arXiv subjects

Shuo Yang

Publications and source records attributed to Shuo Yang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Rigorous Statements and Proofs of the Lemmas in Simon's Algorithm for the Dihedral Coset Problem and Their Underlying Hypothesis

In a recent preprint, Simon proposed a polynomial-time quantum algorithm for the Dihedral Coset Problem and rested the analysis on four lemmas. Three of them carry only proof sketches, and this paper gives each of those three a statement that admits a single reading together with a complete proof. Lemma 1 follows from an exact second-moment computation for the subset-sum counts, and it holds with probability tending to one in place of the constant originally claimed. The amplitude bound of Lemma 3 follows from an exact Parseval identity on the cube of measurement outcomes and holds at every threshold with no well-behavedness hypothesis, so that predicate leaves the argument entirely. For Lemma 4, we compute both balls-in-bins covariances exactly and find that the second carries a term a fixed ball count leaves out. The assumption that the distinguished group contains no faulty samples can also be dropped. The two branch amplitudes share a signed prefactor, so the counting estimates control their difference and not the ratio the lemma states. We prove the additive form and show that the closing argument consumes nothing more than that. A single hypothesis survives all of this. It asks that the partition into the two sides be fixed independently of the measured string, and the rule the algorithm gives for choosing that partition does not supply it. Establishing these four lemmas therefore does not by itself establish the correctness of the algorithm.

cs.CR↗

arXiv2026

Neural Tree Collaborative Filtering: Rethinking Graph Collaborative Filtering as Tree Collaborative Filtering with Curvature-Aware Propagation Depth

Graph Collaborative Filtering (GCF) has become the dominant paradigm in modern recommender systems by modeling user-item interactions as a bipartite graph and propagating embeddings through a fixed number of message-passing layers. However, applying a uniform propagation depth to every node ignores a fundamental property of real interaction graphs: nodes differ substantially in their local connectivity, so peripheral nodes quickly suffer from over-smoothing while hub-like nodes remain under-explored beyond their immediate neighborhood. In this paper, we revisit GCF from a tree-structured perspective and propose Neural Tree Collaborative Filtering (NTCF), a framework that re-interprets each node's local neighborhood as a rooted tree and assigns a node-specific propagation depth based on a closed-form local-degree-imbalance score that serves as a discrete Ricci-curvature proxy. We provide a theoretical analysis showing that (i) NTCF strictly generalizes NGCF, degenerating to NGCF when all curvature-induced depth adjustments vanish (a lower bound on its representation power), and (ii) the curvature-aware schedule retains strictly more discriminative information at deep layers on positively-curved (peripheral) nodes than uniform-depth propagation. NTCF can achieve higher performance than most widely used GCF backbone models and can be integrated into existing advanced self-supervised models as a backbone, replacing their original backbone to achieve enhanced performance. Extensive experiments on three public datasets demonstrate the superiority of NTCF.

cs.IR↗

arXiv2026

Diamond-to-graphite transformation under hypersonic impact

Diamond to graphite transformation is a complex kinetically driven process which has been studied under various conditions for its fundamental importance. We report the transformation of diamond embedded ceramic matrix composites during hypersonic impact. Diamond particles embedded in cubic boron nitride matrix provide a superhard composite that was subjected to high impact collisions of metal projectiles travelling at speeds reaching Mach 8.45. Our observations suggest that the energy absorption and fracture of the composite is primarily enabled via the phase change of diamond into graphite. Characterization of the impact-fractured composite shows transformed diamond particles and provides details of the shock-induced phase transformation and the nature of diamond-graphite interfaces formed during rapid phase change. The study provides new understanding of phase transformation of diamond under extreme conditions.

