arXiv subjects

Jue Wang

Publications and source records attributed to Jue Wang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Invertible Diffusion for Low-Memory Channel Gain Map Construction in Wireless Communication Networks

Channel gain maps (CGMs) enable propagation-aware services in edge-intelligent wireless communication networks, while diffusion-based CGM construction is memory intensive for on-device training or adaptation. This letter proposes InvDiff-CGM, an invertible diffusion framework that constructs CGMs from sparse measurements and environmental priors. By adopting invertible architectures in both the diffusion process and the U-Net noise estimator, InvDiff-CGM achieves near-constant training memory consumption. A prior-informed multi-scale injector further integrates environmental priors with sparse measurements to improve physical consistency and detail preservation. Experiments on RadioMap3DSeer show about an 85\% reduction in peak training memory and a PSNR of 38.02~dB, outperforming representative recent baselines. This validates the practicality of InvDiff-CGM for high-fidelity CGM construction under edge resource constraints.

eess.SP↗

arXiv2026

STORM: End-to-End Referring Multi-Object Tracking in Videos

Referring multi-object tracking (RMOT) is a task of associating all the objects in a video that semantically match with given textual queries or referring expressions. Existing RMOT approaches decompose object grounding and tracking into separated modules and exhibit limited performance due to the scarcity of training videos, ambiguous annotations, and restricted domains. In this work, we introduce STORM, an end-to-end MLLM that jointly performs grounding and tracking within a unified framework, eliminating external detectors and enabling coherent reasoning over appearance, motion, and language. To improve data efficiency, we propose a task-composition learning (TCL) strategy that decomposes RMOT into image grounding and object tracking, allowing STORM to leverage data-rich sub-tasks and learn structured spatial--temporal reasoning. We further construct STORM-Bench, a new RMOT dataset with accurate trajectories and diverse, unambiguous referring expressions generated through a bottom-up annotation pipeline. Extensive experiments show that STORM achieves state-of-the-art performance on image grounding, single-object tracking, and RMOT benchmarks, demonstrating strong generalization and robust spatial--temporal grounding in complex real-world scenarios. STORM-Bench is released at https://github.com/amazon-science/storm-referring-multi-object-grounding.

cs.CV↗

arXiv2026

Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution

We show that verifier-free evolution is bottlenecked by both diversity and efficiency: without external correction, repeated evolution accelerates collapse toward narrow modes, while the uniform use of a high-cost model wastes compute and quickly becomes economically impractical. We introduce Squeeze Evolve, a unified multi-model orchestration framework for verifier-free evolutionary inference. Our approach is guided by a simple principle: allocate model capability where it has the highest marginal utility. Stronger models are reserved for high-impact stages, while cheaper models handle the other stages at much lower costs. This principle addresses diversity and cost-efficiency jointly while remaining lightweight. Squeeze Evolve naturally supports open-source, closed-source, and mixed-model deployments. Across AIME 2025, HMMT 2025, LiveCodeBench V6, GPQA-Diamond, ARC-AGI-V2, and multimodal vision benchmarks, such as MMMU-Pro and BabyVision, Squeeze Evolve consistently improves the cost-capability frontier over single-model evolution and achieves new state-of-the-art results on several tasks. Empirically, Squeeze Evolve reduces API cost by up to $\sim$3$\times$ and increases fixed-budget serving throughput by up to $\sim$10$\times$. Moreover, on discovery tasks, Squeeze Evolve is the first verifier-free evolutionary method to match, and in some cases exceed, the performance of verifier-based evolutionary methods.

