arXiv subjects

Heng Yang

Publications and source records attributed to Heng Yang.

At least 19 recordsLinked to original sources

arXiv2026

QoS-Aware RACH Preamble Slicing via Quota-Projected Branching Deep Reinforcement Learning

Quality-of-service (QoS)-aware random access requires adaptive allocation of a finite random access channel (RACH) preamble budget across heterogeneous traffic and access procedures. This paper proposes QP-BD3QN-RACH, a quota-projected branching deep reinforcement learning controller for mixed two-step (2RA) and four-step (4RA) contention-based random access. Four action branches correspond to the delay-sensitive and delay-tolerant 2RA/4RA preamble pools. A branching dueling Double DQN selects pool-specific multipliers, and deterministic quota projection converts them to nonnegative integer allocations that preserve the preamble budget. With five actions per branch, the controller represents 625 pre-projection branch-action tuples using 20 branch-action outputs. Evaluation covers five arrival loads, cross-method comparison under nominal seed 42, six-seed sensitivity of QP-BD3QN-RACH, and targeted ablations. Across the five-load grid, its mean direction-aligned differences relative to four comparators are positive: 5.74 to 8.21 percentage points for success/collision, 1.23 to 1.92 percentage points for fallback, 0.35 to 0.68 percentage points for blocking, and 0.128 to 0.456 decision intervals for successful-access delay. Load-wise results exhibit metric-dependent tradeoffs, particularly under intermediate and overload conditions.

cs.NI↗

arXiv2026

Afterimage Slow Regions in First-Order Methods for Linear Conic Programming

First-order methods for linear conic programming often stall on long plateaus. Existing analyses characterize when during a run or on which problem instances slow convergence occurs; we instead ask where in the state space slow convergence is present. We introduce the slow region family for parameterized averaged fixed-point iterations. On a slow region, one step moves the state by only a small fraction of its distance to the fixed-point set, so an orbit starting there keeps almost its initial distance for arbitrarily many iterations. We then develop the afterimage principle to construct them. A center family and a nearby petal family share the same limit parameter, so their residual fields become close, while their fixed-point sets or forward drifts stay far apart. The petal geometry then certifies a slow region for the center. We verify the standing assumptions for ADMM, sGS-ADMM, and PDHG, and give an LP, SOCP, and SDP gallery showing how varied slow regions can be.

math.OC↗

arXiv2026

Trajectory Optimization via Schr\"{o}dinger Bridge Sampling

We take a new look at the relation between finite-horizon trajectory optimization and Schr\"odinger bridge sampling. Viewed as inference, KL-regularized trajectory optimization is solved by sampling from a Gibbs--Boltzmann distribution whose energy is the trajectory cost, and the adjoint Schr\"odinger bridge sampler (ASBS) is a simulation-free diffusion sampler designed for exactly such unnormalized targets. Hard equality path and terminal constraints, by contrast, confine the admissible decision variables to a measure-zero feasibility manifold, on which the target must be redefined intrinsically. In particular: $(a)$ we analyze two complementary parametrizations; a rollout parametrization, in which the dynamics are eliminated and only the remaining constraints shape the manifold, and a double-shooting parametrization, in which states and controls are sampled jointly and the dynamics themselves become part of the manifold; $(b)$ we establish regularity conditions under which both admissible sets are smooth embedded manifolds; $(c)$ under compactness and path-connectedness assumptions, we sample from the resulting intrinsic Gibbs measures via Riemannian ASBS, treating strict inequalities through exponential slack variables. Experiments, including contact-rich locomotion and manipulation, demonstrate the effectiveness of both regimes.

eess.SY↗

arXiv2026

Hard-Constrained Sampling on Embedded Riemannian Manifolds via Adjoint Schr\"{o}dinger Bridges

A variety of tasks require sampling from unnormalized Boltzmann distributions supported on manifolds. Building upon the foundations of adjoint matching and adjoint Schr\"{o}dinger bridge sampling, this paper provides a theoretically justified method, through the lens of stochastic optimal control, to address this problem on smooth, compact, path-connected embedded Riemannian manifolds. As an element of novelty compared to existing literature, feasibility is enforced at the level of the state space, meaning the controlled diffusion is defined intrinsically on the curved space. Empirical validations are provided for several physics applications.

