arXiv subjects

Jie Zhang

Publications and source records attributed to Jie Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty

Two-Stage Robust Optimization (2RO) with discrete uncertainty is challenging, often rendering exact solutions prohibitive. Scenario reduction alleviates this issue by selecting a small, representative subset of scenarios to enable tractable computation. However, existing methods are largely problem-agnostic, operating solely on the uncertainty set without consulting the feasible region or recourse structure. In this paper, we introduce PRISE, a problem-driven sequential lookahead heuristic that constructs reduced scenario sets by evaluating the marginal impact of each scenario. While PRISE yields high-quality scenario subsets, each selection step requires solving multiple subproblems, making it computationally expensive at scale. To address this, we propose NeurPRISE, a neural surrogate model built on a GNN-Transformer backbone that encodes the per-scenario structure via graph convolution and captures cross-scenario interactions through attention. NeurPRISE is trained via imitation learning with a gain-aware ranking objective, which distills marginal gain information from PRISE into a learned scoring function for scenario ranking and selection. Extensive results on three 2RO problems show that NeurPRISE consistently achieves competitive regret relative to comprehensive methods, maintains strong calability with varying numbers of scenarios, and delivers 17-200x speedup over PRISE. NeurPRISE also exhibits strong zero-shot generalization, effectively handling instances with larger problem scales (up to 5x), more scenarios (up to 4x), and distribution shifts.

cs.AI↗

arXiv2026

Twig: Parallel and Memory-Efficient Tree Speculative Decoding for Hybrid-Attention LLMs

Emerging LLMs increasingly interleave full attention with recurrent linear attention to reduce long-context serving costs. Tree speculative decoding could further accelerate these hybrid models, but recurrent linear-attention layers carry parent-dependent states. Existing engines therefore verify proposal trees sequentially and snapshot the full state per node, causing latency and memory to grow with tree and batch sizes. We present Twig, a kernel--runtime co-design for tree speculative decoding of hybrid LLMs. Twig derives a tree-structured factorization of the linear-attention recurrence and realizes it with a resource-efficient GPU kernel that verifies all nodes in parallel, accelerating linear-attention tree verification by 3.4--7.7$\times$. It losslessly represents speculative state updates as token-level factors and reconstructs only the accepted state, reducing transient state memory by 82--99$\times$ and freeing GPU memory for KV caches. We integrate Twig into SGLang, a widely deployed production LLM serving engine, and further optimize its runtime through batch-wide verification budgeting. Across four models, two GPU platforms, and diverse datasets, Twig achieves up to $4.72\times$ the offline decode throughput of autoregressive decoding and up to $2.03\times$ that of the strongest tree-speculative baseline. Under online agent workloads, Twig reduces TTFT and TPOT by up to $67.6\%$ and $49.9\%$, respectively, over the strongest tree-speculative baseline.

cs.DC↗

arXiv2026

Hardness Amplification for Approximate Nash Equilibrium with Constantly Many Players

For every fixed integer $k\ge2$ and fixed parameters $δ,\varepsilon\in(0,1)$ and $η\in[0,1)$, we give a deterministic polynomial-time reduction from finding a $δ$-approximate Nash equilibrium ($δ$-ANE) in a $k$-player game $G$ with payoffs in $[0,1]$ to finding an $(\varepsilon,η)$-weak approximate Nash equilibrium (weak ANE) in a game $H$ with $C$ players, where $C$ depends only on $k,δ,\varepsilon,η$, independently of the action-set sizes. The constructed game is symmetric with binary payoffs. The games and strategies are represented by complete payoff tables and probabilities, with rational entries encoded in binary. Consequently, the existence of deterministic polynomial-time weak-ANE algorithms at one fixed pair of parameters $\varepsilon\in(0,1),η\in[0,1)$ for every fixed number of players would give deterministic polynomial-time $δ$-ANE algorithms at every fixed approximation parameter $δ\in(0,1)$ and number of players. Under deterministic PPAD-ETH, combining our reduction with Rubinstein's hardness result (FOCS 2016) for bimatrix games at some fixed approximation parameter $γ_0\in(0,1)$ rules out a deterministic algorithm for $(\varepsilon,η)$-weak ANE with running time $N^{O((\log N)^{1-ξ})}$ for any fixed $ξ\in(0,1)$. This holds for every fixed $\varepsilon\in(0,1)$ and $η\in[0,1)$ at a suitable constant number $C$ of players, where $N$ is the binary encoding length of the constructed game's complete payoff table.