cs.AI↗

arXiv2026

PolyReal: A Benchmark for Real-World Polymer Science Workflows

Multimodal Large Language Models (MLLMs) excel in general domains but struggle with complex, real-world science. We posit that polymer science, an interdisciplinary field spanning chemistry, physics, biology, and engineering, is an ideal high-stakes testbed due to its diverse multimodal data. Yet, existing benchmarks related to polymer science largely overlook real-world workflows, limiting their practical utility and failing to systematically evaluate MLLMs across the full, practice-grounded lifecycle of experimentation. We introduce PolyReal, a novel multimodal benchmark grounded in real-world scientific practices to evaluate MLLMs on the full lifecycle of polymer experimentation. It covers five critical capabilities: (1) foundational knowledge application; (2) lab safety analysis; (3) experiment mechanism reasoning; (4) raw data extraction; and (5) performance & application exploration. Our evaluation of leading MLLMs on PolyReal reveals a capability imbalance. While models perform well on knowledge-intensive reasoning (e.g., Experiment Mechanism Reasoning), they drop sharply on practice-based tasks (e.g., Lab Safety Analysis and Raw Data Extraction). This exposes a severe gap between abstract scientific knowledge and its practical, context-dependent application, showing that these real-world tasks remain challenging for MLLMs. Thus, PolyReal helps address this evaluation gap and provides a practical benchmark for assessing AI systems in real-world scientific workflows.

cs.CV↗

arXiv2026

An Algebraic Method for Full-Rank Characterization in Binary Linear Coding

In this paper, we develop a characteristic set (CS)-based method for deriving full-rank equivalence conditions of symbolic matrices over the binary field. Such full-rank conditions are of fundamental importance for many linear coding problems in communication and information theory. Building on the developed CS-based method, we present an algorithm called Binary Characteristic Set for Full Rank (BCSFR), which efficiently derives the full-rank equivalence conditions as the zeros of a series of characteristic sets. In other words, the BCSFR algorithm can characterize all feasible linear coding schemes for certain linear coding problems (e.g., linear network coding and distributed storage coding), where full-rank constraints are imposed on several symbolic matrices to guarantee decodability or other properties of the codes. The derived equivalence conditions can be used to simplify the optimization of coding schemes, since the intractable full-rank constraints in the optimization problem are explicitly characterized by simple triangular-form equality constraints.

cs.IT↗

arXiv2026

A Unified Codebook Design for Curvature-Reconfigurable Apertures: Seamless Near to Far Field Coverage

Beam training for extremely large-scale arrays with curvature-reconfigurable apertures (CuRAs) faces the critical challenge of severe, geometry-dependent angle-range coupling. While most existing designs compartmentalize near field and far field scenarios, we propose a unified, distance-adaptive hierarchical codebook framework for 1-D and 2-D CuRAs that seamlessly bridges both propagation regimes. Under a spherical-wave model, we first characterize the beamforming-gain correlation in a polar angular domain, deriving an angle-dependent angular sampling rule to capture the varying curvature. To achieve full-range coverage, we introduce a direction-dependent effective Rayleigh distance (ERD) as a soft boundary to gate the range sampling. Crucially, by sampling uniformly in the reciprocal-range domain, the proposed codebook provides precise, dense focusing within the ERD and automatically degenerates into sparse, angle-only steering beyond it. This mechanism eliminates the need for hard mode-switching between near- and far-field operations. Simulation results demonstrate that our unified design consistently outperforms representative baselines in spectral efficiency and alignment accuracy, offering a comprehensive solution for full-range CuRA communications.

eess.SP↗

arXiv2026

From Natural Language to Executable Properties for Property-based Testing of Mobile Apps

Property-based testing (PBT) is a popular software testing methodology and is effective in validating the functionality of mobile applications (apps for short). However, its adoption in practice remains limited, largely due to the manual effort and technical expertise required to specify executable properties. In this experience paper, we propose a novel structured property synthesis approach that automatically translates property descriptions in natural language into executable properties, and implement it in a tool named iPBT. Our approach decomposes the problem into UI semantic grounding and executable property synthesis. It first builds an enriched widget context via multimodal LLMs to align visual elements with their functional semantics, and then uses an LLM with in-context learning to generate framework-specific executable properties. We evaluate iPBT with a closed-source LLM (GPT-4o) and an open-source LLM (DeepSeek-V3) on 124 diverse property descriptions derived from an existing benchmark dataset. iPBT achieves 95.2% (118/124) accuracy on both LLMs. Notably, an ablation study reveals that the enriched widget context contributes to an absolute improvement of up to 20.2% (from 75.0% to 95.2%). A user study with 10 participants demonstrates that iPBT reduces the time required to write executable properties by 56%, suggesting substantially lower manual effort. Furthermore, evaluations on 1,180 linguistically diverse variations demonstrate iPBT's robustness (87.6% accuracy), indicating its capability to handle varied expressions.