eess.SY↗

arXiv2026

Provable Edge-of-Stability for Adam on a One-Dimensional Quadratic

The edge-of-stability (EoS) phenomenon of Adam has been widely observed, while its underlying dynamical mechanism is not yet fully understood. We study uncorrected Adam on a one-dimensional quadratic, a clean setting where constant curvature isolates the optimizer-induced dynamics behind the EoS. We characterize the resulting dynamics across the parameter space. In broad regimes, we prove that Adam exhibits a restoring tendency toward its frozen stability threshold $2(1+\beta_1)/[\eta(1-\beta_1)]$. We also identify settings in which this edge-seeking mechanism breaks down, including strictly subcritical periodic orbits and specially tuned trajectories that converge to the optimum while remaining uniformly supercritical. These results give a concrete dynamical explanation for Adam's EoS in a setting free of evolving loss geometry, while also exposing its limitations.

cs.LG↗

arXiv2026

An Improved Degree Condition for Connectivity-Preserving Spanning $(u,v)$-Paths

Teng and Tian proved the following result. Let $k\ge 2$ and $t\ge 3$, and let $G$ be a $k$-connected graph of order $n$. If $n\ge 6k+1$ and $\delta(G)\ge \lceil(n+6)/2\rceil$ when $t=3$, while $n\ge 6k+7t-17$ and $\delta(G)\ge \lceil(n+t+2)/2\rceil$ when $t\ge 4$, then, for any two distinct vertices $u,v$ and every integer $s$ with $1\le s\le t$, there exist $s$ internally vertex-disjoint $(u,v)$-paths $P_1,\dots,P_s$ whose union spans $G$ and such that $G-E(P_1\cup\cdots\cup P_s)$ is $k$-connected. They asked whether the minimum-degree condition could be lowered to $\delta(G)\ge \lceil(n+t)/2\rceil$ for every $t\ge 3$. We answer this question affirmatively and further reduce the required order to $n\ge \max\{6k+9-3t,\,2k+t+3\}$.

math.CO↗

arXiv2026

$k$-Connected Subgraphs of All Orders in Large Graphs with Minimum Degree at Least $n/q$

For every fixed pair of integers $k\ge 2$ and $q\ge 3$, we prove that every sufficiently large $k$-connected graph $G$ of order $n$ with minimum degree $\delta(G)\ge n/q$ contains a $k$-connected subgraph of every order $\ell\in\{2k,2k+1,\ldots,n\}$. In the case $k=2$, this confirms a conjecture of Liu and Ning~\cite{LiuNing}. The proof combines two constructions. First, we construct a small $k$-connected subgraph $D$ such that every vertex outside $D$ has at least $k$ neighbors in $D$. By successively adding the vertices outside $D$, we obtain $k$-connected subgraphs of every order from $|V(D)|$ to $n$. Second, an averaging argument on common neighborhoods, together with a complete bipartite construction, yields $k$-connected subgraphs of every order from $2k$ to $|V(D)|$. Together, the two constructions cover all orders from $2k$ to $n$. The lower endpoint $2k$ is best possible.

math.CO↗

arXiv2026

X4Val: Learning Neural Surrogates for Variance-Reduced Policy Evaluation

Rigorous evaluation of learning-based robotic systems is an essential prerequisite for deployment. However, real-world test data is expensive to gather; moreover, in a typical iterative development context, data gathered from the latest policy is necessarily limited in scale. This motivates evaluation methodologies that make use of heterogeneous data sources, including simulation, historical policy logs, and data collected from related platforms or environments. While such auxiliary data are abundant and inexpensive, they are generally not directly representative of real-world outcomes -- for example, performance in simulation may differ substantially from performance in the real world -- making their principled use for high-confidence performance estimation challenging. In this paper, we introduce X4Val, a general framework for variance-reduced real-world metric estimation in the presence of non-paired, multi-domain data. X4Val embeds samples from real and auxiliary domains into a shared representation space and learns a transferable predictor of real-world metrics; this learned predictor is then incorporated into a control-variates estimator, enabling variance reduction even when paired samples are unavailable. We provide theoretical analysis and empirical evaluations on autonomous driving and real-world robot manipulation tasks, domains across which X4Val achieves up to 38.4% variance reduction and demonstrates consistent improvements over strong baselines. These results show that non-paired, heterogeneous data can be leveraged to substantially improve the sample efficiency of rigorous robotic system validation.