cs.GT↗

arXiv2026

META-Robot: Self-Cognition and Capability Scaling in Agentic Robots

LLM-based robotic agent systems can generate programs for robot control, yet their generalization to new tasks often depends on elaborate scaffolding. Expanding their skill repertoires alone offers limited guidance on how to assess new capabilities or identify what remains beyond their reach. We introduce META-Robot, a framework that couples self cognition with capability scaling by expanding the criteria through which an agent evaluates and develops its skills. At its core, action-level predicates make execution outcomes explicit and available for LLM reasoning. The agent uses these assessments to identify its own limitations, extend relevant evaluation criteria, and guide the structured expansion of its skills. Proprioceptive feedback further grounds this process in the robot's physical state, enriching the evidence available for self-cognition. Experiments in simulation and on real robots demonstrate stronger overall task performance, generalization to new tasks, continued expansion of skills and evaluation criteria, and effective use of non-visual proprioceptive signals.

cs.RO↗

arXiv2026

Robust Geometric Gates for QCCD Architecture

The trapped-ion quantum charge-coupled device (QCCD) is a promising route toward scalable quantum computing. However, the frequency offset during shuttling operations introduce significant decoherence and control errors, severely degrading gate fidelity on transported ions. Here, using a room-temperature planar chip trap, we demonstrate a robust and universal single-qubit gate set in the QCCD architecture. Based on a recently proposed path-optimizable noncyclic geometric scheme, we show that dynamic noise is strongly suppressed even when multiple shuttling operations are interleaved with gate execution, achieving substantially higher fidelities than conventional dynamical gates. This robustness is further validated in a multi-ion system containing up to 33 qubits. With inherent robustness and adaptability to varying shuttle distances and ion numbers, our work offers a plug-and-play solution for building robust quantum primitives for the QCCD platform.

quant-ph↗

arXiv2026

Entire solutions of a special binomial differential equation

We consider the binomial differential equation $$ ff'-a(f'')^2=be^{2c},$$ where $a(z)$, $b(z)$, $c(z)$ are polynomials such that $b(z)\not\equiv 0$ and $c(z)$ is non-constant. In this paper, we determine all entire solutions of this equation.

math.CV↗

arXiv2026

Non-Maxwellianity in Temperature Relaxation between Plasma Species

Temperature relaxation between plasma species is usually described by Landau--Spitzer (LS) theory, which assumes Maxwellian distributions throughout. We show analytically that, for two Maxwellian species in homogeneous isotropic plasmas, the interspecies collisions driving relaxation generate a universal three-lobe initial distortion and that these distortions initially reduce energy exchange over a broad parameter range. Full Fokker--Planck simulations reveal substantial relaxation delays when interspecies deformation competes with self-thermalization. For post-shock deuterium--tritium plasmas relevant to inertial confinement fusion, with $T_{\mathrm{T}}/T_{\mathrm{D}}=1.5$, the relaxation time exceeds the LS prediction by 47%. The accompanying distortions lower the apparent DD/DT temperature ratio and produce positive DD and negative DT Gamow-shift residuals relative to Maxwellian predictions. These results also motivate examining non-Maxwellianity in fuel heating by fusion $α$ particles.

physics.plasm-ph↗

arXiv2026

FenixWalk: Adaptive Sampling for Large-Scale Dynamic Graphs on Heterogeneous Architectures

Random walks are fundamental to graph analytics, yet executing them efficiently on large, evolving graphs remains challenging. Existing approaches must balance sampling efficiency, update overhead, and memory consumption. Sampling structures optimized for throughput often incur substantial memory overhead and costly maintenance, whereas lightweight alternatives can suffer from high sampling latency on high-degree vertices or skewed weight distributions. These challenges become more pronounced on heterogeneous CPU--GPU platforms, where host memory provides capacity but GPU memory limits the amount of graph data that can benefit from parallel acceleration. We present FenixWalk, a memory-efficient random-walk system that combines unified in-place sampling with selective GPU acceleration for large-scale dynamic graphs. At its core, FenixWalk employs an in-place Fenwick representation that supports both rejection sampling and inverse-transform sampling without duplicating edge-level weight storage. This representation enables expected O(1) weight lookup for rejection sampling, together with O(log d) prefix sampling and updates. To exploit heterogeneous hardware efficiently, FenixWalk maintains the complete graph and its sampling structures in host memory while selectively placing frequently reused vertex-local samplers on the GPU. By transferring compact walker states instead of repeatedly migrating graph partitions, the system reduces cross-device communication and makes effective use of limited GPU memory. Experiments on large real-world graphs and representative random-walk workloads demonstrate that FenixWalk achieves average speedups ranging from 2.06x to 400.57x over existing random-walk systems.