cs.SE↗

arXiv2026

Physical Layer Security for Sensing-Communication-Computing-Control Closed Loop: A Systematic Security Perspective

In industrial automation or emergency rescue, sensors and robots work together with the help of an edge information hub (EIH) containing both communication and computing modules. Typically, the EIH collects the sensing data via the sensor-to-EIH link, processes data and then makes decisions on board before sending commands to the robot via the EIH-to-robot link. This forms a sensing-communication-computing-control (SC3) closed loop. In practice, the inherent openness of wireless links within the closed loop leads to susceptibility to eavesdropping. To this end, this paper refines the conventional physical layer security (PLS) approach with a systematic thinking to safeguard the SC3 closed loop. The closed-loop negentropy (CNE), a new metric for the performance of the whole SC3 closed loop, is maximized under the closed-loop security constraint. The transmit time, power, bandwidth of both wireless links, and the computing capability, are jointly designed. The optimization problem is non-convex. We leverage the Karush-Kuhn-Tucker (KKT) conditions and the monotonic optimization (MO) theory to derive its globally optimal solution. Simulation results show the performance gain of the proposed systematic approach, and reveal the advantage of exploiting the closed-loop structure-level PLS over the link-level or sum-link-level designs.

cs.IT↗

arXiv2026

When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework

We investigate the challenge of applying Large Language Models (LLMs) to long texts. We propose a theoretical framework that distinguishes the failure modes of long context tasks into three categories: cross-chunk dependence (task noise), confusion that grows with context size (model noise), and the imperfect integration of partial results (aggregator noise). Under this view, we analyze when it is effective to use multi-agent chunking, i.e., dividing a lengthy sequence into smaller chunks and aggregating the processed results of each chunk. Our experiments on tasks such as retrieval, question answering, and summarization confirm both the theoretical analysis and the conditions that favor multi-agent chunking. By exploring the accelerated decay of model fidelity with input length, we also explain why, for large inputs, a weaker model configured with chunk-based processing can surpass a more advanced model like GPT4o applied in a single shot. Overall, we present a principled understanding framework and our results highlight a direct pathway to handling long contexts in LLMs with carefully managed chunking and aggregator strategies.

cs.CL↗

arXiv2026

Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models

With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has become both feasible and increasingly prevalent. However, the inherently redundant nature of video sequences poses significant challenges for contemporary state-of-the-art models. These challenges stem from two primary aspects: 1) efficiently incorporating a larger number of frames within memory constraints, and 2) extracting discriminative information from the vast volume of input data. In this paper, we introduce a novel end-to-end schema for long-form video understanding, which includes an information-density-based adaptive video sampler (AVS) and an autoencoder-based spatiotemporal video compressor (SVC) integrated with a multimodal large language model (MLLM). Our proposed system offers two major advantages: it adaptively and effectively captures essential information from video sequences of varying durations, and it achieves high compression rates while preserving crucial discriminative information. The proposed framework demonstrates promising performance across various benchmarks, excelling in both long-form video understanding tasks and standard video understanding benchmarks. These results underscore the versatility and efficacy of our approach, particularly in managing the complexities of prolonged video sequences.

cs.CV↗

arXiv2026

Continuously tunable dipolar exciton geometry for controlling bosonic quantum phase transitions

The geometry and binding energy of excitons, set by electron-hole wavefunction distributions, are fundamental factors that underpin their many-body interactions and determine optoelectronic properties of semiconductors. However, in typical solid-state systems, these quantities are fixed by material composition and structure. Here we introduce a polarizable interlayer exciton hosted in a two-dimensional tetralayer heterostructure whose dipole length, in-plane radius, and binding energy can be continuously programmed in situ over a wide range, enabling direct control over the nature of excitonic many-body phase transitions. An out-of-plane electric field redistributes layer-hybridized electron-hole wavefunctions, realizing in situ control of exciton geometry through a strong quadratic Stark response. This tunability further regulates the nature of interaction-driven Mott transition, transforming it from gradual to abrupt. Our results establish exciton geometry as a continuously tunable materials parameter, opening routes to exciton-based quantum phase-transition simulators and guiding the design of emergent optoelectronic functionalities from programmable excitonic materials.

