Searcharxiv⌕ Search

arXiv subjects

Tao Sun

Publications and source records attributed to Tao Sun.

At least 19 recordsLinked to original sources
arXiv2026

Solution-space heterogeneity shapes federated learning dynamics across partial differential equations

In natural science applications, federated learning (FL) enables collaborative training of models that approximate solutions to partial differential equations (PDEs) for repeated use in distributed settings. However, the input conditions of FL-PDE training samples involve multiple coupled parameters, making data heterogeneity across clients difficult to analyse. We propose solution-space PDE-Dirichlet, which groups existing solution labels into task-specific bins and distributes samples using the classical Dirichlet allocation rule in FL, providing a common partitioning approach across PDE tasks. Theoretical analysis shows an association between differences in solution-bin composition and gradient disagreement, while experiments on three controlled operators and four public simulation datasets quantify the relationships between this heterogeneity, gradient disagreement and prediction error. Based on this connection, we develop Solution-Bin Controlled Federated Optimization, which uses pooled bin-gradient prototypes to correct the component of client gradients associated with bin composition while preserving the sample-weighted training objective. Experiments on low-viscosity Burgers and Darcy flow show that this correction reduces prediction error compared with federated averaging and narrows the gap from bin-balanced IID training.

cs.LG↗
arXiv2026

Adaptive Momentum Benefits Score-based Generative Models

Score-based Generative Models (SGMs) have achieved remarkable success in generation tasks by establishing a diffusion process that gradually perturbs real data into Gaussian noise and then learning a reverse process to reconstruct the data from noise. However, conventional denoising methods, such as Langevin dynamics and numerical stochastic differential equation solvers, rely on randomness but suffer from slow generation speeds due to the high number of score function evaluations. To address this, we propose a plug-and-play Markov adaptive momentum sampling method, inspired by the strong connection between the SGMs' sampling process and stochastic gradient descent optimization. Our approach accelerates the transformation process without introducing additional hyperparameters. Theoretically, we establish a rigorous foundation by analyzing the relationship between the distribution of samples generated by our method and the original data distribution. This provides a novel perspective on the analysis of sampling distributions. Empirically, our method demonstrates superior efficiency, generating high-quality images/graphs in significantly fewer sampling steps, achieving a speedup of 2x to 5x while maintaining or surpassing baseline performance on various image and graph generation benchmarks. These results underscore the effectiveness of adaptive momentum in enhancing the efficiency of SGMs.

cs.LG↗
arXiv2026

MoLS: SNR-Guided Module-Wise Learning-Rate Calibration for Large Language Models

Large language models (LLMs) contain functionally distinct modules with heterogeneous gradient statistics. Although Adam(W) adapts updates at the parameter level, selecting relative learning rates across modules often relies on costly manual tuning. We study this problem through gradient signal-to-noise ratio (SNR). Our analysis identifies structural sources of module-wise SNR differences and relates SNR to the attenuation of Adam's normalized mean-gradient component. Based on these findings, we propose \textbf{Module-wise Learning Rate Scaling via SNR (\name)}, a lightweight method that replaces manual multiplier search with one-shot calibration. MoLS estimates module-level SNRs after an initial adaptation period and uses inverse-square-root scaling to determine relative learning-rate multipliers. The multipliers are introduced smoothly during warmup and then held fixed while the global learning-rate schedule continues. Our theoretical results quantify the effect of calibration and its sensitivity to estimation error and relative SNR drift. Extensive experiments across LLM pre-training and fine-tuning show that MoLS reduces perplexity and improves downstream accuracy with minimal computational overhead. It achieves performance comparable to carefully tuned module-specific learning rates and integrates with memory-efficient optimizers and parameter-efficient fine-tuning.

cs.LG↗
arXiv2026

Plan First, Act Later: Streaming Reasoning for Executable Memory in Robot Control

