Searcharxiv⌕ Search

arXiv subjects

Yue Wang

Publications and source records attributed to Yue Wang.

At least 73 records · Page 4Linked to original sources
arXiv2026

HOTICE: Whole-Body Humanoid Object Transportation in Cluttered Environments

Object transportation is a fundamental capability for humanoid robots operating in real-world, human-centric environments, yet existing methods struggle when clutter constrains free space around both the robot and its carried payload. We present HOTICE, a whole-body humanoid learning framework for transporting objects through such cluttered environments. First, we introduce Humanoid-Object Decoupled Potential Fields, which jointly encode collision-avoidance guidance for the robot and the carried object, enabling coordinated, obstacle-aware motion for both. Second, to address the large action space inherent to whole-body loco-manipulation, we design a dual-agent reinforcement learning architecture that decouples upper- and lower-body control while preserving whole-body coordination via shared state observations and rewards. To train a policy that generalizes across diverse cluttered scenes, we further employ a specialist-to-generalist distillation strategy, in which privileged teacher policies are distilled into a single deployable student policy. We evaluate HOTICE in MuJoCo simulation and on a real Unitree G1 humanoid, demonstrating effective and robust object transportation across cluttered scenarios for objects of varying shapes. Our results show that HOTICE reliably coordinates whole-body motion and object-aware collision avoidance, generalizing effectively to previously unseen cluttered environments while achieving strong performance in sim2real deployment.

cs.RO↗
arXiv2026

BAIT: Boundary-Guided Disclosure Escalation LLM Jailbreaking via Self-Conditioned Reasoning

In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that elicits malicious information through internal disclosure by target large language models (LLMs), instead of external feedback from judge LLMs. BAIT first asks the model to identify the protection boundary, then requires it to refine that boundary, and finally requests a detailed example. By expanding each step upon the model's previous responses, BAIT turns the model's own reasoning and consistency tendency into a disclosure pathway. Experiments on AdvBench, JailbreakBench, AIR-Bench, and SORRY-Bench demonstrate that BAIT consistently achieves strong attack success rates across top-tier large language models, significantly advancing conventional jailbreak baselines. Further analysis reveals that: 1) prevention-oriented framing significantly outperforms direct knowledge requests; 2) the refinement step plays a critical role in disclosure escalation; and 3) the first two steps have a certain chance of eliciting harmful content while triggering little filtering. These findings underscore the necessity of safeguarding against internally driven reasoning trajectories that progressively cross safety boundaries.

cs.CR↗
arXiv2026

DriveReferee: Geometric Safety Verdicts Need Not Be Learned for Driving World-Action Models

Generative world-action models (WAMs) jointly generate future video and vehicle actions, while their action branches remain primarily optimized by expert imitation. Yet imitation provides no explicit closed-loop geometric verdict for generated trajectories, making verification important during both training and deployment. Closed-loop evaluators can check collision and drivable-area violations, but require privileged scene state unavailable at deployment. Existing approaches often close this gap by learning a verifier from sensor features. For these geometric checks, the rule itself is explicit. For example, collision is determined by whether the rolled-out ego footprint overlaps occupied vehicle space. What is unavailable at deployment is the scene state needed to apply the rule. We introduce DriveReferee, which uses a learned geometry readout to predict the scene representation from camera observations and executes the geometric safety rule directly rather than learning it. The resulting analytic referee evaluates collision and drivable-area safety from a scene state and candidate trajectory. During training, it scores self-sampled trajectories on ground-truth state and distills the resulting preferences into the WAM policy. At deployment, the same referee evaluates generated trajectories on this predicted state and selects a safer alternative when needed. The analytic referee requires no verdict-specific training, and its decisions follow an explicit geometric rule. Under matched candidates and inference budgets, it matches or outperforms all learned-verifier and heuristic baselines. Given the same predicted state and trajectory, learning the verdict provides no measurable downstream gain despite requiring tens of thousands of evaluator-labeled training examples. On the full NAVSIM navtest, DriveReferee reaches 92.02 PDMS with single-camera visual input and no external training data.