cond-mat.mtrl-sci↗

arXiv2026

Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time

Large Language Models (LLMs) often rely on long chain-of-thought (CoT) reasoning to solve complex tasks. While effective, these trajectories are frequently inefficient, leading to high latency from excessive token generation, or unstable reasoning that alternates between underthinking (shallow, inconsistent steps) and overthinking (repetitive, verbose reasoning). In this work, we study the structure of reasoning trajectories and uncover specialized attention heads that correlate with distinct cognitive behaviors such as verification and backtracking. By lightly intervening on these heads at inference time, we can steer the model away from inefficient modes. Building on this insight, we propose CREST, a training-free method for Cognitive REasoning Steering at Test-time. CREST has two components: (1) an offline calibration step that identifies cognitive heads and derives head-specific steering vectors, and (2) an inference-time procedure that rotates hidden representations to suppress components along those vectors. CREST adaptively suppresses unproductive reasoning behaviors, yielding both higher accuracy and lower computational cost. Across diverse reasoning benchmarks and models, CREST improves accuracy by up to 17.5% while reducing token usage by 37.6%, offering a simple and effective pathway to faster, more reliable LLM reasoning.

cs.CL↗

arXiv2025

Modeling and Analysis of Land-to-Ship Maritime Wireless Channels at 5.8 GHz

Maritime channel modeling is crucial for designing robust nearshore communication systems, yet reliable models that account for the dynamic marine environment with varying sea waves, wind conditions, and vessel motions remain scarce. This article investigates land-to-ship maritime wireless channel characteristics at 5.8 GHz based upon an extensive measurement campaign, with concurrent hydrological and meteorological information collection. First, a novel large-scale path loss model with physical foundation and high accuracy is proposed for dynamic marine environments. Then, we introduce the concept of sea-wave-induced fixed-point (SWIFT) fading, a peculiar phenomenon in maritime scenarios that captures the impact of sea surface fluctuations on received power. An enhanced two-ray model incorporating vessel rotational motion is propounded to simulate the SWIFT fading, showing good alignment with measured data, particularly for modest antenna movements. Next, the small-scale fading is studied by leveraging a variety of models including the two-wave with diffuse power (TWDP) and asymmetric Laplace distributions, with the latter performing well in most cases, while TWDP better captures bimodal fading in rough seas. Furthermore, maritime channel sparsity is examined via the Gini index and Rician $K$ factor, and temporal dispersion is characterized. The resulting channel models and parameter characteristics offer valuable insights for maritime wireless system design and deployment.

eess.SP↗

arXiv2025

PersonaLive! Expressive Portrait Image Animation for Live Streaming

Current diffusion-based portrait animation models predominantly focus on enhancing visual quality and expression realism, while overlooking generation latency and real-time performance, which restricts their application range in the live streaming scenario. We propose PersonaLive, a novel diffusion-based framework towards streaming real-time portrait animation with multi-stage training recipes. Specifically, we first adopt hybrid implicit signals, namely implicit facial representations and 3D implicit keypoints, to achieve expressive image-level motion control. Then, a fewer-step appearance distillation strategy is proposed to eliminate appearance redundancy in the denoising process, greatly improving inference efficiency. Finally, we introduce an autoregressive micro-chunk streaming generation paradigm equipped with a sliding training strategy and a historical keyframe mechanism to enable low-latency and stable long-term video generation. Extensive experiments demonstrate that PersonaLive achieves state-of-the-art performance with up to 7-22x speedup over prior diffusion-based portrait animation models.

