arXiv subjects

Peng Wang

Publications and source records attributed to Peng Wang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations

Existing interpretability tools do not test whether a representation keeps the same content when only the phrasing changes. We treat each paraphrase pair as a local witness that two activations should agree and build a cellular sheaf over the paraphrase graph; its Laplacian $L_\mathcal{F}$ answers the question on a frozen model with no training. The kernel $H^0$ is a content subspace: at 20 dimensions it beats the preserved subspace of the concept eraser LEACE on held-out CounterFact fact retrieval across eight architectures by a mean $+17.1$\,pp, and constraining all paraphrases of a fact jointly adds a further $+6.5$\,pp. The spectral complement concentrates causal influence: ablating the most paraphrase-variable coordinates, a coordinate-wise proxy for it, changes model outputs $5.6$ to $26.5\times$ more than ablating coordinates of matched per-coordinate variability, across nine models from 124M to 13B parameters. Stacking layers into a grid creates $b_1 = N(L-1)$ algebraic 1-cycles, and the resulting model-derived harmonic mass varies by nearly three orders of magnitude across six architectures and ranks them as their steering fragility does (Spearman $ρ= 0.90$, exact one-sided permutation $p = 0.014$). The same paraphrase graph yields the content subspace, the influence directions, and the fragility measure. Project page: https://cwru-aism.github.io/gluing-lc-page/

cs.CL↗

arXiv2026

Criticality Concentrates Extensive Sensing Information into a Local Readout

We show that criticality concentrates extensive sensing information into a local trajectory. In the rapid-readout limit of an all-to-all dissipative feedback network, a single binary trajectory has a Fisher-information rate linear in $N$ for a common weak field, as does the full record. Critical slowing does not remove this gain because the local weight of the slow mode decreases with $N$. An analytic bound guarantees that the local record retains more than half of the full information across the entire channel-parameter range. We also identify how parameter drives and observation dynamics determine local access to collective information beyond permutation symmetry. Furthermore, our sparse-readout theorem establishes a $k^{-1}$ decay of fractional information loss: only $Θ(\varepsilon^{-1})$ trajectories are needed to retain a fraction $1-\varepsilon$ of the full information rate. Any growing readout set, even of vanishing density, asymptotically recovers the full common-field Fisher-information rate.

quant-ph↗

arXiv2026

Transforming Image Editors into Video Editors

Recent image editing systems have achieved impressive semantic understanding, visual fidelity, and instruction-following ability, while video editing remains substantially more difficult and costly. In this paper, we present a simple alternative to end-to-end video editing: instead of training a monolithic video editor, we transform a strong image editor into a video editor through anchor-based generation. Our key insight is that video editing can be decomposed into two subproblems: editing a sparse set of keyframes and propagating those edits across time. Based on this observation, we propose Anchor-based Video Editing (AVE), a two-stage framework in which a powerful image editor first performs composed editing on selected keyframes, and a motion-guided image-to-video diffusion model then generates the final video by treating the edited keyframes as fixed anchors. This design directly inherits the strengths of modern image editors while avoiding expensive end-to-end video editing training. Experiments on IVEBench and VIE-Bench show that AVE achieves strong performance in instruction following, temporal consistency, and content fidelity. Further ablations reveal that final video editing quality is strongly correlated with the quality of the image editor, suggesting that future progress in video editing may come from stronger image editing foundations and lightweight transfer to video. Code is available at https://github.com/wangf3014/AVE.

cs.CV↗

arXiv2026

MiDashengLM-Spatial: Unifying General Audio Understanding and Spatial Awareness

Large audio-language models (LALMs) have achieved strong performance in general audio understanding, yet most are designed for monaural input and discard the inter-channel cues essential for spatial perception. In contrast, existing spatial audio-language models are purpose-built for spatial tasks and fail to capitalize on the general understanding capabilities of monaural LALMs. We present MiDashengLM-Spatial, the first open-source end-to-end unified audio-language model, to our knowledge, which supports both general audio understanding and spatial awareness within a single architecture. It extends MiDashengLM with a spatial audio encoder, Spatial-Dasheng, integrated through a hierarchical semantic-to-spatial conditioning module that injects intermediate semantic representations into the spatial branch at multiple depths while preserving the original semantic pathway. To provide spatial audio-language supervision at scale, we develop a data synthesis pipeline that renders diverse spatial acoustic scenes with scene-level spatial descriptions and question-answer pairs. Experiments show that Spatial-Dasheng achieves strong performance on sound event localization and detection in real-world scenes, and that MiDashengLM-Spatial substantially outperforms existing LALMs on spatial understanding and reasoning benchmarks. Meanwhile, it remains competitive with state-of-the-art 8B-scale LALMs on diverse monaural benchmarks, demonstrating that spatial awareness can be acquired without compromising general audio understanding. The source code and model checkpoint are available at https://github.com/xiaomi-research/midashenglm-spatial and https://huggingface.co/mispeech/midashenglm-spatial.

