Searcharxiv⌕ Search

arXiv subjects

Xi Chen

Publications and source records attributed to Xi Chen.

At least 109 records · Page 6Linked to original sources
arXiv2026

Hyperparameter Transfer Laws for Non-Recurrent Multi-Path Neural Networks

Deeper modern architectures are costly to train, making hyperparameter transfer preferable to expensive repeated tuning. Maximal Update Parametrization ($μ$P) helps explain why many hyperparameters transfer across width. Yet depth scaling is less understood for modern architectures, whose computation graphs contain multiple parallel paths and residual aggregation. To unify various non-recurrent multi-path neural networks such as CNNs, ResNets, and Transformers, we introduce a graph-based notion of effective depth. Under stabilizing initializations and a maximal-update criterion, we show that the optimal learning rate decays with effective depth following a universal -3/2 power law. Here, the maximal-update criterion maximizes the typical one-step representation change at initialization without causing instability, and effective depth is the minimal path length from input to output, counting layers and residual additions. Experiments across diverse architectures confirm the predicted slope and enable reliable zero-shot transfer of learning rates across depths and widths, turning depth scaling into a predictable hyperparameter-transfer problem.

cs.LG↗
arXiv2026

Bridging continuous control and Floquet driving for charging many-body spin chains

Recent advances in quantum information and quantum thermodynamics have reshaped the understanding of energy storage at the microscopic scale, paving the way toward protocols for storing and transferring energy in quantum devices. These systems, known as quantum batteries, offer a conceptual alternative to conventional macroscopic chemical batteries by exploiting quantum coherence, correlations, and many-body dynamics. By navigating the landscape of established spin-based quantum batteries, we review existing charging and work-extraction protocols, as well as the impact of external factors on their performance. Motivated by Floquet-engineered proposals, we further establish a connection between continuously and periodically driven spin chains as platforms for quantum energy storage. Finally, we survey experimental realizations and proposals, highlighting their implementability and scalability in current and near-term quantum technologies.

quant-ph↗
arXiv2026

Kicked-Ising Quantum Battery

Entanglement has been identified as a key resource for enhancing charging performance in quantum batteries. We show that the kicked-Ising model at the self-dual point provides an explicit charging mechanism, where maximal entanglement growth yields maximal energy injection. Identifying the Floquet dynamics as a Clifford quantum cellular automata and considering exact diagonalization in momentum space, we analytically characterize the charging process, featuring a stable performance while achieving maximal charging. We further propose a fixed time window protocol that accelerates charging toward the continuously driven transverse-field limit. Spin-correlator analysis reveals that scrambling and light-cone spreading govern charging performance. The protocols remain compatible with diverse platforms, underscoring their scalability and practical feasibility.

quant-ph↗
arXiv2026

Inverse Scattering by Diffracted Waves

In addition to reflection and refraction, another form of wave deviation is defined as diffraction. Notably, when incident waves strike a corner, diffracted waves emanate from the corner tip and propagate omnidirectionally. This paper proposes a novel framework for detecting rigid cornered obstacles using measured diffracted wave data. The framework first transforms the underlying initial-boundary value problems into initial value problems on conic manifolds via the method of images. Subsequently, the retrieval of obstacle information is achieved through Cheeger--Taylor functional calculus and microlocal analysis on conic manifolds. Specifically, we prove that for a given pulse, measurements of the resulting diffracted waves captured by a curve receiver uniquely determine both the location and shape of the visible portion of a polygonal obstacle. The proof is constructive, explicitly formulating the corresponding recovery scheme. This methodology offers two key advantages: first, the size and placement of the receiver can be arbitrary; second, the inversion only requires measurements of diffracted waves and obviates the need to solve wave equations within the cornered domain as in conventional methods.

math.AP↗
arXiv2026

Online Bipartite Matching with Reusable Capacity under Non-Stationary Rewards

We study online bipartite matching with reusable server capacity and non-stationary rewards. Jobs arrive sequentially, reveal compatible servers, reward rates, and processing durations, and must be accepted or rejected irrevocably. An accepted job occupies one unit of server capacity only during its processing interval, so an assignment may displace an unknown sequence of future jobs. Existing guarantees are typically calibrated by a global reward range, which can become arbitrarily large when rewards drift over a long horizon. We instead impose a locally bounded reward condition: reward rates of jobs that can compete for the same server within a relevant time window differ by at most a factor $δ$. Under this condition, we develop two BALANCE-type algorithms with time-aware opportunity-cost losses. TS-BAL maximizes cumulative blocking losses over feasible reuse schedules and achieves a competitive ratio of $2\ln(δD)+\mathcal O(\ln\ln(δ\vee D))$. GR-BAL uses a greedy relaxation of this loss and achieves $\ln(δD)+\mathcal O(\ln\ln(δ\vee D))$, matching a lower bound of $\ln(δD)$ in the leading term. Numerical experiments demonstrate robust performance under substantial global reward drift and favorable finite-capacity performance.