cond-mat.mtrl-sci↗

arXiv2026

Statistical Study of Solar Prominence Plumes Based on NVST H$α$ Observations

Plumes are one of the most representative dynamic features observed in prominences and play a key role in mass and magnetic transport within them. However, their physical nature and triggering processes remain actively debated. Based on limb H$α$ observations from the New Vacuum Solar Telescope (NVST) during 2013--2025, we statistically investigated 34 plumes with clear and complete evolutions by developing an automated image-processing pipeline. It is revealed that plume lifetimes mainly range from 300 s to 700 s, with vertical displacements between 3--7 Mm. The mean widths and velocities are concentrated in the range of 0.5--1.5 Mm and 10--20 km s$^{-1}$, respectively. Besides wide distribution ranges, plume parameters exhibit irregular evolution fluctuations, indicating that the formation and evolution of various plumes may exhibit different physical patterns. Correlation analysis among the parameters further reveals that: (1) Positive correlations were found among lifetime, vertical displacement, and mean width, indicating an intrinsic coupling between the temporal and spatial scales of plumes. (2) Trajectory curvature is negatively correlated with lifetime, vertical displacement, and velocity. Accelerating and width-contracting plumes typically have lower curvature, suggesting that curvature may reflect environmental influences and the stability of plumes. (3) Plumes with higher initial velocities were more likely to be accompanied by precursor brightening, suggesting that these plumes may be triggered by magnetic reconnection. Furthermore, we infer that some plumes in non-bubble regions may be inherently driven by mini-filament eruptions. These results establish a statistical framework for prominence plumes and reveal diversity in their dynamical evolution and triggering mechanisms.

astro-ph.SR↗

arXiv2026

Parent Hamiltonian and intrinsic phase transition in non-Hermitian photonic systems

Non-Hermitian systems host phenomena absent in Hermitian physics, but realizing Hamiltonians with intrinsic non-Hermitian properties remains challenging. The theoretical method of non-Hermitian parent Hamiltonian (NH-PH) enables the construction of a non-Hermitian system from a pair of matrix product states (MPSs) with tailored properties. Here, we report the first experimental generation of NH-PHs. This generation starts from MPSs that represent asymmetric Affleck--Kennedy--Lieb--Tasaki (AKLT) states. The construction is validated with single photons via imaginary-time evolution of the generated NH-PH to obtain its left and right ground states. We then characterize the properties of the system by measuring four different order parameters that probe non-reciprocal correlations, chiral imbalance, and conventional antiferromagnetic correlations. Furthermore, extending the framework to a larger system with a different model, we observe an intrinsic non-Hermitian phase transition, manifested by abrupt jumps of an order parameter when the designated zero-energy modes cease to be the globally lowest-energy states. Our work provides the first experimental realization and characterization of non-Hermitian Hamiltonians with controllable and customizable properties, opening new avenues for exploring intrinsic non-Hermitian phenomena across diverse physical platforms.

quant-ph↗

arXiv2026

Divergence Decoding: Training-Free Capability Fusion

While large language models excel in reasoning, these generalists often lack knowledge for specialized scientific domains. Conversely, domain models~(specialists), while knowledgeable, suffer from specialization side-effects including diminished logic and reduced robustness.To address this dilemma, we introduce Divergence Decoding, a training-free framework for capability fusion. It reconstructs the "draft-and-verify" skeleton of speculative decoding into an adaptive routing mechanism. The core is using Jensen-Shannon divergence to monitor the distributional disagreement between the two models at each token. When the specialist exhibits significant divergence, our method identifies it as a potential reasoning risk and instantaneously routes control to the generalist. This allows the dynamic injection of general reasoning while preserving domain expertise, achieving inference-time policy composition of the generalist and the specialist.We evaluate Divergence Decoding across diverse model families (Qwen and Llama series) on challenging scientific benchmarks (GPQA, ChemBench, and ChemCoTBench). Experimental results demonstrate that Divergence Decoding outperforms both the domain-specialized and general-purpose models, effectively surpassing the performance of most single-model baseline. This suggests that Divergence Decoding provides a general, training-free paradigm for fusing diverse LLM capabilities through adaptive inference-time collaboration.

cs.AI↗

arXiv2026

One Graph, Multiple Gains: Single High-Quality Item-Item Graph for Multimodal Recommendation

Multimodal recommendation leverages item multimodal features alongside collaborative signals to capture user preferences. While item-item graphs have become a key building block in advanced models, existing methods typically construct them with noisy similarity edges and limit their role to a single function of item-item representation propagation, leaving substantial potential untapped. In this paper, we propose IIMRec, a framework that constructs a single high-quality item-item graph during preprocessing and systematically reuses it across three stages of the recommendation pipeline: representation enhancement, interaction graph enhancement, and optimization enhancement. The graph is built by fusing semantic and co-occurrence signals, then refined via Neighborhood Consistency Edge Reweighting (NCER), which applies the triadic closure principle to amplify structurally reliable edges and suppress spurious ones. Once constructed, the graph is leveraged in three complementary ways: (1) Item-item propagation with a Residual II Gate (RIG) that adaptively controls per-item absorption of semantic neighborhood signals for representation enhancement; (2) A content-guided UI graph expansion that introduces virtual user-item edges through high-confidence semantic neighbors for interaction graph enhancement; (3) II-Neighbor BPR Augmentation (INA) that treats top neighbors of positive items as discounted soft positives for optimization enhancement. We provide theoretical analysis showing that NCER reduces the spectral noise-to-signal ratio, RIG converges to a non-degenerate gating regime, and INA yields a tighter generalization bound. Extensive experiments on four datasets demonstrate that IIMRec consistently outperforms state-of-the-art baselines while running faster and consuming less GPU memory, with particularly strong gains under cold-start and sparse-interaction conditions.