cs.CV↗
arXiv2026

Single-electron detection in a high-purity Ge device

High-purity germanium (HPGe) detectors are among the most powerful instruments for gamma ray spectroscopy, combining exceptional energy resolution with large active volumes. Although they operate close to the fundamental resolution limit at high energies, their performance at very low energies has long been limited by electronic noise, restricting detection thresholds to above approximately 30 electron-hole pairs ($\sim$100 eV). Here we introduce a cryogenic HPGe detector architecture that achieves single electron-hole pair sensitivity by calorimetrically measuring ionization at temperatures near 20 mK. The device integrates a NbSi transition-edge sensor into a point-contact-inspired geometry, concentrating athermal phonon energy generated during charge drift and enabling eV-scale sensitivity ultimately set by the semiconductor band gap. Beyond single-charge detection, the device rejects the low-energy excess background that limits existing cryogenic low-threshold technologies, establishing a pathway towards discrimination between electron- and nuclear-recoil events below 100 eV. These advances open a route towards next-generation detectors for direct dark matter searches, coherent elastic neutrino-nucleus scattering, and nuclear reactor monitoring for non-proliferation applications.

physics.ins-det↗
arXiv2026

G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation

Recovering the relative 6-DoF pose between two image groups underlies cross-sequence relocalization and multi-camera rig odometry. Each group carries known intra-group geometry from visual odometry or rig calibration, and pretrained multi-view backbones already fuse such geometry into visual features. Yet current models treat all views as an unstructured set, leaving cross-group reasoning as the missing piece. We introduce G2G, which keeps the foundation model entirely frozen and adds three lightweight trainable modules to bridge the two groups: a perceiver resampler, a cross-group bridge with merged self-attention, and a multi-frame pose head. The trainable footprint totals about 32M parameters, under 6% of the full model, and is supervised only by relative poses. Across four datasets that span indoor and outdoor simulation, real-world cross-season capture, and zero-shot sim-to-real transfer, G2G attains state-of-the-art accuracy on both tasks, while trainable baselines are retrained with their original supervision. Code and visualizations: https://github.com/WeiYuFei0217/G2G.

cs.CV↗
arXiv2026

Qwen-Music Technical Report

We introduce Qwen-Music, a music generation model that produces high-fidelity songs with complete vocals. It supports text-to-music generation from descriptions, lyrics, and musical attributes, and cover song generation with different styles and vocal characteristics. Qwen-Music comprises three components: Qwen-Music-Tokenizer, Qwen-Music-LLM, and Qwen-Music-Render. The tokenizer compresses audio into a 25 Hz single-codebook stream of Music Semantic Tokens that preserve semantic and melodic information. The LLM performs autoregressive modeling with a melody-token-based chain-of-thought (Melody-CoT) mechanism that plans melodies before full-song generation, improving musicality, structural coherence, and reference-melody preservation. The renderer enriches discrete semantic tokens with acoustic details to produce high-fidelity stereo waveforms. We train the LLM using a quality-aware pre-training curriculum followed by progressive post-training with supervised initialization, offline DPO, and online GSPO to improve musicality and instruction following. On 600 evaluation inputs, Qwen-Music achieves state-of-the-art results in 13 of 16 objective musicality and audio-quality metrics. Professional evaluators also prefer Qwen-Music over leading proprietary systems. For cover generation, Qwen-Music preserves reference melodies more accurately than Suno V5.5, Suno V5, and MiniMax Cover on the AI-generated reference set, and outperforms MiniMax Cover on most metrics on the real-world popular-song reference set.

cs.SD↗
arXiv2026

CREPES-X: Hierarchical Bearing-Distance-Inertial Direct Cooperative Relative Pose Estimation System

