arXiv subjects

Jie Wang

Publications and source records attributed to Jie Wang.

At least 73 records · Page 4Linked to original sources

arXiv2026

OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing

The quality and diversity of instruction-based image editing datasets are continuously increasing, yet large-scale, high-quality datasets for instruction-based video editing remain scarce. To address this gap, we introduce OpenVE-3M, an open-source, large-scale, and high-quality dataset for instruction-based video editing. It comprises two primary categories: spatially-aligned edits (Global Style, Background Change, Local Change, Local Remove, Local Add, and Subtitles Edit) and non-spatially-aligned edits (Camera Multi-Shot Edit and Creative Edit). All edit types are generated via a meticulously designed data pipeline with rigorous quality filtering. OpenVE-3M surpasses existing open-source datasets in terms of scale, diversity of edit types, instruction length, and overall quality. Furthermore, to address the lack of a unified benchmark in the field, we construct OpenVE-Bench, containing 431 video-edit pairs that cover a diverse range of editing tasks with three key metrics highly aligned with human judgment. We present OpenVE-Edit, a 5B model trained on our dataset that demonstrates remarkable efficiency and effectiveness by setting a new state-of-the-art on OpenVE-Bench, outperforming all prior open-source models including a 14B baseline. Project page is at https://lewandofskee.github.io/projects/OpenVE.

cs.CV↗

arXiv2026

Scalable Ground-State Certification of Quantum Spin Systems via Structured Noncommutative Polynomial Optimization

A fundamental challenge in quantum physics is determining the ground-state properties of many-body systems. Whereas standard variational approaches posit a wave-function ansatz and minimize over the possible states expressible by that ansatz, the problem can alternatively be formulated as a noncommutative polynomial optimization problem and treated through a hierarchy of semidefinite programming relaxations. In contrast to variational calculations, these relaxations provide lower bounds on ground-state energies and both lower and upper bounds on observable expectation values. However, this approach typically suffers from severe scalability issues, limiting its applicability to small-to-medium-scale systems. In this article, we demonstrate that systematically leveraging the inherent structures of the system can substantially mitigate these scalability challenges and thus permits computing meaningful bounds for quantum spin systems on square lattices of size up to $16\times16$.

quant-ph↗

arXiv2026

A Dual Riemannian Augmented Lagrangian Method for Low-Rank SDPs with Unit Diagonal

We propose ManiDSDP, a dual Riemannian augmented Lagrangian method for solving low-rank semidefinite programs in the dual form whose positive semidefinite variable has unit diagonal. The method first eliminates the unconstrained variable by a variable projection, expresses affine consistency through an orthogonal-projector residual, and then applies the Burer--Monteiro factorization. The resulting subproblems are optimization problems on the oblique manifold and are solved by a Riemannian trust-region method with dynamic rank adjustment. A negative-curvature direction extracted from the certificate of a completed subproblem is carried into the next subproblem, leading to a one-step-delayed curvature-correction design. Under controlled inner errors, we prove that every cluster point returned by the method is a KKT point. Under additional full-sequence convergence, strict complementarity, and finite-tail exact complementarity, the iterations identify the rank of the limiting solution in finitely many steps. Under a strictly complementary rank-one solution, we further establish a local one-step locking theorem, providing a mechanism for the observed residue diving phenomenon. Numerical experiments on dense and sparse BQPs and on UCQPs demonstrate high accuracy and favorable efficiency and scalability relative to MOSEK, SDPNAL+, and ManiSDP.

math.OC↗

arXiv2026

Optimal strategies for shadow tomography with limited resources

Shadow tomography addresses the task of efficiently predicting many expectation values of an unknown quantum state from randomized measurements on comparatively few copies. Existing analyses promise large scaling advantages, but the optimal strategies realizing these guarantees are not always known, and the required measurements are potentially challenging to implement on current hardware. We address this gap for Pauli observables by computing optimal sample-complexity parameters and constructing optimal measurement strategies under realistic resource constraints. We focus on memoryless protocols, where each copy is measured only once, and on measurements with bounded interaction range. Our approach reduces the problem to the analysis of graph parameters of the frustration graph encoding the Pauli anticommutation relations. We provide efficient numerical methods for the general case and analytically prove that Clifford measurements are optimal in many situations. This includes all perfect graphs, all single-qubit, all two-qubit measurement scenarios, and more. Applied to Hamiltonian energy estimation, our framework yields constructive strategies and improved variance bounds for molecular benchmarks.