cs.DC↗

arXiv2026

Scheduling Data to Compute: Hierarchical Data Pipelining for LLM Training on AMD GPUs

Large language models (LLM) have been the key focus of recent machine learning breakthroughs. As the model size grows exponentially, the computation needed for training is astronomical. A GPU can do a huge amount of arithmetic. However, the data its compute units need is not always available when they are ready. This data may still be in slow memory or on another GPU. While the chip waits, expensive compute sits idle, and at scale even a small drop in utilization translates into substantial cost. In this paper, we treat this waiting time as the primary bottleneck. We focus on hardware features designed for explicit data movement. These features load data from off-chip memory onto the chip, rearrange it into the layout the computation requires as it is loaded, and transfer it between GPUs. By orchestrating them, we keep a steady pipeline of data flowing to the compute units so that they remain busy. We present kernel and framework implementations that address this bottleneck using three key data-movement instructions and hardware features. The Tensor Data Mover (TDM) moves tensor data from high-bandwidth memory (HBM) into on-chip memory. Transpose-load instructions transpose tensor data into the layout that LLM computations require as it is loaded on-chip. Finally, System DMA (SDMA) and Remote DMA (RDMA) move data between GPUs over the scale-up and scale-out networks, respectively. Our results show that TDM and transpose-load provide on average 1.88x and 1.19x speedup at the kernel level, respectively. The SDMA and RDMA lead to on average 1.16x and 1.33x speedup for computation overlapped with communication. This is the first AMD LLM training system to utilize all the GPU data pipelining features. Our implementation has been integrated into open source framework and library for AMD GPUs. https://github.com/AMD-AGI/Primus-Turbo https://github.com/AMD-AGI/Primus

cs.AR↗

arXiv2026

SynBench: A Benchmark for Differentially Private Text Generation

Synthetic text generation with Differential Privacy (DP) guarantees emerges as a principled approach that can enable the sharing of sensitive datasets across institutional and regulatory boundaries, while bounding the risks of re-identification and membership inference. LLM-based methods deliver promising results; however, comparisons are exacerbated by differing evaluation setups and "private" datasets, potential pre-training contamination is not considered and guarantees are not verified with DP audits. To advance this field, we introduce a unified evaluation framework with standardised utility and fidelity metrics and privacy audits, encompassing nine curated datasets that capture domain-specific complexities such as technical jargon, long-context dependencies, and specialised document structures. In a large-scale empirical study, we benchmark LLM-based state-of-the-art DP text generators of varying sizes (between 1--8B). Our results indicate that DP synthetic text generation remains an unsolved challenge, with quality deteriorating more as the private datasets deviate further from the generators' pre-training corpora. Our analyses suggest that synthetic data quality may be overestimated when LLMs have been pre-trained---without DP---on portions of the "private" data to be generated, and our membership inference (MIA) auditing setup for synthetic text reveals measurable membership signals even under tight privacy budgets. Finally, we note that under the "public pre-training, private generation" paradigm, the nominal $(\varepsilon,δ)$ guarantee does not account for exposure during pre-training, motivating contamination-aware evaluation of DP synthetic text generation. Code and data splits: https://github.com/ImperialGlobalSingapore/synbench

cs.AI↗

arXiv2026

HIVE-Diff: High Frame Rate HDR Video Reconstruction from a Single LDR Frame and Events