Relative localization is essential for cooperation in autonomous multi-robot systems. Existing approaches either rely on shared environmental features or inertial assumptions, or they degrade under pairwise non-line-of-sight conditions and outliers in complex environments. Robustly and efficiently fusing inter-robot bearings, distances, and inertial measurements for tens of robots remains challenging. We present CREPES-X (Cooperative RElative Pose Estimation System with multiple eXtended features), a hierarchical relative localization framework that enhances speed, accuracy, and robustness under challenging conditions, without requiring any global information. The hardware packs infrared (IR) LEDs, an IR camera, an ultra-wideband module, and an IMU into a cube no larger than $6\,\text{cm}$ on each side. On this hardware, a two-stage hierarchical estimator meets different latency, accuracy, and robustness requirements. The single-frame estimator returns instantaneous relative poses from a closed-form solution with bearing outlier rejection. The multi-frame estimator then refines these poses with IMU pre-integration under robocentric relative kinematics, using loosely- and tightly-coupled optimization. Extensive simulations and real-world experiments validate the effectiveness of CREPES-X, demonstrating robustness of up to $90\%$ bearing outliers, resilience in challenging conditions, and RMSE of $7.0\,\text{cm}$ and $2.2^\circ$ in real-world datasets.

cs.RO↗
arXiv2026

The Neverwhere Visual Parkour Benchmark Suite

State-of-the-art visual locomotion controllers are increasingly capable at handling complex visual environments, making evaluating their real-world performance before deployment increasingly difficult. This work intends to narrow this train/evaluation gap by developing a collection of hyper-photo-realistic, closed-loop evaluation environments - The Neverwhere Benchmark Suite - comprised of over sixty 3D Gaussian Splatting reconstructions of urban indoor and outdoor scenes. Our goal is to encourage large-scale and reproducible robot evaluation by making it easier to create and integrate Gaussian splats-based reconstructions into simulated continuous testing setups. We also underscore the potential pitfalls of relying exclusively on 3D Gaussian-generated data for training, by providing policy checkpoints trained over multiple Neverwhere scenes and their performance when evaluated in novel scenes. Our analysis illustrates the necessity of sourcing diverse data to ensure performance. Code and data are available on the project page: https://ziyc.github.io/neverwhere-bench/.

cs.RO↗
arXiv2026

WaveHiTS: Wavelet-Enhanced Hierarchical Time Series Modeling for Wind Direction Nowcasting in Eastern Inner Mongolia

Wind direction forecasting plays a crucial role in optimizing wind energy production, but faces significant challenges due to the circular nature of directional data, error accumulation in multi-step forecasting, and complex meteorological interactions. This paper presents a novel model, WaveHiTS, which integrates wavelet transform with Neural Hierarchical Interpolation for Time Series to address these challenges. Our approach decomposes wind direction into U-V components, applies wavelet transform to capture multi-scale frequency patterns, and utilizes a hierarchical structure to model temporal dependencies at multiple scales, effectively mitigating error propagation. Experiments conducted on real-world meteorological data from Inner Mongolia, China demonstrate that WaveHiTS significantly outperforms deep learning models (RNN, LSTM, GRU), transformer-based approaches (TFT, Informer, iTransformer), and hybrid models (EMD-LSTM). The proposed model achieves RMSE values of approximately 19.2°-19.4° compared to 56°-64° for deep learning recurrent models, maintaining consistent accuracy across all forecasting steps up to 60 minutes ahead. Moreover, WaveHiTS demonstrates superior robustness with vector correlation coefficients (VCC) of 0.985-0.987 and hit rates of 88.5%-90.1%, substantially outperforming baseline models. Ablation studies confirm that each component-wavelet transform, hierarchical structure, and U-V decomposition-contributes meaningfully to overall performance. These improvements in wind direction nowcasting have significant implications for enhancing wind turbine yaw control efficiency and grid integration of wind energy.

cs.LG↗
arXiv2026

Consensus-based Decentralized Distributed Swarm Learning with Heterogeneous Big Data

Artificial intelligence increasingly relies on large-scale, distributed, and heterogeneous data collected by edge devices. However, the practice of edge intelligence remains challenging due to non-convex objectives, data heterogeneity, and complex wireless network topology. To address these issues, this paper proposes a consensus-based decentralized distributed swarm learning (CD-DSL) framework for wireless edge networks. Our CD-DSL integrates consensus optimization with particle swarm optimization (PSO), by reaching the model consensus among neighboring devices while leveraging the PSO exploration and exploitation. The consensus mechanism supports decentralized coordination without raw-data exchange, while PSO-inspired updates utilize historical and neighbor-shared experience to enhance exploration for non-convex optimization, improve robustness to data heterogeneity, and accelerate convergence. We further develop an adaptive neighbor-mixing strategy that learns performance-aware consensus weights, improving decentralized collaboration among heterogeneous edge devices. Theoretical analysis establishes that CD-DSL maintains participant consistency and achieves non-ergodic convergence to a neighborhood of a stationary point under non-convex objectives. Experimental results show that CD-DSL can mitigate the performance degeneration of existing decentralized baselines caused by heterogeneous data.