cs.SD↗

arXiv2026

Online Adaptive Computation Reuse in Collaborative Edge Computing: A Two-Timescale Approach

Collaborative Edge Computing (CEC) is an efficient computing paradigm that enables neighboring edge servers to share computational resources with each other. Although CEC can enhance resource utilization, it still suffers from duplicate computations because nearby end-users often offload tasks with similar inputs. To improve system efficiency, the computation results of previously executed tasks can be cached and reused by subsequent tasks. However, time-varying task popularity and arrival rates require caching and scheduling decisions to adapt to demand changes, while frequent cache updates incur additional costs. To address this issue, this paper develops a two-timescale computation reuse algorithm for CEC networks. We formulate an optimization problem that jointly considers weighted response time and cache update cost, with result caching decisions determined at the frame level and workload scheduling, cache searching, and computational resource allocation adjusted at the slot level. Using recent workload observations, we construct a frame-level surrogate problem and decompose it into a caching subproblem and a scheduling subproblem. For the caching subproblem, we introduce marginal storage efficiency and incorporate cache update costs into a bisectionbased algorithm. Under bounded normalized marginal sensitivity, the algorithm achieves a near-optimal objective value for the single-BS caching subproblem when individual result sizes are small relative to the cache capacity and the relaxed solution is sufficiently accurate. For the scheduling subproblem, we utilize projected gradient descent and backtracking with warm starts across consecutive slots. Numerical results demonstrate consistent performance gains over benchmark schemes across diverse network and workload settings.

cs.NI↗

arXiv2026

LR-V2X: Loss-Resilient Collaborative Perception under Low-Bandwidth Communication

Given the inherent unpredictability of packet loss in vehicular wireless communications, V2X collaborative perception can yield practical benefits only if agents can achieve reliable collaboration under lossy and low-bandwidth communication conditions. Existing dense BEV feature fusion methods depend on redundant BEV feature exchange, which is infeasible in low-bandwidth scenarios, while compact-communication methods aggressively compress messages but can hardly recover the missing feature content after packet loss. In this paper, we present LR-V2X, a loss-resilient, latent-space reconstruction framework that converts corrupted received latents (even under severe 90% packet loss) into a spatial prior and then reconstructs the missing BEV information from this informative prior and using ego context as condition. Notably, the model can be trained under complete communication conditions and can be directly applied to lossy conditions at test time, eliminating the need for training under numerous lossy conditions. Experiments on DAIR-V2X and V2XREAL show that LR-V2X delivers the strongest robustness under severe packet loss and preserves reliable collaboration as communication quality degrades. And it reduces communication overhead by $64\times$ compared to dense BEV feature fusion baselines. Code will be released at https://github.com/sidiangongyuan/LR-V2X.

cs.CV↗

arXiv2026

ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion

Autoregressive video diffusion models have become a leading approach to real-time interactive video generation and video world modeling. However, existing methods typically allocate computation uniformly across space when generating the next video chunk, updating all patches with the same denoising schedule and number of function evaluations. This ignores the spatial heterogeneity of video content: static, simple, or recurring regions are often easier to denoise, while other regions require further refinement or additional context. A uniform budget thus leads to redundant computation on easy patches, whereas reducing the fixed step count can leave difficult patches insufficiently refined. We introduce \methodname{}, a general framework that dynamically allocates denoising steps to individual patches: easy patches stop early to improve efficiency, while difficult patches receive more refinement steps. This design accelerates generation with negligible quality degradation. Our method is compatible with most existing few-step autoregressive diffusion models, requiring only a lightweight routing module with modest training. Experiments demonstrate that \methodname{} reduces the total number of denoising steps applied across video patches by about 50\% while maintaining visual quality comparable to the four-step baseline.

cs.CV↗

arXiv2026

AirGroundVLN: A Large-Scale Benchmark for Goal-Oriented Air-Ground Collaborative Vision-and-Language Navigation