quant-ph↗

arXiv2026

Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On

The rapid advancement of Large Language Models has given rise to autonomous LLM-based agents capable of complex reasoning and execution. As these agents transition from isolated operation to collaborative ecosystems, we witness the emergence of the Agent-to-Agent (A2A) network, a paradigm where heterogeneous agents autonomously coordinate to solve multi-step tasks. While these networks may offer better task performance compared to simply using one agent to complete the entire task, they introduce systemic vulnerabilities, such as adversarial composition, semantic misalignment, and cascading operational failures, that existing agent alignment techniques cannot address. In this vision paper, we argue that the trustworthiness of A2A networks cannot be fully guaranteed via retrofitting on existing protocols that are largely designed for individual agents. Rather, it must be architected from the very beginning of the A2A coordination framework. We present a comprehensive conceptual framework that situates trust in A2A systems through four design pillars.

cs.AI↗

arXiv2026

Beyond Boundary Frames: Talking-Head Inbetweening via Context-Aware Motion Modeling

Existing talking-head generation methods primarily target open-ended generation rather than bridging two existing video segments. In this paper, we study talking-head inbetweening, a practical editing task that aims to generate realistic intermediate frames under fixed endpoint constraints. Unlike generic video inbetweening, this task requires recovering subtle speech-driven facial dynamics over long temporal gaps, where the boundary frames alone provide insufficient guidance for realistic motion recovery. To address this problem, we propose BBF (Beyond Boundary Frames), a unified context-aware framework for talking-head inbetweening. BBF consists of three complementary components: Endpoint Anchoring for preserving endpoint consistency, Motion Evolution Modeling for capturing plausible temporal transitions from surrounding visual context, and Speech Dynamics Refinement for injecting fine-grained speech-driven facial dynamics from speech audio. A progressive optimization strategy further balances structural consistency and motion refinement during denoising. Extensive experiments on the talking-head benchmarks HDTF and Hallo3 demonstrate that BBF consistently achieves state-of-the-art performance. In particular, BBF surpasses the strongest baseline on Hallo3 by 23.3% in FID and 36.5% in FVD. Moreover, BBF demonstrates strong generalization on generic video inbetweening benchmarks.

cs.CV↗

arXiv2026

HRRC on the Farm: Quantile Forecasting for Highly-Reliable Remote Control via LEO Networks

LEO satellite networks are an attractive solution to support farm automation in Agriculture 4.0 because of their ubiquitous coverage. However, LEO networks often suffer from high latency volatility, which can limit their utility in mission-critical farm operations such as remote control. This paper studies highly-reliable remote control over LEO networks by (i) casting highly-reliable remote control as a quantile forecasting problem and (ii) proposing a high-quantile estimator that can predict latency spikes at a given reliability level. Our results, drawn from a real-world OneWeb dataset collected in a major agricultural hub in the US, show that the proposed estimator can support highly-reliable remote control on the farm by meeting reliability requirements while allowing the remote-controlled vehicle to operate at speeds up to 138.6% higher than what would be possible otherwise.

cs.NI↗

arXiv2026

A high-significance detection of primordial tidal torque imprints

Tidal-torque theory predicts that galaxy angular momenta are imprinted by the primordial tidal field acting on proto-structures and that they can retain information about the early Universe through cosmic evolution. Here we test this prediction by comparing observed galaxy angular momentum vectors with those predicted from the primordial density field reconstructed by ELUCID for the nearby Universe. Among the galaxy populations considered, the gas component of central massive elliptical galaxies provides the clearest signal, exhibiting a strong direction correlation at a significance of about $7σ$. These results provide a robust observational evidence for tidal-torque theory and open a window for cosmological measurements of neutrino mass and other cosmological parameters.