cs.RO↗

arXiv2026

From Vintage Mythology to Topological Physics: Unveiling a Universal Structural Attractor in Alcoholic Beverage Aging

Alcoholic beverage properties are increasingly understood through ethanol-water structural states rather than empirical labels such as alcohol content and vintage. Yet whether chronological vintage similarly reflects an intrinsic structural state remains unclear. Here, we apply persistent homology to map the topological evolution of self-assembled molecular aggregates in strong-aroma Baijiu aged 1-10 years. The resulting fingerprints reveal a three-stage maturation pathway: rapid scaffold consolidation (B0), population-level channel stabilization (B1), and non-monotonic cavity reorganization (B2). These coupled trajectories converge toward a mature topological state rather than passively tracking chronological age. We therefore propose a universal topological attractor, in which optimal aging is defined by a system's position in persistence space relative to a mature structural domain. This framework reframes beverage aging as navigation through structural state space, providing a physical basis for quality evaluation and accelerated maturation.

physics.atom-ph↗

arXiv2026

BEACON: Cross-Domain Co-Training of Generative Robot Policies via Best-Effort Adaptation

We introduce BEACON--Best-Effort Adaptation for Cross-Domain Co-Training--a theory-driven framework for training generative robot policies with abundant source demonstrations and limited target demonstrations. BEACON casts cross-domain co-training as a discrepancy-aware importance-reweighting problem, jointly learning a diffusion-based visuomotor policy and per-sample source weights that minimize an objective informed by target-domain generalization guarantees. To make best-effort adaptation practical for high-dimensional sequence policies, we develop scalable instance-level discrepancy estimators, stochastic alternating updates for policy and weights, and a multi-source extension that balances heterogeneous source domains. Across sim-to-sim, sim-to-real, and multi-source manipulation settings, BEACON improves robustness and data efficiency over target-only, fixed-ratio co-training, and feature-alignment baselines. Importantly, even without an explicit alignment objective, BEACON achieves feature alignment as an implicit result of discrepancy-aware cross-domain co-training.

cs.RO↗

arXiv2026

Simplicial Regularizability of the Pseudo-Moment Cone and Carath\'eodory-Type Atomic Decomposition of Moment Matrices

We study the facial geometry of the homogeneous pseudo-moment cone $\Sigma_{n,2d}^*$ and its implications for atomic decomposition of moment matrices. For fixed $d \ge 2$, we show that if a moment matrix is formed by $O(n^d)$ generically chosen weighted atoms, then its minimal face in the matrix realization of the pseudo-moment cone is \emph{simplicial} and generated by the planted rank-one atoms. Based on this geometric result, we develop a Carath\'eodory-type extreme-ray decomposition algorithm for spectrahedral cones and show that, when specialized to the pseudo-moment cone, it yields an efficient atomic decomposition method for generically generated moment matrices in the same regime. A stabilized numerical implementation demonstrates strong recovery performance and suggests that, outside the guaranteed regime, the algorithm may serve as a practical sampler of high-rank extreme rays.

math.OC↗

arXiv2026

CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies

Flow-based vision-language-action (VLA) policies offer strong expressivity for action generation, but suffer from a fundamental inefficiency: multi-step inference is required to recover action structure from uninformative Gaussian noise, leading to a poor efficiency-quality trade-off under real-time constraints. We address this issue by rethinking the role of the starting point in generative action modeling. Instead of shortening the sampling trajectory, we propose CF-VLA, a coarse-to-fine two-stage formulation that restructures action generation into a coarse initialization step that constructs an action-aware starting point, followed by a single-step local refinement that corrects residual errors. Concretely, the coarse stage learns a conditional posterior over endpoint velocity to transform Gaussian noise into a structured initialization, while the fine stage performs a fixed-time refinement from this initialization. To stabilize training, we introduce a stepwise strategy that first learns a controlled coarse predictor and then performs joint optimization. Experiments on CALVIN and LIBERO show that our method establishes a strong efficiency-performance frontier under low-NFE (Number of Function Evaluations) regimes: it consistently outperforms existing NFE=2 methods, matches or surpasses the NFE=10 $\pi_{0.5}$ baseline on several metrics, reduces action sampling latency by 75.4%, and achieves the best average real-robot success rate of 83.0%, outperforming MIP by 19.5 points and $\pi_{0.5}$ by 4.0 points. These results suggest that structured, coarse-to-fine generation enables both strong performance and efficient inference. Our code is available at https://github.com/EmbodiedAI-RoboTron/CF-VLA.