math.OC↗
arXiv2026

Toward Anthropomorphic Dialogue: A Closed-Loop Framework for Human-Like Chat Generation, Evaluation, and Preference Alignment

Human-like private chat requires more than fluent response generation: a system must preserve persona, relationship, memory, bounded knowledge, medium-specific timing, and a coherent multi-turn arc. We present AnthroDial, a closed-loop framework that formulates anthropomorphic dialogue as a joint problem of system architecture, executable evaluation, and diagnostic alignment. It combines (1) a role-conditioned scheduled dialogue runtime with persona and scenario cards, long-term memory, virtual time, and single-draft message decisions; (2) an executable benchmark with an L0 validity gate, five per-turn dimensions, and five dialogue-level dimensions; and (3) a post-training pipeline that filters 16,436 scheduled-decision examples for SFT and applies GRPO with a cognitive-diagnostic, ZPD-aware reward. The reward maintains Kalman-filtered capability estimates for each behavioral dimension, upweights dimensions with larger capability deficits, and uses rollout scores as task-level ZPD matches to focus optimization on learnable weak skills. On a benchmark with 55 personas, 50 scenarios, 50 persona-scenario bindings, and 100 role-conditioned cases per model, we evaluate 16 systems spanning frontier baselines, open models, thinking/no-think variants, and SFT/RL ablations. The strongest non-trained baseline reaches 32.00% strict ACC, while Qwen3.6-27B-SFT+RL reaches 39.00% strict ACC and a 98.5 overall score. In the 9B no-think setting, SFT and RL improve strict ACC from 0.00% to 13.00% and 18.37%. These results show that anthropomorphic dialogue benefits when generation, evaluation, and reward shaping share the same behavioral dimensions.

cs.AI↗
arXiv2026

Job-level Carbon and Water Footprint Estimation for HPC: Bias Assessment from Runtime to Full Life Cycle

High performance computing evaluation has traditionally focused on performance and energy, but these metrics alone cannot capture the sustainability cost of runtime configurations. We proposes a unified job-level water and carbon accounting framework with both operational and embodied impacts. Results show that higher thread counts generally reduce total footprint, but the benefit diminishes at higher thread counts. Water is mainly dominated by embodied impact, whereas carbon is mainly dominated by operational impact.

cs.PF↗
arXiv2026

Isotrivial smooth curves on surfaces

We prove that a smooth projective non-uniruled surface of Picard rank one, generated by an ample and base point free line bundle, cannot be covered by an isotrivial family of smooth curves in the primitive polarisation.

math.AG↗
arXiv2026

PEARL: Auditable Repair for Scientific Reasoning Graph Extraction

Scientific Reasoning Graph Extraction (SRGE) aims to recover explicit links among observations, evidence, intermediate claims, and paper-level conclusions. LLMs can produce graph-like scientific explanations, but their outputs often mix malformed syntax, drifting edge labels, incorrectly oriented roots, and weak source anchors. We propose PEARL (Peircean Extraction via Abstraction and Repair Layer), a training-free framework that turns noisy LLM graph responses into auditable reasoning graphs and repairs them toward strict semantic validity. PEARL first materializes explicit graph content under a closed Peircean schema, then uses matched evidence-grounded judge feedback to repair rejected edge types, local inference steps, and terminal roots while preserving an audit trail. On five 70-paper model archives from ARCHE, a benchmark for latent reasoning-chain extraction, PEARL raises strict gate passes from 0/350 for the LLM baseline to 300/350, with average REA improving from 0.339 to 0.906. The graphs provide a reliability layer for research-agent and AI scientist workflows that need inspectable reasoning traces rather than unconstrained graph regeneration. Code and audit artifacts are available at https://github.com/BohanSu/auditable-repair-reasoning-graphs/tree/300-350_workshop .

cs.AI↗
arXiv2026

Hybrid Rigid-Soft Robotic Gripper with Shape Adaptation, Uniform Force Distribution, and Self-Locking Capabilities