cs.CV↗

arXiv2025

StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation

The growing adoption of XR devices has fueled strong demand for high-quality stereo video, yet its production remains costly and artifact-prone. To address this challenge, we present StereoWorld, an end-to-end framework that repurposes a pretrained video generator for high-fidelity monocular-to-stereo video generation. Our framework jointly conditions the model on the monocular video input while explicitly supervising the generation with a geometry-aware regularization to ensure 3D structural fidelity. A spatio-temporal tiling scheme is further integrated to enable efficient, high-resolution synthesis. To enable large-scale training and evaluation, we curate a high-definition stereo video dataset containing over 11M frames aligned to natural human interpupillary distance (IPD). Extensive experiments demonstrate that StereoWorld substantially outperforms prior methods, generating stereo videos with superior visual fidelity and geometric consistency. The project webpage is available at https://ke-xing.github.io/StereoWorld/.

cs.CV↗

arXiv2025

Surrogate compliance modeling enables reinforcement learned locomotion gaits for soft robots

Adaptive morphogenetic robots adapt their morphology and control policies to meet changing tasks and environmental conditions. Many such systems leverage soft components, which enable shape morphing but also introduce simulation and control challenges. Soft-body simulators remain limited in accuracy and computational tractability, while rigid-body simulators cannot capture soft-material dynamics. Here, we present a surrogate compliance modeling approach: rather than explicitly modeling soft-body physics, we introduce indirect variables representing soft-material deformation within a rigid-body simulator. We validate this approach using our amphibious robotic turtle, a quadruped with soft morphing limbs designed for multi-environment locomotion. By capturing deformation effects as changes in effective limb length and limb center of mass, and by applying reinforcement learning with extensive randomization of these indirect variables, we achieve reliable policy learning entirely in a rigid-body simulation. The resulting gaits transfer directly to hardware, demonstrating high-fidelity sim-to-real performance on hard, flat substrates and robust, though lower-fidelity, transfer on rheologically complex terrains. The learned closed-loop gaits exhibit unprecedented terrestrial maneuverability and achieve an order-of-magnitude reduction in cost of transport compared to open-loop baselines. Field experiments with the robot further demonstrate stable, multi-gait locomotion across diverse natural terrains, including gravel, grass, and mud.

cs.RO↗

arXiv2025

"6 choose 4": A framework to understand and facilitate discussion of strategies for overall survival safety monitoring

Advances in anticancer therapies have significantly contributed to declining death rates in certain disease and clinical settings. However, they have also made it difficult to power a clinical trial in these settings with overall survival (OS) as the primary efficacy endpoint. Therefore, two approaches have been recently proposed for the pre-specified analysis of OS as a safety endpoint (Fleming et al., 2024; Rodriguez et al., 2024). In this paper, we provide a simple, unifying framework that includes the aforementioned approaches (and a couple others) as special cases. By highlighting each approach's focus, priority, tolerance for risk, and strengths or challenges for practical implementation, this framework can help to facilitate discussions between stakeholders on "fit-for-purpose OS data collection and assessment of harm" (American Association for Cancer Research, 2024). We apply this framework to a real clinical trial in large B-cell lymphoma to illustrate its application and value. Several recommendations and open questions are also raised.

stat.ME↗

arXiv2025

Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost

The KV cache is a dominant memory bottleneck for LLM inference. While 4-bit KV quantization preserves accuracy, 2-bit often degrades it, especially on long-context reasoning. We close this gap via an algorithm-system co-design for mixed-precision KV caching: Kitty. On the algorithm side, extensive experiments show that Dynamic Channel-wise Precision Boost -- which ranks Key-cache channels by sensitivity and keeps only a small fraction at higher precision -- maintains near-zero loss in accuracy drop while approaching 2-bit memory. The main challenge is handling dynamic 4-bit channel boosts while keeping the page layout coalesced and the dequantization uniform, with no scattered reads or hard-coded masks. Kitty addresses these issues by decompose each mixed-precision Key page into two tensors with unified 2-bit precision. Based on this, Kitty provides a page-centric KV layout, Triton-compatible page dequantization kernels, and a lightweight runtime pipeline that preserves coalescing and avoids divergence. Across seven tasks and two model families (Qwen3, LLaMA3), Kitty cuts KV memory by nearly 8x with negligible accuracy loss, enabling up to 8x larger batches and 2.1x-4.1x higher throughput under the same memory budget. We release the full implementation of Kitty at https://github.com/Summer-Summer/Kitty.

cs.LG↗