cs.IR↗

arXiv2026

MoE-Based Learned Inertial Odometry for Bicycle Localization

GNSS suffers from multipath errors in urban canyons, making reliable bicycle localization difficult. Hand-crafted inertial alternatives, such as cycling dead reckoning and nonholonomic constraints, fail to generalize across riders, postures, and road surfaces. This work implements learned inertial odometry for bicycle localization: a neural velocity predictor, trained on multirider, multi-bicycle, and multi-surface IMU data, is tightly coupled with an extended Kalman filter for three-dimensional pose estimation, replacing hand-crafted cycling models with a data-driven representation. To reduce computational overhead, the predictor is realized as a sparsely-gated Mixture of Experts (MoE) network with top-K routing, trained under an alternating parameter-freezing scheme with a per-expert capacity constraint to encourage diverse and balanced specialization.The proposed model attains 0.333 m/s inference error, 9.49 m ATE, and 2.58 m RTE at only 28.76 M FLOPs. This corresponds to approximately 7 times and 9 times fewer FLOPs than the ResMLP and ResNet backbones used in LLIO and TLIO, while maintaining comparable or superior accuracy. The proposed MoE variants further rank first on both ATE and RTE across all evaluation splits, demonstrating strong generalization.

cs.RO↗

arXiv2026

Tensor network characterization and mitigation of readout errors

Readout errors are a major bottleneck to extracting reliable information from near-term quantum processors, especially when spatial correlations are non-negligible. We present a unified tensor-network framework that models the readout process as a matrix product operator (MPO), enabling efficient characterization and mitigation beyond uncorrelated approximations. The MPO model is trained via likelihood optimization on calibration data and applies to multiple tasks, including nonlocal observable estimation, random circuit sampling, and random-measurement protocols, such as classical shadows and learning-based tomography. Experiments on a superconducting processor and numerical simulations up to 20 qubits show that the MPO model captures correlated readout errors that uncorrelated models miss, with a sample cost that grows only near-linearly with system size. When extended to two-dimensional systems, the framework can also be integrated with tensor-network quantum error-correction decoders by performing joint inference over data and readout errors. These results establish tensor-network readout error mitigation as a scalable and versatile approach for noise-aware quantum data processing.

quant-ph↗

arXiv2026

Experience Augmented Policy Optimization for LLM Reasoning

Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for improving the reasoning capabilities of large language models (LLMs). However, existing RLVR methods typically rely on on-policy optimization from scratch, resulting in high sampling costs and inefficient utilization of accumulated experience. As model capabilities and policy behaviors evolve during training, recent attempts to reuse experience via fixed reasoning trajectories further suffer from policy mismatch. Motivated by these limitations, we argue that experience in RLVR should not be reused as fixed reasoning trajectories, but instead expressed in a policy-adaptive manner. In this work, we propose Experience-Augmented Policy Optimization (EAPO), which leverages a prior RL-optimized policy as an action-level experience prior and selectively injects experience at critical decision points during rollout. To ensure stable and unbiased learning from experience-augmented rollouts, EAPO further incorporates an adapted importance sampling scheme. Experiments on using Qwen-2.5-math 7b and Qwen-3-8B on five different benchmarks demonstrate that EAPO consistently improves reasoning performance over state-of-the-art RLVR methods.

cs.LG↗

arXiv2026

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples

Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), yet the training process remains notoriously fragile. In this work, we investigate a critical source of this instability: over-optimization, where models exploit training heuristics at the expense of generalizable reasoning. While reverse KL regularization is the standard defense against such degradation, our analysis reveals that it is often insufficient in this regime, as it fails to ensure comprehensive coverage of the reference distribution. To address this, we propose ARMOR (Anchor Rollout and Mixed Optimization for RL), a framework that shifts the paradigm from passive penalty to active sample stabilization. ARMOR comprises two key components: (1) Anchor Rollout, which leverages off-policy data from the reference policy to preserve established solution patterns; and (2) Mixed Optimization, which reformulates the policy objective to enable controlled exploration without relying on auxiliary losses. Extensive experiments on reasoning benchmarks validate that ARMOR effectively mitigates validation collapse, enabling sustained performance improvements over extended training horizons.