Long-horizon robot manipulation requires a robot to remember task-relevant information beyond its short observation window. Existing memory-augmented policies typically retrieve relevant information from history and reason over it at execution time, placing a heavy reasoning burden on the high-level model. To address this challenge, we propose PAL (\textbf{P}lan first, \textbf{A}ct \textbf{L}ater), a hierarchical memory framework for vision-language robot manipulation. It maintains a short-term visual buffer, a semantic-event memory, and an executable \texttt{subtask\_list}. A high-level vision-language model (VLM) converts streaming visual observations into the \texttt{subtask\_list}. At execution time, the VLM selects the currently relevant subtask from the \texttt{subtask\_list} and passes it to a low-level vision-language-action (VLA) policy. To teach the model what to write to memory and when to update it, we introduce a two-stage data generation procedure that first expands sparse update supervision and then uses self-labeling with task-grounded verification to generate training data that better match the state distribution encountered during execution. We evaluate our approach on memory-dependent benchmarks and real-world manipulation tasks. On RoboMME, PAL achieves a \textbf{56.05\%} success rate, outperforming the strongest baseline, FrameSamp-Modul, at 44.51\%. In real-world experiments across four manipulation tasks, \pal{} reaches \textbf{60.83\%} overall success, surpassing MemER (45.00\%) and FrameSamp-Modul (28.33\%). These results show that proactively writing future-relevant subtasks into hierarchical memory improves long-horizon visual reasoning and robot control. Code and videos can be found on our website: https://qinghangliu.github.io/pal-webpage/

cs.RO↗
arXiv2026

GeoNaviDiff: Transferring Disentangled Semantic Controls to Diffusion Features via Local Riemannian Navigation

Disentangled real-image manipulation requires factor-specific semantic control while preserving image fidelity and non-target content. StyleSpace $S$ provides interpretable controls but is limited by GAN inversion, whereas diffusion models offer stronger image realization without an explicit factorized control basis. We introduce GeoNaviDiff, an unsupervised cross-space framework that transfers disentangled StyleSpace interventions to local Riemannian trajectories in diffusion $h$-space. GeoNaviDiff constructs reconstruction-decoupled supervision by extracting a spherical Log-map tangent from a matched StyleGAN reconstruction-edit pair and parallel-transporting it to the real-image diffusion state. A shared, factor-conditioned Navigator predicts this tangent at inference, while norm-preserving geodesic realization and source-anchored rollout stabilize the reverse process without edited references or factor-specific models. Experiments across multiple datasets show that GeoNaviDiff outperforms the compared methods in fidelity, factor selectivity, edit locality, and trajectory smoothness.

cs.CV↗
arXiv2026

Photon-conserving Raman soliton attractors in focusing and defocusing Kerr media

The sign of the Kerr nonlinear coefficient has long been regarded as irrelevant to the direction of the Raman-induced soliton self-frequency shift. Yet the standard generalized nonlinear Schrödinger equation (GNLSE) predicts a frequency shift that depends on the sign of the nonlinearity, which leads to an unphysical blue shift in the defocusing case. We resolve this inconsistency by deriving the time-domain form of the photon-conserving GNLSE (pcGNLSE) from its established frequency-domain counterpart. The derivation reveals that photon-number conservation imposes two sign modifications relative to the standard GNLSE: the Raman-shift coefficient acquires the absolute value of the Kerr nonlinear coefficient in place of its signed counterpart, and the self-steepening-Raman dissipation term likewise carries an absolute-value prefactor rather than a signed one. These two modifications jointly guarantee a universal spectral redshift and monotonically decreasing pulse energy during propagation, irrespective of the signs of the Kerr nonlinear coefficient and its frequency derivative. Applying the method of moments to the time-domain pcGNLSE with appropriate chirped ansätze, we derive closed-form evolution equations for five pulse parameters and establish explicit attractor conditions under which bright or dark Raman solitons propagate with constant peak power. Direct numerical integration of the pcGNLSE confirms all analytical predictions and demonstrates that the standard GNLSE fails qualitatively, predicting unphysical energy growth and spectral blueshift in the negative-nonlinearity regime. The results provide a rigorous analytical framework for Raman soliton dynamics in materials with negative third-order susceptibility, with direct implications for soliton-based devices in emerging semiconductor waveguide and microresonator platforms.

physics.optics↗
arXiv2026

ARC: A Reasoning Recipe for Robot Foundation Models

The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations, and costly training at scale. We show that there exists an effective and efficient complementary approach: the right reasoning recipe can substantially improve the zero-shot task performance of existing state-of-the-art RFMs. We refer to this recipe as ARC. It consists of three key ingredients: a reasoning trace, a scalable automatic labeling pipeline, and a strategy for adapting pretrained RFMs to use these traces for control. First, we find that effective reasoning traces should be grounded in the robot's next action and explain its causal structure: why the action is appropriate and what effect it should produce. Second, we show that these traces can be generated automatically from existing demonstrations, enabling us to construct ARC-Trace-DROID from DROID without collecting new robot data. Third, we show how state-of-the-art VLAs such as $π_{0.5}$ and WAMs such as Cosmos3-Nano-Policy can learn to use these traces for control, with fine-tuning and inference tailored to each model's architecture and capabilities. Using ARC, we obtain gains in zero-shot RFM performance that, to our knowledge, are unprecedented without additional robot demonstrations or foundation-scale training. The adapted models establish a new state of the art on RoboLab-120 and MolmoSpaces, with gains of up to 50 percentage points on RoboLab-Reasoning-50. On real robots, ARC improves $π_{0.5}$'s task success by 82.2 percentage points. Project website: https://arc-robot-reasoning.github.io/