astro-ph.CO↗

arXiv2026

Déjà Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates

Tracking links observations of the same object through visual change, yet cannot by itself determine when the object is empty or filled, intact or cut. We formulate identity-conditioned state-moment retrieval: given a tracked-object history and alternative state descriptions, localize an interval in which each described state holds. Absolute image-text similarity scores descriptions independently; because every visible frame depicts the same target, shared object compatibility can obscure the state evidence needed to identify the target interval. The alternatives provide the missing reference: evidence for one state should be measured against the others. We introduce Déjà Cue, a training-free framework that turns these alternatives into a vocabulary-relative coordinate system. It subtracts their state-balanced centroid from each description, calibrates frame scores, and scans multiple durations within contiguous visible runs using a frozen encoder. On 78 VOST histories, holding the temporal scan fixed and changing only the query reference nearly doubles R@1 at tIoU 0.5 from 10.3\% to 20.5\% and raises Top-1 tIoU from 16.0\% to 21.5\%. Candidate-rank analyses show that vocabulary-relative queries rank useful intervals higher within the same candidate set. Related state descriptions can therefore serve as an object-specific, query-time coordinate system for reading frozen visual representations.

cs.CV↗

arXiv2026

Computing with Agentic Oracles

This paper extends the stochastic-oracle model of AI-augmented computing to include agentic oracles. Unlike a stationary stochastic oracle, which responds to the same query according to a fixed response distribution across calls, an agentic oracle can pursue a goal autonomously and may access an environment containing task-relevant resources. These capabilities affect both response distributions and token costs beyond what is visible at the query-response interface. We develop a framework for analyzing token costs in Stochastic-Oracle Turing Machines (SOTMs) that compute with agentic oracles. Each call has an \emph{orchestration token cost}, visible to the caller at the query-response interface, and an \emph{agentic token cost}, incurred by internal operations not exposed to the caller. We show that an SOTM computing with an agentic oracle that can retain intermediate state can have token-cost advantages over SOTMs using stationary stochastic oracles when solving the same task at the same quality level, both with and without environment access. We also investigate goal-loss risk, including how internal dispatch ordering can reduce exposure to irreversible actions. We provide a goal-loss avoidance criterion, derive progress--retry--goal-loss formulas, establish goal-depth lower bounds on token complexity, characterize token complexity when the probability of goal loss is zero, and show that goal-loss risk can impose an upper bound on the achievable quality of a task involving environment updates.

cs.AI↗

arXiv2026

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series rests on three components: (i) agent-driven data pipelines producing large-scale, verifiable trajectories across agentic coding and agentic cowork, each grounded in an executable workspace and an artifact-aligned reward; (ii) Forge, a scalable agent-native RL system that adapts to long-horizon agent trajectories, paired with windowed-FIFO scheduling, prefix-tree merging, inference optimization, and a clean training-inference-agent decoupling that supports both white-box and black-box agents; (iii) the latest M2.7 checkpoint takes an early step toward self-evolution -- autonomously debugging training runs and modifying its own scaffold. Across M2 through M2.7, this combination translates a mini-activation footprint into frontier-tier performance on agentic coding, deep search, office-task, and reasoning benchmarks.

cs.AI↗

arXiv2026

TiPToP: A Modular Open-Vocabulary Robot Manipulation System That Plans

We present TiPToP, a modular manipulation system that integrates pretrained foundation models with a GPU-accelerated Task and Motion Planner to solve tasks directly from RGB images and natural language. TiPToP composes perception, planning, and execution modules and requires no robot training data. It can be deployed on a standard DROID setup in under an hour and adapted to new embodiments with minimal effort. We evaluate TiPToP against $π_{0.5}\text{-DROID}$, a state-of-the-art VLA fine-tuned on 350 hours of demonstrations, across two real-world DROID setups (one operated by an external team) and simulation, where TiPToP attains a higher average success rate and faster average completion time. We also evaluate on the MolmoSpaces benchmark, where TiPToP ranks first overall on pick and pick-and-place tasks among methods not trained on in-distribution data. We further show that TiPToP's modularity enables us to trace failures to specific components, revealing where to target improvements. We release TiPToP open-source to serve as a reproducible baseline and to enable further research on modular manipulation systems. Project website and code: https://tiptop-robot.github.io

cs.RO↗

arXiv2026

SMEFT-Pheno-Agent: a natural-language-driven AI agent for machine-learning-assisted Standard Model Effective Field Theory phenomenology