cs.CV↗

arXiv2026

Towards Safe Mobility: A Unified Transportation Foundation Model enabled by Open-Ended Vision-Language Dataset

Urban transportation systems face growing safety challenges that require scalable intelligence for emerging smart mobility infrastructures. While recent advances in foundation models and large-scale multimodal datasets have strengthened perception and reasoning in intelligent transportation systems (ITS), existing research remains largely centered on microscopic autonomous driving (AD), with limited attention to city-scale traffic analysis. In particular, open-ended safety-oriented visual question answering (VQA) and corresponding foundation models for reasoning over heterogeneous roadside camera observations remain underexplored. To address this gap, we introduce the Land Transportation Dataset (LTD), a large-scale open-source vision-language dataset for open-ended reasoning in urban traffic environments. LTD contains 11.6K high-quality VQA pairs collected from heterogeneous roadside cameras, spanning diverse road geometries, traffic participants, illumination conditions, and adverse weather. The dataset integrates three complementary tasks: fine-grained multi-object grounding, multi-image camera selection, and multi-image risk analysis, requiring joint reasoning over minimally correlated views to infer hazardous objects, contributing factors, and risky road directions. To ensure annotation fidelity, we combine multi-model vision-language generation with cross-validation and human-in-the-loop refinement. Building upon LTD, we further propose UniVLT, a transportation foundation model trained via curriculum-based knowledge transfer to unify microscopic AD reasoning and macroscopic traffic analysis within a single architecture. Extensive experiments on LTD and multiple AD benchmarks demonstrate that UniVLT achieves SOTA performance on open-ended reasoning tasks across diverse domains, while exposing limitations of existing foundation models in complex multi-view traffic scenarios.

cs.CV↗

arXiv2026

Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics

We propose a sampling-based framework for finite-horizon trajectory and policy optimization under differentiable dynamics by casting controller design as inference. Specifically, we minimize a KL-regularized expected trajectory cost, which yields an optimal "Boltzmann-tilted" distribution over controller parameters that concentrates on low-cost solutions as temperature decreases. To sample efficiently from this sharp, potentially multimodal target, we introduce tempered sequential Monte Carlo (TSMC): an annealing scheme that adaptively reweights and resamples particles along a tempering path from a prior to the target distribution, while using Hamiltonian Monte Carlo rejuvenation to maintain diversity and exploit exact gradients obtained by differentiating through trajectory rollouts. For policy optimization, we extend TSMC via (i) a deterministic empirical approximation of the initial-state distribution and (ii) an extended-space construction that treats rollout randomness as auxiliary variables. Experiments across trajectory- and policy-optimization benchmarks show that TSMC is broadly applicable and compares favorably to state-of-the-art baselines.

cs.LG↗

arXiv2026

Local Second-Order Limit Dynamics of the Alternating Direction Method of Multipliers for Semidefinite Programming