cs.RO↗
arXiv2026

UP-MOPD: Update Projection in Multi-Teacher On-Policy Distillation

On-policy distillation from multiple teachers combines expertise from different domains in a single student, but conflicting gradients can hinder this integration. Gradient corrections directly constrain parameter updates under plain SGD. With optimizers such as AdamW, however, momentum, adaptive scaling, and weight decay can turn a corrected gradient into an update that increases a domain loss to first order. To address this gap, we propose Update Projection for Multi-Teacher On-Policy Distillation (UP-MOPD). UP-MOPD lets the original mixed gradient update the optimizer state and generate a candidate displacement, then projects only violating candidates before they are committed to the parameters. The projection gives the unique feasible update closest to the candidate in Euclidean distance. In experiments combining medical and general domains, UP-MOPD improves IFEval-loose accuracy late in training by 2.96 points over vanilla M-OPD. It achieves an average score of 60.03 across eight metrics, compared with 59.00 for gradient projection and 59.15 for update rejection. On a public benchmark covering mathematics, code, and instruction following, it achieves the best average across six tasks (32.67), leads on LiveCodeBench v5, and ties for the best IFEval result.These results support projecting optimizer updates to reduce interference between domains.

cs.CV↗
arXiv2026

Visual Sim-to-Real Learning for Robotic Insertion under Geometric Variations: Application to Rebar Installation

Rebar insertion is among the most repetitive and physically demanding tasks on construction sites, and a contact-rich problem at 1.4 mm clearance. The parts, however, vary at two levels: a nominal design per structural member, and fabrication tolerance around each nominal design. Real-world data therefore has to be re-collected as designs and batches change. We present RebarSim, a visual sim-to-real system trained entirely in simulation. A privileged state-based teacher is trained with reinforcement learning over procedurally generated rebar geometries, then distilled into a multi-view student that maps raw RGB and proprioception directly to actions under extensive domain randomization. The student transfers to the real world zero-shot, seating rebars taken from a real factory production run in 91.3% of real-robot rollouts. Underlying that result, geometry diversity and pretraining both bring benefits. Training across a diverse set of nominal designs rather than one lifts the zero-shot success of both the teacher and the student on unseen designs, and the student policy outperforms a single-design specialist on that specialist's own design. A pretrained student then adapts to a new design with 4--6x fewer distillation samples than one trained from scratch. Visual sim-to-real transfer depends on appearance randomization and the DAgger mixture: removing either one sharply lowers success. Videos, code, and task assets are available at https://rebarsim.github.io.

cs.RO↗
arXiv2026

FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations

Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial geometry and motion evidence. Most feed-forward methods infer articulation from a single observation and therefore rely heavily on learned category-level shape priors. We present FAMOS, a feed-forward model that predicts movable-part segmentation and joint parameters from a sparse, unordered set of partial point clouds. Our model jointly reasons over multiple observations and naturally supports a variable number of inputs, including a single view. To aggregate articulation cues across observations, we introduce a Multi-state Articulation Transformer with alternating state-wise and global attention. We further propose an observed articulation span objective that supervises the motion range each part exhibits across the input observations, encouraging the model to leverage the full observation set. To overcome the limited scale and diversity of existing datasets, we introduce a procedural data generator that synthesizes self-annotated assets during training. Experiments on PartNet-Mobility, ACD, and ArtiCraft-10K demonstrate consistent improvements over both feed-forward and optimization-based baselines. Project page: https://kevinqu7.github.io/famos

cs.CV↗
arXiv2026

MuJoCable: Reduced-Order Surface-Routed Cable Transmission for Tendon-Driven Robots

Tendon transmissions reduce distal inertia and add compliance, yet routing, slack, and friction govern motion and force transfer. Mainstream rigid-body robotics simulators such as MuJoCo do not jointly resolve moving noncircular contact, unilateral tension, and segment friction. We present MuJoCable, which adds a reduced-order, configuration-dependent cable transmission to MuJoCo. Its routing algorithm jointly optimizes an ordered path across moving analytic and mesh surfaces. A unilateral axial law, directional Capstan propagation, and nodal virtual work map this path to segment tensions and body forces. The warm-started engine plugin applies these forces during simulation and exposes route and load states for design. Pulley benchmarks recover analytical transmission relations with a Capstan-ratio error below 0.5%. On the underactuated 18-joint SpiRobs, MuJoCable reveals friction-driven load growth and proximal redistribution of joint rotation that the native tendon does not represent. Hardware tests on SpiRobs and a tendon-route-coupled finger reproduce observed motion sequences. By making physical threading executable, MuJoCable brings transmission sources of the simulation-to-reality gap into route, cable, and actuator design before fabrication.

