ``theory of mind'': belief attribution under hidden information, opponent modeling through repeated strategic interaction, cooperative inference under knowledge asymmetries, and sustained deception in social deduction. Built on TextArena, Mindgames provides a unified interaction interface, TrueSkill-based rating, and full trajectory logging across four game environments. We instantiate Mindgames through a 2025 competition cycle hosted at a major AI conference, which assessed 944 submitted agents from 76 teams across four games: Colonel Blotto, Iterated Prisoner's Dilemma, Codenames, and Secret Mafia. Our analysis surfaces both agent-level and evaluation-level limitations: brittle rule adherence remains a major bottleneck, top-performing systems repeatedly rely on explicit structural scaffolding, and leaderboard validity differs sharply across environments. In particular, failure-heavy environments can reward robustness to opponent errors as much as strategic ability, with Secret Mafia exhibiting a pronounced error-survival confound in this cycle. We release a dataset of 29,571 multi-agent games with turn-level observations, actions, and rewards, together with MG-Ref, a deterministic offline tournament protocol that scores new agents against a frozen reference pool of top-ranked, low-error Stage~II submissions under the same error-attribution lens used in this analysis.

cs.AI↗

SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments

Spatial reasoning over three-dimensional scenes is a core capability for embodied intelligence, yet continuous model improvement remains bottlenecked by the cost of geometric annotation. The self-evolving paradigm offers a promising path, but its reliance on model consensus to construct pseudo-labels causes training to reinforce rather than correct the model's own geometric errors. We identify a property unique to 3D spatial reasoning that circumvents this limitation: ground truth is a deterministic consequence of the underlying geometry, computable exactly from point clouds and camera poses without any model involvement. Building on this insight, we present SpatialEvo, a self-evolving framework for 3D spatial reasoning, centered on the Deterministic Geometric Environment (DGE). The DGE formalizes 16 spatial reasoning task categories under explicit geometric validation rules and converts unannotated 3D scenes into zero-noise interactive oracles, replacing model consensus with objective physical feedback. A single shared-parameter policy co-evolves across questioner and solver roles under DGE constraints: the questioner generates physically valid spatial questions grounded in scene observations, while the solver derives precise answers against DGE-verified ground truth. A task-adaptive scheduler endogenously concentrates training on the model's weakest categories, producing a dynamic curriculum without manual design. Experiments across nine benchmarks demonstrate that SpatialEvo achieves the highest average score at both 3B and 7B scales, with consistent gains on spatial reasoning benchmarks and no degradation on general visual understanding.

cs.CV↗

WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics

Existing web-generation benchmarks rely on text prompts or static screenshots as input. However, videos naturally convey richer signals such as interaction flow, transition timing, and motion continuity, which are essential for faithful webpage recreation. Despite this potential, video-conditioned webpage generation remains largely unexplored, with no dedicated benchmark for this task. To fill this gap, we introduce WebVR, a benchmark that evaluates whether MLLMs can faithfully recreate webpages from demonstration videos. WebVR contains 175 webpages across diverse categories, all constructed through a controlled synthesis pipeline rather than web crawling, ensuring varied and realistic demonstrations without overlap with existing online pages. We also design a fine-grained, human-aligned visual rubric that evaluates the generated webpages across multiple dimensions. Experiments on 19 models reveal substantial gaps in recreating fine-grained style and motion quality, while the rubric-based automatic evaluation achieves 96% agreement with human preferences. We release the dataset, evaluation toolkit, and baseline results to support future research on video-to-webpage generation.

cs.CV↗

Zeroth-Order primal-dual Alternating Projection Gradient Algorithms for Nonconvex Minimax Problems with Coupled linear Constraints

In this paper, we study zeroth-order algorithms for nonconvex minimax problems with coupled linear constraints under the deterministic and stochastic settings, which have attracted wide attention in machine learning, signal processing and many other fields in recent years, e.g., adversarial attacks in resource allocation problems and network flow problems etc. We propose two single-loop algorithms, namely the zeroth-order primal-dual alternating projected gradient (ZO-PDAPG) algorithm and the zeroth-order regularized momentum primal-dual projected gradient algorithm (ZO-RMPDPG), for solving deterministic and stochastic nonconvex-(strongly) concave minimax problems with coupled linear constraints. The iteration complexity of the two proposed algorithms to obtain an $\varepsilon$-stationary point are proved to be $\mathcal{O}(\varepsilon ^{-2})$ (resp. $\mathcal{O}(\varepsilon ^{-4})$) for solving nonconvex-strongly concave (resp. nonconvex-concave) minimax problems with coupled linear constraints under deterministic settings and $\tilde{\mathcal{O}}(\varepsilon ^{-3})$ (resp. $\tilde{\mathcal{O}}(\varepsilon ^{-6.5})$) under stochastic settings respectively. To the best of our knowledge, they are the first two zeroth-order algorithms with iterative complexity guarantees for solving nonconvex-(strongly) concave minimax problems with coupled linear constraints under the deterministic and stochastic settings. The proposed ZO-RMPDPG algorithm, when specialized to stochastic nonconvex-concave minimax problems without coupled constraints, outperforms all existing zeroth-order algorithms by achieving a better iteration complexity, thus setting a new state-of-the-art.

math.OC↗

Derivative-free Alternating Projection Algorithms for General Nonconvex-Concave Minimax Problems

In this paper, we study zeroth-order algorithms for nonconvex-concave minimax problems, which have attracted widely attention in machine learning, signal processing and many other fields in recent years. We propose a zeroth-order alternating randomized gradient projection (ZO-AGP) algorithm for smooth nonconvex-concave minimax problems, and its iteration complexity to obtain an $\varepsilon$-stationary point is bounded by $\mathcal{O}(\varepsilon^{-4})$, and the number of function value estimation is bounded by $\mathcal{O}(d_{x}+d_{y})$ per iteration. Moreover, we propose a zeroth-order block alternating randomized proximal gradient algorithm (ZO-BAPG) for solving block-wise nonsmooth nonconvex-concave minimax optimization problems, and the iteration complexity to obtain an $\varepsilon$-stationary point is bounded by $\mathcal{O}(\varepsilon^{-4})$ and the number of function value estimation per iteration is bounded by $\mathcal{O}(K d_{x}+d_{y})$. To the best of our knowledge, this is the first time that zeroth-order algorithms with iteration complexity gurantee are developed for solving both general smooth and block-wise nonsmooth nonconvex-concave minimax problems. Numerical results on data poisoning attack problem and distributed nonconvex sparse principal component analysis problem validate the efficiency of the proposed algorithms.

math.OC↗

Training GANs with Centripetal Acceleration

Training generative adversarial networks (GANs) often suffers from cyclic behaviors of iterates. Based on a simple intuition that the direction of centripetal acceleration of an object moving in uniform circular motion is toward the center of the circle, we present the Simultaneous Centripetal Acceleration (SCA) method and the Alternating Centripetal Acceleration (ACA) method to alleviate the cyclic behaviors. Under suitable conditions, gradient descent methods with either SCA or ACA are shown to be linearly convergent for bilinear games. Numerical experiments are conducted by applying ACA to existing gradient-based algorithms in a GAN setup scenario, which demonstrate the superiority of ACA.

cs.LG↗