The alternating direction method of multipliers (ADMM) is widely used for solving large-scale semidefinite programs (SDPs), yet on instances with multiple primal-dual optimal solution pairs, it often enters prolonged slow-convergence regions where the Karush-Kuhn-Tucker (KKT) residuals nearly stall. To explain and predict the fine-grained dynamical behavior inside these regions, we develop a local second-order limit dynamics framework for ADMM near an arbitrary KKT point -- not necessarily the eventual limit point of the iterates. Assuming the existence of a strictly complementary primal-dual solution pair, we derive a second-order local expansion of the ADMM dynamics by leveraging a refined and simplified variational characterization of the (parabolic) second-order directional derivative of the PSD projection operator. This expansion reveals a closed convex cone of directions along which the local first-order update vanishes, and it induces a second-order limit map that governs the persistent drift after transient effects are filtered out. We characterize fundamental properties of this mapping, including its kernel, range, and continuity. A primal-dual decoupling further yields a clean scaling law for the effect of the penalty parameter in ADMM. We connect these properties to second-order dynamical features of ADMM, including fixed points, almost-invariant sets, and microscopic phases. Three empirical phenomena in slow-convergence regions are then explained or predicted: (i) angles between consecutive iterate differences are small yet nonzero, except for sparse spikes; (ii) primal and dual infeasibilities are insensitive to penalty-parameter updates; and (iii) iterates can be transiently trapped in a low-dimensional subspace for an extended period. Extensive numerical experiments on the Mittelmann dataset corroborate our theoretical predictions.

math.OC↗

arXiv2026

Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models

Process Reward Models (PRMs) are rapidly becoming the backbone of LLM reasoning pipelines, yet we demonstrate that state-of-the-art PRMs are systematically exploitable under adversarial optimization pressure. To address this, we introduce a three-tiered diagnostic framework that applies increasing adversarial pressure to quantify these vulnerabilities. Static perturbation analysis uncovers a fluency-logic dissociation: high invariance to surface-level style changes reward changes $<$0.1, yet inconsistent detection of logically-corrupted reasoning, with different models failing on different attack types. Adversarial optimization demonstrates that gradient-based attacks inflate rewards on invalid trajectories, with reward landscapes exhibiting wide, exploitable peaks. RL-induced reward hacking exposes the critical failure mode: policies trained on AIME problems achieve near-perfect PRM rewards ($>$0.9), while ground-truth accuracy remains low (below 4%), with 43% of reward gains attributable to stylistic shortcuts. These findings reveal that current PRMs function as fluency detectors rather than reasoning verifiers, creating systematic blind spots that undermine their use as training signals. We release PRM-BiasBench and a diagnostic toolkit to enable robustness evaluation before deployment. The code and dataset are available at https://github.com/SqueezeAILab/reward-under-attack.

cs.LG↗

arXiv2026

Advances in Global Solvers for 3D Vision

Global solvers have emerged as a powerful paradigm for 3D vision, offering certifiable solutions to nonconvex geometric optimization problems traditionally addressed by local or heuristic methods. This survey presents the first systematic review of global solvers in geometric vision, unifying the field through a comprehensive taxonomy of three core paradigms: Branch-and-Bound (BnB), Convex Relaxation (CR), and Graduated Non-Convexity (GNC). We present their theoretical foundations, algorithmic designs, and practical enhancements for robustness and scalability, examining how each addresses the fundamental nonconvexity of geometric estimation problems. Our analysis spans ten core vision tasks, from Wahba problem to bundle adjustment, revealing the optimality-robustness-scalability trade-offs that govern solver selection. We identify critical future directions: scaling algorithms while maintaining guarantees, integrating data-driven priors with certifiable optimization, establishing standardized benchmarks, and addressing societal implications for safety-critical deployment. By consolidating theoretical foundations, practical advances, and broader impacts, this survey provides a unified perspective and roadmap toward certifiable, trustworthy perception for real-world applications. A continuously-updated literature summary and companion code tutorials are available at https://github.com/ericzzj1989/Awesome-Global-Solvers-for-3D-Vision.

cs.CV↗

arXiv2026

Accelerating Structured Chain-of-Thought in Autonomous Vehicles

Chain-of-Thought (CoT) reasoning enhances the decision-making capabilities of vision-language-action models in autonomous driving, but its autoregressive nature introduces significant inference latency, making it impractical for real-time applications. To address this, we introduce FastDriveCoT, a novel parallel decoding method that accelerates template-structured CoT. Our approach decomposes the reasoning process into a dependency graph of distinct sub-tasks, such as identifying critical objects and summarizing traffic rules, some of which can be generated in parallel. By generating multiple independent reasoning steps concurrently within a single forward pass, we significantly reduce the number of sequential computations. Experiments demonstrate a 3-4$\times$ speedup in CoT generation and a substantial reduction in end-to-end latency across various model architectures, all while preserving the original downstream task improvements brought by incorporating CoT reasoning.

cs.RO↗