We present SMEFT-Pheno-Agent, a Python workflow guided by a natural-language AI agent to perform machine-learning-assisted Standard Model Effective Field Theory (SMEFT) phenomenology at high-energy colliders. The software coordinates twelve automated execution phases spanning configuration intake, environment validation, event generation, machine-learning selection, statistical inference, and final audit. At each phase boundary, the agent interprets natural-language intent to generate runnable parameter files and adapter invocations required for subsequent execution. Once the detector-level events are written, the agent automatically proposes key kinematic observables alongside candidate machine-learning algorithms suited to the specific data structure and analysis objectives. All numerical calculations are delegated strictly to validated domain tools, with MadGraph5_aMC@NLO, Pythia, Delphes generating collider simulations, and MLAnalysis extracting features. The agent cannot modify physical parameters outside the locked configuration, and all LLM-produced artifacts, including parameter files, observable choices, algorithm selections, and prose drafts, are documented in machine-readable phase manifests prior to execution. These manifests establish complete reproducibility and audit traceability for SMEFT phenomenology studies.

hep-ph↗

arXiv2026

A RELHIC twin candidate near the galaxy M51

We report the discovery of a pair of H I clouds near M51 (NGC 5194) using the Five-hundred-meter Aperture Spherical radio Telescope (FAST). These clouds have no optical counterparts and are potential candidates for Reionization-Limited H I Clouds (RELHICs). We search for compact H I sources in deep FEASTS observations using SoFiA and remove objects with optical counterparts through cross-matching with the DESI Legacy Imaging Surveys. The remaining candidates are modelled as hydrostatic H I structures embedded in Navarro-Frenk-White dark matter haloes and compared with RELHIC predictions and TNG50 simulations. We identify two H I clouds, Cloud S and Cloud N, at projected distances of 70--90 kpc from M51. Each cloud has an H I mass of approximately 10^6.5 solar masses, a velocity dispersion of about 20 km/s, and no detectable optical counterpart down to a g-band surface brightness limit of approximately 27.5 mag arcsec^-2. Their stellar luminosities are constrained to be below 10^5 solar luminosities. Their H I properties are consistent with RELHIC predictions, corresponding to host halo masses of 3.7 +- 0.4 * 10^9 solar masses. Cloud S and Cloud N are promising but not definitive RELHIC candidates. A tidal origin remains possible in the interacting M51 system, especially because the clouds are unresolved by FAST and Cloud N may show a velocity gradient. Future high-resolution interferometric observations will be crucial for distinguishing between starless dark matter haloes and tidal debris.

astro-ph.GA↗

arXiv2026

AXIS: A Growable Community-Driven Data Engine for Scalable Robot Manipulation

Learning effective robot manipulation policies requires diverse, high-quality demonstrations, yet existing data pipelines are often difficult to scale because they rely on specialized hardware, centralized operators, or fixed task suites. We present AXIS, a growable community-driven data engine and benchmark for scalable robot learning, which enables browser-based teleoperation for large-scale demonstration collection, automatically generates and validates new manipulation tasks, and transforms community-collected demonstrations into training-ready data through automated success checking, quality filtering, trajectory smoothing, and visual and physics-based augmentation. The AXIS dataset currently contains 207 diverse tasks and 50K+ trajectories. Meanwhile, AXIS organizes data into task snapshots and evaluates policies with a systematic held-out protocol. We compare vision-language-action (VLA) policies under a unified AXIS evaluation suite and analyze scaling behavior across different data volumes. Continual pretraining on AXIS substantially improves the overall success rate of $π_{0.5}$ by 5.8%, outperforms the model pretrained on RoboCasa365 by 37.3%, and exhibits consistent scaling with increasing data volume, with the largest gains observed under layout, sensor-noise, and camera perturbations.