cs.DC↗
arXiv2026

Sharp Metric Cotype Inequalities for $L_1$ via Nonlinear Cut Smoothing

For every $1\leq p<\infty$ and even integer $m\geq4$, we determine the optimal order of the $p$-moment torus inequality for $L_1$: it is $m^p n^{(1-p/2)_+}+n$, with comparison constants independent of $p,m,n$ after taking $p$-th roots. Consequently, for every $2\leq q<\infty$ and $1\leq p\leq q$, the corresponding metric cotype inequality holds at the sharp scale $m=O(n^{1/q})$. In particular, the quadratic inequality holds with $m=O(\sqrt{n})$, answering the $L_1$ sharp metric cotype question of Mendel and Naor. The proof combines finite cut representations with a nonlinear smoothing estimate and an exact ternary rounding identity.

math.FA↗
arXiv2026

PccDiffuser: Multi-solution Motion Planning for Continuum Robots

We present the PccDiffuser, a conditional diffusion framework for continuum robots that learns a multimodal distribution over complete configuration-space paths and samples multiple candidate solutions in parallel, which are subsequently converted into an executable trajectory by time allocation considering actuator constraints. Under the piecewise constant-curvature model, we use exponential co-ordinates to describe the robot kinematics, and use graph neural network to encode a variable number of environment obstacles. Analytical differential kinematics is incorporated in the denoising process to improve terminal accuracy and whole-body clearance. On a mixed test set comprising workspace with zero to four obstacles, PccDiffuser achieved a success rate of 91\%. Compared with existing sampling- and optimisation-based benchmarks, it delivered both a higher success rate and greater computational efficiency, with the latter advantage becoming more substantial when sampling more candidate solutions. Experiments on a three-section tendon-driven continuum robot further demonstrate consecutive planning, multi-solution planning, and whole-body obstacle avoidance.

cs.RO↗
arXiv2026

An integrated viscoelastic modeling framework combining analytical and FEM approaches: Application to WSe2 coatings

This work presents an integrated methodology combining analytical and finite element FEM based viscoelastic modeling for characterizing the nanoindentation response of coatings. The proposed framework combines two complementary modeling approaches: an analytical model based on the Burgers formulation to analyze nanoindentation load displacement data and extract rheological parameters, and a numerical FEM model implemented in ABAQUS using a 2D axisymmetric indenter coating substrate configuration with viscoelasticity represented through Prony series. An automated inverse optimization routine employing the Nelder Mead simplex algorithm minimizes the discrepancy between experimental and simulated responses. The methodology is demonstrated and validated on WSe2 coatings, showing an agreement between the analytical predictions, FEM simulations, and experimental measurements. Despite the geometric simplifications, the FEM approach provides accurate predictions while maintaining high computational efficiency of time dependent mechanical behavior. The proposed framework provides a robust tool for characterizing viscoelastic behavior from nanoindentation data while enabling access to internal stress and strain fields, thereby offering deeper insight into plastic deformation, crack initiation, and failure mechanism.

physics.app-ph↗
arXiv2026

Water-network decisions share one hydraulic gradient, and it can now be computed exactly