cs.RO↗
arXiv2026

Knowledge-Guided Hierarchical Policy Learning for High-Precision Cylindrical Assembly under Tight Tolerances

A hybrid hierarchical learning framework is proposed to achieve high-precision assembly of 170mm cylindrical components with tolerance of 0.1mm. The lower-level network integrates expert experience through Behavior Cloning (BC), giving the robot human-like intuition, and incorporates the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm to enhance training stability and robustness. The upper-level network dynamically adjusts the lower-level decisions based on heuristic rules, ensuring flexibility in operations. A simulated model is constructed to learn before transferring to real world. An efficient and safe training is allowed. Comparisons show that the reward curve converges within 500 episodes, indicating high learning efficiency. It also demonstrates better adaptability to initial conditions and pose errors, achieving satisfactory success rates even under extreme conditions. Moreover, the method exhibits good stability under Gaussian noise interference. In the real world, the assembly trajectory of the cylindrical segment shows smoother motion and less fluctuation.

cs.RO↗
arXiv2026

SolarBench: A global solar energy nowcasting benchmark

As the share of solar power grows, nowcasting weather-driven solar variability becomes critical for reliable energy system operation. State-of-the-art approaches increasingly apply deep learning to sky camera and geostationary satellite observations, but fragmented datasets and inconsistent evaluation make it difficult to determine whether reported improvements generalize across climates, cloud regimes, and photovoltaic (PV) systems. Here we introduce SolarBench, an open global benchmark for image-based solar nowcasting. SolarBench harmonizes more than six million sky and satellite images from 11 diverse sites spanning a decade, together with irradiance or PV output and auxiliary atmospheric data. An accompanying toolbox supports reproducible data access, processing, model development, and evaluation. Using SolarBench, we benchmark representative models and reveal a gap between average forecasting accuracy and the ability to capture rapid solar fluctuations. We further quantify predictability across cloud regimes and demonstrate data-efficient adaptation to new PV systems. SolarBench provides an extensible foundation for fair comparison and methodological innovation in solar nowcasting.

cs.CV↗
arXiv2026

GWT: Scalable Optimizer State Compression for Large Language Model Training

Training large language models (LLMs) requires substantial memory, a significant fraction of which is consumed by the moment states maintained by adaptive optimizers such as Adam. Existing memory-efficient approaches commonly compress parameters or gradients through low-rank projections, which may discard information outside the selected subspace or incur additional costs from subspace construction and singular value decomposition (SVD). We introduce \textbf{Gradient Wavelet Transform (GWT)}, an SVD-free framework that applies a multilevel Haar transform to matrix gradients. GWT maintains first- and second-moment states only for the compact approximation coefficients, while retaining all detail coefficients transiently in each update. We show that the orthogonal transform preserves the complete current gradient and establish gradient alignment and a stationary-point guarantee for smooth objectives under bounded preconditioning and a directly verifiable coarse-momentum coherence condition. Experiments on language-model pre-training and downstream fine-tuning show that GWT reduces estimated model-and-optimizer-state memory by up to 52\% while maintaining competitive or improved model quality. On LLaMA-3B pre-training, GWT achieves $1.9\times$ the throughput of 8-bit Adam and is compatible with multiple optimizer families, including Adam, Adam-mini, and Muon.

cs.LG↗
arXiv2026

Geometric Parametric Instability in Nonlinear Multipass Cells

Geometric parametric instability (GPI) is the resonant growth of discrete spectral sidebands enabled by longitudinally periodic multimode evolution and has been studied primarily in graded-index fibers. Here we show theoretically and numerically that GPI can occur in gas-filled nonlinear multipass cells (MPCs). By mapping a mode-matched MPC onto an equivalent waveguide, we derive a Floquet quasi-phase-matching condition governed by the single-pass Gouy-phase imbalance of the signal--idler pair relative to the pump pair. The theory predicts the small-signal gain and bandwidth. A pump-depleted coupled-mode model (CMM) further relates the maximum converted fraction to the residual phase mismatch. The CMM predicts multiple geometrically tunable sideband pairs associated with different radial indices and Floquet orders. For argon at $5$~bar, varying the cavity geometry shifts the sideband detuning from approximately $96$ to $46$~THz when the $p_{\mathrm{s}}=1$, $h=0$ branch is considered. A truncated multimode generalized nonlinear Schrödinger equation (MMGNLSE) model is used for numerical simulations with a semiclassical stochastic seed corresponding to one photon per spectral mode. The MMGNLSE simulations reproduce the predicted sideband frequencies and reveal pump depletion and competition among the retained radial channels. GPI in MPCs may therefore limit spatial beam quality in nonlinear pulse compression while providing a tunable mechanism for broadband multicolor generation.