Goal-oriented Vision-and-Language Navigation (VLN) requires agents to locate and reach targets described in natural language without prescribed routes. Air--ground collaboration is valuable for tasks requiring both wide-area search and fine-grained localization. However, systematic study of goal-oriented air--ground collaborative VLN remains limited by the lack of large-scale, diverse benchmarks and two core challenges: 1) substantial differences between aerial and ground views, together with useful observations becoming unavailable as navigation proceeds, make it difficult to maintain spatially consistent context across platforms and over time; and 2) asymmetric spatial observability makes ground perception locally detailed but spatially limited and aerial perception broad but locally coarse, limiting the reliability of single-platform planning. To address these limitations, we introduce AirGroundVLN, a benchmark containing 10,281 navigation episodes and 955 target instances across 19 Unreal Engine environments, with seen/unseen splits and an aerial-visibility protocol for systematic evaluation. Alongside the benchmark, we propose AG-CoNAV, a trainable reference framework comprising two key components: Spatiotemporally Anchored Collaborative Memory (SACM) and Aerial-Guided Regional-to-Local Planning (AGRLP). SACM maintains and retrieves spatially consistent historical context across aerial and ground observations. Meanwhile, AGRLP combines regional aerial guidance with fine-grained ground navigation. Extensive experiments demonstrate the effectiveness of AG-CoNAV and establish AirGroundVLN as a comprehensive benchmark for future exploration.

cs.RO↗

arXiv2026

Nuclear mass table in deformed relativistic Hartree-Bogoliubov theory in continuum, III: nuclei with $8 \leq Z \leq 120$

The mass table in the deformed relativistic Hartree-Bogoliubov theory in continuum (DRHBc) with the PC-PK1 density functional has been established for nuclei with $8 \leq Z \leq 120$, extended from the previous works for even-even nuclei [Zhang et al. (DRHBc mass table collaboration), At. Data Nucl. Data Tables 144, 101488 (2022)] and for even-$Z$ nuclei [Guo et al. (DRHBc mass table collaboration), At. Data Nucl. Data Tables 158, 101661 (2024)]. The calculated binding energies, two- and one-nucleon separation energies, root-mean-square (rms) radii of neutron, proton, matter, and charge distributions, quadrupole deformations, neutron and proton Fermi surfaces, and the blocked neutron (proton) orbitals of odd-$N$ ($Z$) nuclei are tabulated and compared with the available experimental data. A total of 9495 nuclei are predicted to be bound, with an rms deviation of 1.444 MeV from the 2380 mass data. Good agreement with the available experimental pairing gaps, $α$ decay energies, and charge radii is also achieved. The accuracies of the calculated nuclear masses and nucleon separation energies as well as the prediction for drip lines are compared with those obtained by other relativistic and nonrelativistic density functional calculations. It turns out that the DRHBc theory with PC-PK1 provides one of the best microscopic descriptions for nuclear masses. The systematics of nucleon separation energies, pairing gaps, pairing energies, two-nucleon gaps, $α$ decay energies, rms radii, quadrupole deformations, potential energy curves, neutron density distributions, and neutron mean-field potentials are discussed.

nucl-th↗

arXiv2026

A Local Geometric Analysis of Maximal Coding Rate Reduction via Error Bounds

While the maximal coding rate reduction (MCR$^2$) objective has become a useful principle for learning compact and discriminative representations, a theoretical understanding of its optimization geometry remains limited, especially regarding why first-order methods often exhibit fast convergence near its local maximizers. In this work, we show that the MCR$^2$ objective satisfies an error-bound property in a neighborhood of its local maximizers. This property guarantees that the distance to the local maximizer set can be bounded above by the gradient norm at any point in the neighborhood, directly implying regularity conditions such as the Polyak--Łojasiewicz inequality and quadratic growth. Leveraging this property, we prove that first-order methods converge linearly to a local maximizer of the MCR$^2$ objective under mild conditions. Numerical experiments validate the predicted local convergence behavior and provide empirical evidence that optimizing the MCR$^2$ objective improves representation geometry while maintaining competitive downstream accuracy.