cs.LG↗

arXiv2026

Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing

Automated malware classifiers achieve strong detection performance, but auditing requires more than flagging a sample: analysts must explain malicious behaviors and justify them with code evidence. Traditional signature-based methods and learning-based XAI often fail to provide such support in a human-interpretable form. Large Language Models (LLMs) appear promising, yet their reliability for malware auditing remains unclear. Evaluation faces three challenges: (1) the lack of human-written behavioral ground truth; (2) real-world codebases that exceed current context limits; and (3) the lack of reliable mechanisms to verify whether generated claims are grounded in code evidence. These obstacles make benchmarking difficult and leave model capabilities and failure modes opaque. We introduce MalEval, a diagnostic framework for measuring the capability boundaries of LLMs in malware auditing. MalEval pairs real-world application codebases with expert-written audit reports to provide fine-grained behavior-level ground truth. It compresses large codebases into behavior-relevant program contexts through a context-driven intermediate representation that preserves call relations. Expert reports and model outputs are mapped, via constrained reasoning, into structured evidence chains linking code-level facts to high-level behaviors in a shared space. MalEval decomposes auditing into four stage-wise tasks, enabling each intermediate judgment to be verified under limited context windows. We evaluate seven LLMs and find that they rely on surface cues rather than verifiable evidence, struggle to compose dispersed facts into coherent attack chains, and are highly sensitive to context formulation. These findings shift attention from isolated outputs to reliable LLM and agentic workflows for malware auditing. MalEval is publicly available at https://github.com/ZhengXR930/MalEval.git

cs.CR↗

arXiv2026

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but its sparse trajectory-level rewards offer limited guidance on intermediate decisions, leaving a supervision gap between episode-level outcomes and token-level policy learning. We propose SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills and distills their behavioral effect back into the policy model. SEED first fine-tunes the policy to analyze completed trajectories and generate natural-language skills that capture reusable workflows, decisive observations, or failure-avoidance rules. During RL, the current policy both collects trajectories and serves as the analyzer that extracts hindsight skills from them. Policy updates therefore improve subsequent decision making and skill analysis together, allowing hindsight supervision to evolve with the policy. SEED then re-scores the sampled actions under ordinary and skill-augmented contexts, converting the skill-induced probability shift into a dense token-level on-policy distillation signal. This signal is jointly optimized with outcome-based RL, keeping the auxiliary supervision aligned with the current trajectory distribution. Extensive experiments on text-based and vision-based agentic tasks show that SEED consistently improves performance and sample efficiency, exhibiting robust generalization to unseen scenarios. Our code is available at https://github.com/jinyangwu/SEED.

cs.CL↗

arXiv2026

TouchWorld: A Predictive and Reactive Tactile Foundation Model for Dexterous Manipulation

Dexterous manipulation in everyday environments requires both anticipation and reaction: a robot must predict how contact should evolve while rapidly correcting local errors caused by slip, misalignment, unstable grasping, or force mismatch. Vision and language provide semantic and geometric guidance, but they cannot reliably reveal hidden contact states such as force, slip, and contact stability. Although tactile sensing exposes these physical cues, most existing policies treat touch as a low-frequency observation stream within a monolithic action model, coupling slow task reasoning, action generation, and fast contact feedback in a single loop. We introduce TouchWorld, a predictive-and-reactive tactile foundation model for dexterous manipulation. TouchWorld uses a hierarchical policy that separates vision-language subtask planning, tactile world-model prediction, visuo-tactile goal-conditioned action generation, and high-frequency tactile residual refinement. A High-Level Planning Layer produces executable subtasks and predicts tactile subgoals; a Visuo-Tactile Goal-Conditioned Policy generates nominal action chunks; and a Tactile-Conditioned Refinement Policy performs online residual correction using recent tactile and proprioceptive feedback. By using touch as both a predictive contact reference and a fast feedback signal, TouchWorld preserves the semantic generalization of vision-language-action policies while improving local contact adaptation. Across six long-horizon and contact-rich dexterous manipulation tasks, TouchWorld achieves 65.0% success in the clean setting and 53.7% success under human perturbations, outperforming the strongest baseline by 15.7 and 18.5 percentage points, respectively.