High frame rate HDR video is important in applications such as autonomous driving and scientific imaging, where rapid motion and extreme illumination often occur simultaneously. Conventional frame cameras face a trade-off between temporal resolution and dynamic range, while event cameras provide complementary high-speed brightness-change measurements over a wide illumination range. These properties have motivated event-based HDR reconstruction, with existing methods broadly following event-only and hybrid event-frame paradigms. Event-only HDR reconstruction, however, suffers from brightness and color drift due to the lack of absolute intensity references. Hybrid event-frame methods alleviate this ambiguity using low-dynamic-range (LDR) frames as anchors, but most perform one-to-one HDR reconstruction at available LDR timestamps. In this work, we investigate single-reference HDR temporal expansion, reconstructing N HDR frames from one LDR reference and events instead of N aligned LDR observations. We develop HIVE-Diff, an event-conditioned video diffusion framework that decomposes the task into event-guided temporal generation and HDR content completion. Because paired real HDR-event data are scarce, we train on synthetic data and adapt the model to real event domains using LDR-event sequences as proxy supervision with teacher-student distillation. Experiments on synthetic and multiple real-world datasets demonstrate strong reconstruction quality and robust real-data adaptation.

eess.IV↗

arXiv2026

Rubric-Guided Process Reward for Stepwise Model Routing

Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods formulate routing as a sequential decision process and train the router with reinforcement learning. However, although they model routing as a process, they still supervise the router with outcome rewards. Such rewards only reflect final answer correctness and fail to evaluate intermediate routing decisions, which can weaken performance and generalization. To address this gap, we propose RoRo, a rubric-guided process reward framework for stepwise model routing. RoRo first collects diverse routing trajectories and constructs preference pairs based on outcome, cost, and process quality. It then trains a Rubricor to generate a query-specific evaluation rubric and a Judge to score routing trajectories under this rubric through alternating optimization. The resulting process rewards are combined with outcome rewards to optimize the routing policy via GRPO. Experiments on five reasoning benchmarks under both same-family and cross-family settings show that RoRo consistently outperforms strong baselines and achieves better accuracy and cost trade-offs.

cs.AI↗

arXiv2026

Experimental Realization of a Nonreciprocal Quantum Battery

Quantum batteries promise faster and more efficient energy storage and extraction by harnessing quantum mechanics, serving as essential building blocks for future quantum devices. A key practical requirement-unidirectional energy flow during charging-is straightforward in classical batteries via potential difference, yet remains a major challenge in the quantum regime due to the inherent reciprocity of coherent coupling. Here, we realize the first backflow-free, nonreciprocal quantum battery in the few-quantum regime, implemented in a highly controlled trapped-ion system via a qubit-reservoir engineering technique. By subtly tailoring quantum interference between coherent and dissipative couplings of two laser-cooled motional modes, we achieve strictly unidirectional energy flow from the charger to the battery. We observe maximum charging power at an exceptional point and demonstrate a complete charge-discharge cycle with unitary work extraction. This work establishes the foundation for directional energy transfer and storage in micro- and nanoscale quantum devices, with broad implications for nonreciprocal energy harvesting, precision metrology, information processing, and quantum thermodynamics.

quant-ph↗

arXiv2026

VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon

Vision-Language-Action (VLA) foundation models have recently achieved strong progress in embodied intelligence. To reduce policy-call frequency while preserving temporal coherence, most generative policies adopt an action chunk mechanism, executing multiple future actions in an open-loop manner under a fixed action horizon. However, this "predict-then-blindly-execute" paradigm sacrifices closed-loop reactivity: in contact-rich physical interactions, even small local perturbations can rapidly amplify within the open-loop blind spot, leading to compounding errors and ultimately task failure. To address this limitation, we propose VLA-Corrector, a lightweight corrective inference framework for action-chunked VLA policies. Without modifying the backbone policy weights, VLA-Corrector introduces a lightweight Latent-space Vision Monitor (LVM) that continuously compares predicted and actual visual feature evolution, enabling online detection of visual dynamics deviations. Once persistent deviation is detected, the system triggers a truncation event, discards the remaining stale actions, and invokes corrective replanning via Online Gradient Guidance (OGG). The detect-and-correct mechanism of VLA-Corrector naturally induces an event-triggered adaptive action horizon: it preserves long-horizon execution when the current chunk remains reliable, and invokes short-horizon corrective replanning when execution begins to drift. In doing so, VLA-Corrector mitigates the trade-off imposed by static horizons between execution robustness and policy-call frequency. It can be integrated into different VLA models without further retraining the VLA backbone, interrupting compounding errors while preserving much of the efficiency benefit of action chunking and substantially improving robustness in long-horizon, contact-rich robotic manipulation tasks.

cs.RO↗

arXiv2026

MarineLife-16K: An Attribute-Rich Video-Text Dataset for Motion-Aware Marine Video Understanding