math.OC↗

arXiv2026

Quasinormal-Mode Collider Spectroscopy

Black-hole (BH) quasinormal modes encode the properties of merger remnants and provide powerful tests of strong-field gravity. The BH spectroscopy has predominantly treated them as independent linear oscillations. Nonlinear ringdown can additionally reveal how these modes interact and which intermediate states mediate their interactions. Inspired by cosmological collider physics, we introduce quasinormal-mode collider spectroscopy (QCS), a framework for organizing and predicting nonlinear BH responses. We establish two structural results. First, at an isolated, nondegenerate intermediate pole, a cubic strain residue factorizes into an excitation amplitude and a quadratic conversion coefficient. This factorization imposes rank constraints across output channels and choices of second-order initial data, providing consistency tests of the intermediate-mode description. Second, the intermediate pole residue can be reconstructed from its horizon and infinity radiation. With the first-order field and third-order data held fixed, this reconstruction extends to the full cubic waveform difference generated by changing the second-order initial data. QCS thus connects lower-order radiation to higher-order observables and provides a framework for probing the interaction structure of nonlinear ringdown.

gr-qc↗

arXiv2026

UGOD: Uncertainty-Guided Opacity and Dropout for Sparse-View 3D Gaussian Splatting

Sparse-view 3D Gaussian Splatting is prone to overfitting because limited observations leave many Gaussian primitives weakly constrained, yet their contributions are still accumulated through alpha blending. Without uncertainty estimation, the renderer cannot distinguish unreliable primitives from well-constrained ones, allowing their erroneous contributions to corrupt novel-view synthesis. We introduce UGOD, an uncertainty-guided framework that estimates a view-dependent uncertainty score for each Gaussian and uses it to regulate its rendering contribution. A lightweight uncertainty head conditioned on Gaussian attributes and viewing direction predicts this score, which then drives a differentiable opacity-modulation mechanism that attenuates high-uncertainty primitives before compositing. During training, a detached soft-dropout branch applies an uncertainty-controlled continuous keep mask to discourage the model from relying on poorly constrained Gaussians and thereby reduce overfitting. Crucially, detaching the uncertainty score prevents gradients from this stochastic regulariser from biasing or collapsing the uncertainty prediction. Experiments on Mip-NeRF~360 and LLFF show that UGOD improves sparse-view novel-view synthesis while producing more compact Gaussian representations than the compared methods. These results demonstrate that Gaussian uncertainty provides an effective rendering-time control for sparse-view reconstruction.

cs.CV↗

arXiv2026

ElectrolyteFM: Unifying Electrolyte Property Prediction through Cross-Property Knowledge Learning

Electrolyte formulation design requires balancing multiple physicochemical properties, yet existing models often focus on a limited subset. Learning each property in isolation can overlook transferable chemical information, whereas indiscriminate sharing can introduce cross-property interference. Our directed transfer analysis shows that jointly learning two property prediction tasks can improve or degrade prediction relative to separate training, with asymmetric transfer effects between the tasks. We propose ElectrolyteFM, a unified multi-property prediction model which can more accurately predict multiple properties of each electrolyte by effectively identifying and utilizing property-specific features and knowledge shared across properties. More specifically, ElectrolyteFM learns property-specific representations independently and captures cross-property knowledge through a separately trained expert pool. A router selects relevant shared information for each formulation and target property, and property-specific residual adapters convert this information into corrections to the corresponding representation for prediction. Experiments on Electrolyte12 show that ElectrolyteFM reduces normalized mean absolute error averaged across 12 electrolyte properties by 14.8% relative to the strongest electrolyte-specific baseline. On an independent sodium-electrolyte dataset unseen during training, it reduces conductivity mean absolute error by 6.7% relative to the best-performing baseline.

cs.LG↗

arXiv2026

Q-learning Penalized Transformer for Safe Offline Reinforcement Learning

This paper addresses the problem of safe offline reinforcement learning, which involves training a policy to satisfy safety constraints using an offline dataset. This problem is inherently challenging as it requires balancing three highly interconnected and competing objectives: satisfying safety constraints, maximizing rewards, and adhering to the behavior regularization imposed by the offline dataset. To tackle this trilogy challenge, we propose Q-learning Penalized Transformer policy (QPT), a \emph{training--inference consistent} framework that bridges conditional sequence modeling with constraint-aware value estimation. QPT trains a Transformer policy that generates actions conditioned on trajectory context and target return/cost, retaining strong behavior regularization. To inject explicit safety semantics during learning, we augment sequence-model training with a Q-shaped penalty using learned reward and cost Q-functions to favor high return under low constraint violation. At inference, the same Q-functions enforce the cost threshold and choose the highest-reward feasible action, closing the loop between training and deployment. We provide a principled analysis under stylized near-deterministic CMDPs, characterizing how Q-penalized conditional generation improve safety and performance. Empirically, QPT consistently outperforms strong safe offline RL baselines across 38 tasks on the DSRL benchmark, and exhibits robust zero-shot adaptation to different constraint thresholds.