cs.RO↗

arXiv2026

SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing

Diffusion Transformers (DiTs) have become a leading backbone for video generation, yet their quadratic attention cost remains a major bottleneck. Sparse attention reduces this cost by computing only a subset of attention blocks. However, prior methods often either drop the remaining blocks, which incurs information loss, or rely on learned predictors to approximate them, introducing training overhead and potential output distribution shifting. In this paper, we show that the missing contributions can be recovered without training: after semantic clustering, keys and values within each block exhibit strong similarity and can be well summarized by a small set of cluster centroids. Based on this observation, we introduce SVG-EAR, a parameter-free linear compensation branch that uses the centroid to approximate skipped blocks and recover their contributions. While centroid compensation is accurate for most blocks, it can fail on a small subset. Standard sparsification typically selects blocks by attention scores, which indicate where the model places its attention mass, but not where the approximation error would be largest. SVG-EAR therefore performs error-aware routing: a lightweight probe estimates the compensation error for each block, and we compute exactly the blocks with the highest error-to-cost ratio while compensating for skipped blocks. We provide theoretical guarantees that relate attention reconstruction error to clustering quality, and empirically show that SVG-EAR improves the quality-efficiency trade-off and increases throughput at the same generation fidelity on video diffusion tasks. Overall, SVG-EAR establishes a clear Pareto frontier over prior approaches, achieving up to 1.77$\times$ and 1.93$\times$ speedups while maintaining PSNRs of up to 29.759 and 31.043 on Wan2.2 and HunyuanVideo, respectively.

cs.CV↗

arXiv2026

Higher-order exponential Runge-Kutta Galerkin finite element method for semilinear parabolic problems with nonsmooth data

We develop a rigorous numerical analysis framework for a class of semilinear parabolic problems with nonsmooth initial data. We employ a linear Galerkin finite element method for spatial discretization coupled with a high-order explicit exponential Runge-Kutta (EERK) temporal integration scheme. In contrast to conventional smooth error analysis, the nonsmooth case lacks a priori estimates for the higher-order derivatives of both the nonlinear term and the exact solution. By combining analytic semigroup techniques with fractional power space theory, we establish rigorous bounds for these derivatives. Finally, our analysis proves that the $p$th-order EERK method achieves a convergence rate of $\min(1 + γ/2 + ρ_1(γ)/2,\:p)$, where $γ$ characterizes the initial data regularity and $ρ_1(γ)$ quantifies the boundedness of the nonlinearity's first Fréchet derivative. Numerical experiments confirm the sharpness of these estimates.

math.NA↗

arXiv2026

Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models

Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models. For complex tasks such as image editing, reward models are required to capture global semantic consistency and implicit logical constraints beyond local similarity. Existing reward modeling approaches have clear limitations. Discriminative reward models align well with human preferences but struggle with complex semantics due to limited reasoning supervision. Generative reward models offer stronger semantic understanding and reasoning, but they are costly at inference time and difficult to align directly with human preferences. To this end, we propose Joint Reward Modeling (JRM), which jointly optimizes preference learning and language modeling on a shared vision-language backbone. This approach internalizes the semantic and reasoning capabilities of generative models into efficient discriminative representations, enabling fast and accurate evaluation. JRM achieves state-of-the-art results on MMRB2 and EditReward-Bench, and significantly improves stability and performance in downstream online reinforcement learning. These results show that joint training effectively bridges efficiency and semantic understanding in reward modeling.

cs.AI↗

arXiv2026

AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems

Recommendation algorithm iteration is moving from an artisanal, engineer-bound process toward an industrialized research loop, but this transition remains blocked by a structural execution bottleneck: the idea-to-launch cycle still depends on human engineers to generate hypotheses, modify production code, launch A/B experiments, and attribute online results. Innovation therefore scales linearly with headcount rather than compounding with evidence, compute, and accumulated experimental knowledge. We present AgentX, a production-deployed multi-agent system that fundamentally restructures this production function. AgentX operates as a self-evolving development engine: it autonomously generates, implements, evaluates, and learns from recommendation experiments at a scale and pace that no manual workflow can sustain. The system orchestrates four tightly coupled stages in a closed loop. A Brainstorm Agent synthesizes evidence from historical experiments, system architecture, data analysis, and external research into ranked, executable proposals. A Developing Agent translates each proposal into production-ready code through repository-grounded generation and multi-dimensional reliability verification. An Evaluation Agent conducts safe online rollout with guardrail-vetoed A/B judgment, converting both successes and failures into structured knowledge assets. A Harness Evolution layer (SGPO) then distills execution trajectories into semantic-gradient updates that continuously sharpen the agents themselves -- making the system not merely automated, but self-improving.

cs.AI↗