Marine video understanding is crucial for a wide range of real-world applications. However, existing marine video datasets suffer from limitations, including the limited number of data samples, fine-grained text descriptions, and detailed visual attributes. To address these limitations, we introduce a large-scale, video-text dataset featuring rich, in-the-wild visual attributes tailored for complex marine environments. Our dataset comprises 2,000 video-text pairs annotated with 13 attributes covering up to four objects per scene, object visual/geometric properties, behaviors, environmental context, and camera motion, spanning diverse lighting conditions, times of day, and 7 countries. From these annotations, we generate 16,080 video-question pairs (12,080 multiple-choice, 4,000 open-ended). Furthermore, we benchmark both proprietary and open-source video-LLM models on video question answering and video captioning tasks. We find that (i) proprietary models often achieves superior performances; (ii) VLMs handle object motion well but struggle with complex camera motion; (iii) closed-source models struggle to perceive camera motion; and (iv) VLMs struggle to reason in static cameras.

cs.CV↗

arXiv2026

A Sub-Aperture-Based Ray-Tracing Framework for Near-Field U-MIMO THz Communications

Terahertz (THz) communications are characterized by antennas with large apertures and extended near-field (NF) region, offering the opportunity to develop adaptable beam manipulation strategies, particularly related to ultra-massive MIMO (U-MIMO). While Ray-Tracing (RT) offers an attractive alternative to full-wave methods, conventional ray-based approaches are generally formulated under far-field (FF) assumptions. We propose a technique that extends RT to the NF regime, enabling ray-based NF characterization of transmitting arrays. We model the transmitting array as an antenna aperture and develop a RT framework that partitions the transmitting aperture into sub-apertures emitting FF contributions which can be propagated via geometric optics (GO). We develop a Ray-Launching algorithm based on the proposed framework and assess its beam-reconstruction accuracy against full-wave propagation. The results demonstrate that, through tunable aperture partitioning, the proposed approach can reproduce beam manipulation effects characteristic of NF U-MIMO THz communications using GO ray propagation.

eess.SP↗

arXiv2026

Vision-Language Agents Can Learn in Their Own Latent Worlds

Learning from experience is essential for building the next generation of agents that continually expand their capabilities. Pretrained vision-language models (VLMs) already internalize rich world knowledge, yet this knowledge is rarely leveraged to drive policy improvement through online interaction. Realizing this potential efficiently remains challenging, as policy updates shift the agent's interaction distribution, requiring the world model to adapt accordingly, while continually updating large pretrained models is computationally expensive. To address this challenge, we introduce Dwell, a model-based reinforcement learning (RL) framework that reframes a VLM as a recurrent latent transition operator, endowing it with the ability to predict, adjust, and act in latent space. Leveraging the VLM's own representations and its dual role as both world model and policy, the agent continually learns from real interactions to anticipate and evaluate action outcomes, and from latent imagination to improve its behavior. Across five interactive visual environments, Dwell achieves the strongest overall performance among trainable methods while substantially reducing the compute required for imagination, showing that effective world models for VLM agents need not reconstruct the future; they need to predict futures that are useful for action. Our code is publicly available at https://github.com/Tom111-lhx/Dwell

cs.AI↗

arXiv2026

BROCADE: Broker-based Contract Design for the Multi-Agency Model

We study welfare maximization in a contract model with $m$ principals who privately value a public project's success and $n$ agents whose costly effort is unobservable. Contracts induce truthful dominant strategies for principals and equilibrium effort by agents, maximizing the expected total value of eligible principals. We develop three tools: a broker that separates payments from principals and payments to agents, an extension of Myerson's Lemma characterizing dominant-strategy incentive compatibility (DSIC), and a black-box reduction to budget-constrained single-principal contract design. When the success probability is a strictly monotone XOS function of agents' actions, these tools yield three results. First, a deterministic DSIC contract achieves a constant approximation against a benchmark that qualifies every principal and maximizes success probability using budget $\sum_j v^j$, but may violate budget balance (BB). Second, against benchmarks with budgets at least the largest principal value, deterministic DSIC and BB contracts admit no finite approximation guarantee, even with two agents. Universally DSIC and universally BB randomized contracts have an $Ω(n)$ approximation lower bound, even for a fixed number of principals. Third, using one quarter of the optimal fixed-price revenue supported by at least two principals as the benchmark budget, we obtain a universally DSIC and universally BB randomized contract with an $O(\log m)$ approximation ratio independent of $n$.

cs.GT↗