cs.LG↗

arXiv2026

Alignment-Guided Flow Transformer for Efficient Vision-Language-Action Policy Learning

Recent advances in Vision-Language-Action (VLA) models point toward general-purpose robotic intelligence by unifying perception, instruction, and control. Despite impressive progress, existing VLA models often adapt poorly due to \emph{tri-modal misalignment} among vision, language, and action, which weakens action grounding and hurts generalization and fine-tuning efficiency. In this work, we present Alignment-Guided Flow Transformer (AGFT), a novel framework that explicitly enforces tri-modal alignment through a dedicated alignment loss, bridging the representational gap across modalities and enhancing task adaptation. While prior research has predominantly emphasized bi-modal vision--language alignment, we systematically formalize and study tri-modal alignment in VLA models, and provide both ablations and analysis to isolate its role in improving adaptation and robustness. To further accelerate deployment, we adopt a flow-matching objective, enabling substantially fewer inference steps than diffusion-based policies while maintaining accuracy. Theoretically, we establish a quantitative connection between the tri-modal alignment gap and the optimization tightness of flow matching; empirically, experiments on the extensive benchmark show that AGFT achieves superior success rates and lower inference latency compared to SOTA baselines, underscoring tri-modal alignment as a key ingredient for scaling robust VLA manipulation.

cs.LG↗

arXiv2026

On the Willmore energy of flat $n$-tori in $\mathbb{R}^N$ and Chen's conjecture for $n$-tori

This paper establishes the sharp lower bound $(4nπ^2)^{n/2}$ for the Willmore energy $\mathcal{W}$ of flat $n$-tori in the Euclidean space. Up to Möbius transformations, the Clifford $n$-torus $\mathbb{S}^1\bigl(\sqrt{1/n}\,\bigr) \times \cdots \times \mathbb{S}^1\bigl(\sqrt{1/n}\,\bigr) \subset \mathbb{S}^{2n-1} \subset \mathbb{R}^{2n}$ is shown to be the unique minimizer attaining this bound. This also confirms Chen's conjecture for flat $n$-tori. However, when $n \geq3 $, we show that Chen's conjecture fails on the total mean curvature of general immersed $n$-tori: certain Möbius transformations of the Clifford $n$-torus strictly decrease the total mean curvature.

math.DG↗

arXiv2026

Willmore Energy Estimates for Klein Bottles

In this note, we provide an estimate for the Willmore energy of Klein bottles in $\mathbb R^N$, building on the ideas of Li-Yau and Montiel-Ros for $2$-tori. In particular, we prove that the Willmore energy $\mathcal{W}(ϕ)> 6π$ for any conformal branched immersion $ϕ:\mathbb{K}^2_b\rightarrow \mathbb R^N$, where $\mathbb{K}^2_b$ is a flat Klein bottle with $0.350\lesssim b \lesssim 0.755$. This confirms partially a conjecture of Kusner. Moreover, for a flat immersion $ψ:\mathbb{K}^2_b\rightarrow \mathbb R^N$, we derive a lower bound of $\mathcal{W}(ψ)$, which confirms a conjecture of Hirsch-Mäder-Baumdicker for flat Klein bottles in $\mathbb R^N$. We also construct a smooth family of flat Klein bottles in $\mathbb R^5$, with Willmore energy between $6.912π$ and $8π$.

math.DG↗

arXiv2026

Ordering controlled by the measurement-feedback interval in quantum Boltzmann samplers

We show that the measurement--feedback interval alone can induce ordering in a quantum Boltzmann sampler with fixed programmed couplings and a fixed local dissipative rule. At zero environmental dephasing, repeated projective measurements remove transverse coherence regenerated during relaxation, thereby enhancing the local longitudinal response. We derive the exact finite-interval Markov kernel for successive measurement records and obtain the ordering threshold in the Curie--Weiss limit. For couplings below the equilibrium Curie--Weiss threshold, shortening the readout interval drives a continuous transition to an ordered stationary state even though the programmed Boltzmann distribution remains disordered. The stationary response and equation of state map exactly onto those of a continuously interacting model with dephasing, while the linear relaxation rates remain distinct at matched static response. Exact finite-size stationary calculations reveal the transition through bimodal magnetization distributions and mean-field critical scaling.

quant-ph↗