cs.RO↗

arXiv2026

Strengthened Complex Moment Hierarchies and Finite Convergence over Spheres

This paper proposes strengthened complex moment relaxations for complex polynomial optimization. The proposed relaxation augments the pruned complex moment relaxation with selected positive semidefinite blocks from the full complex moment matrix. For the first strengthening, these blocks are motivated by the normality of multiplication operators and provide a tunable tradeoff between relaxation strength and computational cost through an additional normal order. In analogy with the real moment hierarchy, a flat-truncation condition for detecting global optimality is derived for the strengthened hierarchy. Furthermore, by considering the joint normality of multiplication operators, we propose a second strengthened complex moment hierarchy. For this stronger hierarchy, we are able to prove generic finite convergence and flat truncation for optimization over spheres. Numerical experiments demonstrate that the proposed strengthenings recover almost all the strength of the full relaxation at substantially lower computational cost.

math.OC↗

arXiv2026

The FAST All Sky HI Survey DR2: the FASHI Catalog and the HI Mass Function

The FAST All Sky HI Survey (FASHI) conducted with the Five-hundred-meter Aperture Spherical radio Telescope (FAST) has mapped $\sim 19500\,\mathrm{deg}^2$ of the sky north of DEC $= -14^{\circ}$, detecting $156411$ extragalactic HI sources at $z< 0.09$ with a median sensitivity of $0.57\,\mathrm{mJy}\,\mathrm{beam}^{-1}$ at a velocity resolution of $6.4\,\mathrm{km}\,\mathrm{s}^{-1}$. The survey achieves unprecedented depth and area coverage, significantly improving upon previous single-dish surveys. Through a detailed completeness analysis that accounts for the survey's non-uniform sensitivity and line-width dependence, we construct a robust HI mass function (HIMF) using a completeness-corrected sample of over $109000$ sources. The HIMF is robustly constrained down to $M_{\mathrm{HI}}\sim 10^{6.2}\,M_{\odot}$. When systematic uncertainties are included, the HIMF is well described by a single-Schechter function with a characteristic mass $\log (M_{*} / h_{70}^{-2}M_{\odot}) = 9.89\pm 0.02$, low-mass end slope $α= -1.31\pm 0.02$, and amplitude $ϕ_{*} = (6.38\pm 0.49)\times 10^{-3}\,h_{70}^{3}\,\mathrm{Mpc}^{-3}\,\mathrm{dex}^{-1}$. The derived cosmic HI density is $Ω_{\mathrm{HI}} = (4.71\pm 0.03_{\mathrm{stat}}\pm 0.40_{\mathrm{sys}})\times 10^{-4}\,h_{70}^{-1}$. FASHI provides the most extensive and sensitive HI catalog to date, establishing an important benchmark for studies of gas accretion, galaxy evolution, and large-scale structure in the local universe.

astro-ph.GA↗

arXiv2026

Computing with Stochastic Oracles in AI-Augmented Computation

The Stochastic-Oracle Turing Machine (SOTM) framework models AI-augmented computation as the interaction of a probabilistic Turing machine with an oracle whose responses are drawn from context-dependent distributions. This paper studies what an SOTM can achieve under two oracle-response schemes: in a cached-response oracle, each distinct query receives one response that is reused on later calls to the same query, while in a fresh-response oracle, each call returns an independent response. In both schemes, the SOTM first computes from its input and internal random source to generate its first query, then proceeds adaptively, computing from its query-response transcript (the record of queries issued and responses received) to generate each subsequent query or produce a final output. Cached responses impose two transcript-based ceilings on achievable performance: a correct-identification ceiling governed by the total variation distance between the transcript distributions induced by the hidden states of the oracle, and an output quality ceiling equal to the expected score of the best output the SOTM can compute from the transcript. Fresh responses can raise these ceilings by allowing repeated calls to accumulate independent evidence toward correct or high-quality outputs. In the binary single-informative-query case, the error probability decreases exponentially in the number of calls to the same query at the Chernoff rate. For output quality, query-count bounds characterize threshold stopping when the score function is incorporated as part of the SOTM, and majority-based amplification bounds characterize the binary candidate-output model when it is not. Together, the results identify how response reuse, transcript information, and access to the score function determine what an SOTM can compute and at what token cost.

cs.CC↗