Conventional robotic grippers face a significant challenge in agricultural automation: the trade-off between compliant, adaptive grasping, pressure balancing among all joints, and high load capacity, often at the cost of high energy consumption. This paper presents a novel hybrid rigid-soft gripper that integrated low-cost, membrane-based pneumatic actuators with 3D-printed dual ratchet-pawl mechanisms to simultaneously achieve shape adaptation, uniform force distribution, and energy-free self-locking. The dual-ratchet structure assembled in an offset configuration significantly increased the angular resolution of the joint locking mechanism. Key experimental results demonstrated the gripper's superior performance: a remarkable maximum load capacity of 4200 g, far exceeding that of conventional soft grippers (45-210 g); more uniform force distribution across object sizes (1.75-35.29% difference ratio) compared to a rigid gripper (56.77-66.44%), with peak contact forces remaining below surface damage thresholds; and a 50.05% reduction in total energy consumption to 42.6 J per grasp cycle, achieved by eliminating the need for continuous pneumatic pressure through the self-locking mechanism, compared to 85.28 J for a conventional soft gripper. The combination of additive manufacturing for ratchets and commercially available materials for pneumatic chambers ensured a low-cost and easily fabricated design. These findings validated that the proposed gripper successfully bridged the gap between soft compliance and rigid reliability, offering a robust and efficient solution for scalable agricultural harvesting and manipulation tasks.

cs.RO↗
arXiv2026

Large-Sample Bayesian Approximations for Privatized Data

The increased use of differential privacy (DP) has allowed the sharing of large amounts of data while reducing the risk of disclosure of sensitive information at the individual level. However, the noise introduced by DP methods makes performing statistical inference more challenging. While various methods have been proposed to address different inferential tasks, they often require strong parametric assumptions and/or do not scale well with sample sizes (e.g. U.S. Census products). In response to these limitations, we propose an approximate Bayesian method to analyze privatized data products, which uses a two-step approach of imputing the confidential data and then sampling from the non-private posterior, and which is inspired by the method of Guha and Reiter (2025). We prove that this approximate sampler is asymptotically valid under mild assumptions. While this approach is motivated by Bayesian theory, we show through simulations that it provides conservative frequentist properties as well. We demonstrate the utility of our method by applying it in simulated settings as well as for an analysis on the drivers of homeownership via the 2022 American Community Survey.

stat.ME↗
arXiv2026

Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model

Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements for multi-view consistency, geometric coherence, and robot embodiment constraints. Existing methods typically adapt foundation models with limited robot data, often sacrificing visual knowledge acquired during large-scale pre-training. We present Xiaomi-Robotics-U0, a 38-billion-parameter multimodal autoregressive model for unified embodied synthesis. It treats embodied generation as an extension of foundation image and video generation and jointly optimizes text-to-image generation, image editing, embodied scene generation, embodied transfer, and embodied video generation. This unified framework preserves the generalization of the pre-trained world foundation model while adapting it to embodied settings. Xiaomi-Robotics-U0 is the first model to support high-quality multi-view scene generation across multiple robot embodiments and to introduce structured, controllable embodied transfer for fine-grained editing while preserving multi-view consistency and interaction dynamics. It achieves state-of-the-art results on single-step and sequential generation tasks, outperforming GPT-Image-2.0 in human evaluations of embodied scene generation and transfer, ranking first on World Arena for embodied video generation, and improving the out-of-distribution success rate of pi_0.5 from 36.9% to 63.2% on challenging real-world manipulation tasks. These results show that foundation world models can serve both as embodied world models and scalable data engines for embodied intelligence. Code and checkpoints are available at https://robotics.xiaomi.com/xiaomi-robotics-u0.html.

cs.RO↗
arXiv2026

When is the diagonal contractible?

For a smooth projective complex variety $X$, we study the problem of when there exists a birational morphism $X\times X\to Y$ to a projective variety $Y$ contracting the diagonal $Δ_X\subset X\times X$ to a subvariety of smaller dimension. We prove this happens if and only if various conditions related to the Albanese morphism of $X$ are satisfied. We also give necessary and sufficient conditions for the existence of a contraction which is an isomorphism outside the diagonal and initiate the problem of understanding contractions of diagonals in higher products.

math.AG↗
arXiv2026

Understanding and Mitigating the Video-Action Generalization Gap via Temporal Ratio

Generative video foundation models exhibit strong compositional priors, yet world-action models (WAMs) and video-action models (VAMs) often lose these priors after finetuning on robotic action data. We refer to this discrepancy as the video-action generalization gap. In this paper, we systematically investigate this gap by evaluating a comprehensive design space of VAMs, demonstrating that standard design choices yield no emergent explanation pattern. To explain this behavior, we introduce the Temporal Ratio (TR), an attention-based measure of how strongly the action head relies on future latent rollouts relative to the anchored current frame. TR has two key properties: first, a model's structural reliance on future-predictive latents, measured via TR, acts as a predictor of its compositional generalization capacity; second, it natively fluctuates based on task phase, shifting attention to future frames during planning and reverting to the present frame for precise manipulation. Finally, based on these findings, we propose an inference-time adaptive guidance method, which exploits this intrinsic feature attention pattern to dynamically amplify compositional video conditioning signals precisely when the policy relies on future rollouts. Evaluated on the LIBERO benchmark and real-world tasks, our approach mitigates the OOD-ID compositional generalization gap. More details: https://umishra.me/temporal-ratio/

cs.CV↗
arXiv2026

Nested Simulation Methods for Sobol' Index Estimation: Bias Correction, Budget Allocation, and Latin Hypercube Sampling