physics.optics↗
arXiv2026

ConRub-Med: Reinforcement Learning with Consensus Rubrics for Open-Ended Medical Question Answering

Reinforcement learning with verifiable rewards has been especially effective in mathematics and coding, where answers can be checked automatically. Many open-ended medical questions lack comparably cheap outcome verifiers: responses may be partly correct, incomplete, or contain clinically consequential errors. Rubrics written or validated by physicians offer strong clinical grounding, but involving experts in every instance is costly. Model-generated rubrics make this supervision scalable. We introduce ConRub-Med to preserve useful distinctions as rubric feedback moves from construction to policy optimization. For each prompt, three heterogeneous language models propose atomic criteria independently; a separate model reviews them, retaining only criteria with semantic support from all three generators. Three-State scoring distinguishes correct coverage, missing information, and incorrect claims. Errors receive negative rather than zero credit. When every response in a complete Group Relative Policy Optimization (GRPO) group receives the same final reward, a pairwise judge provides sequence advantages only if both candidate orders agree, without changing the scalar rewards. Groups without ties use vanilla GRPO. In a blinded study matched by question, two medical experts rate panels from the full pipeline as more clinically relevant than panels produced by one generator. Across the evaluated open models, ConRub-Med ranks first on six of nine benchmarks and achieves the highest medical and generalization averages. Using the resulting rubric dataset of 5,166 prompts, it scores $38.98 \pm 1.04$ (mean $\pm$ SD) on HealthBench-Hard, compared with InfiMed-ORBIT's 33.60 with 8,000 samples and 37.30 with 28,000.

cs.CL↗
arXiv2026

The Sample Pre-selection and Characterization Station at the SECUF: Instrumentation, Capabilities, and Representative Scientific Achievements

The Synergetic Extreme Condition User Facility (SECUF) is a comprehensive, state-of-the-art user facility designed to provide integrated extreme physical conditions-including ultrahigh pressure, ultralow temperature, strong magnetic fields, and ultrafast optical fields-for frontier research in condensed matter physics and materials science. Within SECUF, the F2 Sample Pre-selection and Characterization Station plays a pivotal supporting role. Its mission is to provide comprehensive sample synthesis, processing, pre-screening, and characterization services to prepare high-quality specimens for subsequent experiments under extreme conditions. This paper details the specifications and performance of ten core instrument systems within these units. Furthermore, we highlight several breakthrough scientific achievements enabled by the F2 Station, encompassing the discovery of novel quantum spin supersolid states, pressure-induced high-temperature superconductivity in nickelates, giant anomalous Hall angles, and molecular water in lunar soil. We also outline ongoing technical developments that expand the station's capabilities, such as integrated high-pressure cells and self-built ancillary measurement systems.

cond-mat.str-el↗
arXiv2026

Generative Bayesian Filtering for State Estimation

The state of a dynamic system evolves over time, switching among several latent modes that govern its observable behavior. Filtering methods infer the latent state from observations. Classical filtering approaches, including Kalman filters, typically rely on simple observation models, such as linear-Gaussian models, that are incapable of characterizing the increasingly nonlinear and heterogeneous patterns in high-dimensional sensor signals. To tackle the challenge, we propose Generative Bayesian Filtering (GBF), a filtering framework that replaces restrictive observation models with pretrained conditional generative models parametrized by conditional variational autoencoders (CVAE). For online inference, GBF performs a Bayesian prediction-update recursion in which the measurement update is formulated as a posterior sampling problem that combines the dynamical prior with the CVAE-induced likelihood. The resulting filtering problem is then transformed into a score-based sampling problem, which naturally inherits the flexibility from generative models and the uncertainty quantification capabilities from ensembling. Experiments on synthetic datasets and real-world applications involving manufacturing system monitoring and arrhythmia diagnosis demonstrate that GBF improves state estimation accuracy and robustness relative to baseline approaches.

cs.LG↗