Estimating the variance of a conditional expectation is a recurring problem in stochastic simulation, with applications in global sensitivity analysis and Sobol' index estimation. This paper revisits Sobol' index estimation through the lens of nested simulation and develops a unified comparison of classical pick-freeze estimators and nested simulation estimators under a common computational budget. We show that several standard pick-freeze estimators can be interpreted as nested simulation estimators with fixed inner-level sample sizes, enabling direct performance comparisons and clarifying their bias-variance behavior. Building on this perspective, we analyze the standard nested simulation estimator for the Sobol' index numerator and propose two jackknife-based extensions: an unbiased jackknife estimator and a split jackknife estimator that uses an independent preliminary sample to estimate the mean. Under crude Monte Carlo (CMC), the split jackknife estimator attains the canonical mean squared error (MSE) rate, whereas the standard nested simulation and unbiased jackknife estimators attain the slower nested simulation rate. We also characterize the associated allocations of outer- and inner-level simulation effort. Finally, we study the impact of Latin hypercube sampling (LHS), showing that it can improve the standard nested simulation estimator while undermining bias reduction in jackknife-based estimators unless the inner-level sample size grows with the total budget. Numerical experiments corroborate the theory and provide practical guidance on estimator selection for Sobol' index estimation under CMC and LHS.

stat.ME↗
arXiv2026

Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulation

Massive Activations (MAs) have been widely observed in Transformer-based models, yet their structure and functional roles in Diffusion Transformers (DiTs) remain insufficiently understood. In this work, we systematically analyze MAs in representative DiTs and find that they are spatially distributed across image tokens while concentrated in a small set of fixed feature dimensions. We further show that these dimensions are closely aligned with AdaLN residual scaling factors and are primarily modulated by the denoising timestep rather than text conditions. This structure leads to two task-dependent effects: for generation, MAs are critical for fine-grained detail synthesis while having limited influence on global semantics; for understanding, their shared high-magnitude directions make raw DiT features overly similar across spatial tokens and weaken dense feature discrimination. Based on these findings, we introduce Eliciting Massive Activation (EMA), a training-free framework that leverages Massive Activations (MAs) as a unified modulation signal to improve both generative and representational capabilities of DiTs. For generation, EMA proposes MA-driven Detail G}uidance (DG), which suppresses MA dimensions to construct a detail-deficient counterfactual prediction and guides sampling toward finer visual details. DG further supports efficient partial-forward inference, integration with classifier-free guidance, and token-level Local DG for refining selected image regions. For understanding, EMA introduces MA-modulated REPresentation extraction (MREP), which uses pretrained AdaLN channel-wise modulation to reduce MA directional dominance and concatenates spatially normalized MA maps to preserve useful spatial structure. Extensive experiments demonstrate that EMA consistently improves both the generation quality and representation capability of DiTs.

cs.CV↗
arXiv2026

HieDG: A Hierarchical Discrete Geometry-Guided Framework for Multi-Animal Tracking

Multi-animal tracking (MAT) is critical for wildlife monitoring and behavioral analysis, yet remains challenging due to uniform appearance, high density, and irregular motion. Existing methods typically follow heuristic- or query-based paradigms: the former relies on handcrafted geometric associations without end-to-end optimization, whereas the latter enables joint optimization but relies heavily on appearance embeddings. In such conditions, continuous geometric embeddings can be unstable, as small coordinate perturbations may disproportionately alter cross-frame attention weights, degrading identity association performance. To address this limitation, we propose HieDG, a Hierarchical Discrete Geometry-guided tracking framework that reformulates geometric dynamics as structured discrete representations within a query-based tracker. Instead of directly using raw geometric signals, HieDG employs a two-stage residual codebook to discretize position, scale, and velocity cues, transforming unstable continuous geometry into structured, stable discrete tokens. These tokens are aligned with visual embeddings and integrated into the tracking queries to enhance identity consistency. Extensive experiments on animal-specific benchmarks (AnimalTrack, BFT, and BuckTales) demonstrate state-of-the-art association performance with significant improvements in HOTA, AssA, and IDF1. Additional evaluations on generic multi-object tracking benchmarks, including DanceTrack and SportsMOT, show competitive performance, indicating the broader applicability of discretized geometric modeling beyond animal-specific scenarios.

cs.CV↗