Calibration, leak localisation and sensor placement on water distribution networks (WDNs) are decisions about continuous parameters, yet the hydraulic engine that defines the physics returns a solution and no derivatives, so practice falls back on derivative-free search or on surrogates whose error the answer inherits. We make the global gradient algorithm itself exactly differentiable: the forward pass reproduces the reference engine's discrete devices, status switching and low-flow linearisation included, and the backward pass solves the implicit adjoint by reusing the forward pass's terminal factorisation, so one extra sparse solve returns every parameter's gradient at once, batched over scenarios on one graphics processor. Across 52 public, synthetic and operational networks and 8,140 simulation frames, every network meets the acceptance criterion, the largest head deviation from EPANET 2.2 is 1.137e-13 ft and 25 agree exactly. One adjoint solve replaces the 906 simulations a finite-difference roughness Jacobian costs on the 905-pipe L-TOWN benchmark, and a leak-inversion training loop runs at 463-470 ms per optimiser step for 256 scenarios, 191 times the prior pipeline. Gradient calibration reaches its endpoint within a median 595 model calls, where the strongest of five tuned metaheuristics needs 8,060 to match it on the training loss and two never do within 20,000. On a 554-link operating network, one adjoint pass audits, pipe by pipe, which roughness parameters the installed sensors can constrain and which sensors to add, on the model the utility already operates.

cs.DC↗
arXiv2026

What if LLMs Ate Their Words: Causal History Effects in Multi-Turn Interaction

Multi-turn interaction creates a feedback process in which an LLM's previous responses become context for later behavior. Prior work shows substantial multi-turn degradation and that assistant-generated history can affect later behavior. However, it remains unclear how these effects manifest across models, tasks, turns, and inside a model. We study these gaps across six task families and five models. Degradation from fully specified single-turn input (FULL) to progressively revealed multi-turn interaction (SHARDED) is clearly task- and model-dependent, and stronger one-shot performance does not imply greater interaction robustness. We then retrospectively analyze completed SHARDED conversations by replaying the user messages already observed in each trajectory while editing only assistant-generated history. Replacing prior assistant responses with neutral content (termed neutralization) changes downstream min-max normalized performance by +.027 across 2,973 trajectories. On a prespecified length-controlled subset, short and length-matched neutralization yield nearly identical effects (+.069 versus +.068), showing that simple context shortening is insufficient to explain the effect of history editing. Turn Surgery further intervenes on one assistant turn at a time. Among 237 selected degraded trajectories, 63.7% contain at least one beneficial intervention, while most tested positions remain unchanged; for binary tasks, 48.4% admit a fail-to-success reversal. An open-weight case study links behaviorally consequential history changes to measurable downstream state differences, but finds task-dependent rather than universal internal signatures. Overall, assistant-generated history has active but selective effects on multi-turn performance, motivating selective rather than uniform history management.

cs.CL↗
arXiv2026

SPARC: Spine with Prismatic And Revolute Compliance for Faster Quadrupedal Bounding

Quadruped mammals coordinate sagittal spinal bending with axial extension and compression during dynamic locomotion. Yet most robotic quadrupeds use rigid trunks, passively compliant spines with fixed properties, or actively controlled spines that track prescribed trajectories. Whether actively regulated spinal compliance can support faster dynamic locomotion remains unclear. We present SPARC, a compact 1.26-kg, 3-DoF sagittal-plane spine that combines revolute and prismatic motion with independently tunable task-space stiffness and damping. A floating-base impedance controller renders the desired task-space compliance, and benchtop tests show that the fitted axial stiffness matches commanded values within 1.5%. We integrate SPARC into an 8-DoF quadruped and evaluate it across 97 bounding trials under three spine configurations: impedance-controlled SPARC, the same SPARC module held near a fixed pose using position control, and a lightweight rigid spine. Impedance-controlled SPARC reaches 1.029 m/s, compared with 0.769 m/s for position-controlled SPARC and 0.673 m/s for the rigid spine. Impedance-controlled SPARC reaches higher speeds with larger axial motion and greater mechanical power exchange, while at matched speed it has a higher electrical cost of transport than the rigid spine, revealing an energetic trade-off. Code and hardware are available at: https://github.com/YueWang996/sparc

cs.RO↗
arXiv2026

Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR

Reinforcement learning with verifiable rewards (RLVR) improves vision-language models (VLMs) by optimizing outcome rewards derived from final answers. However, such outcome-only rewards do not tell the model which image regions justify an answer. For questions that require visual grounding, these rewards cannot distinguish responses supported by relevant visual evidence from those produced by language-prior shortcuts or lucky guesses. We introduce EASE (Evidence-Anchored Spatial Attention), which augments multimodal RLVR with visual-evidence process supervision. EASE converts annotated evidence regions into a smoothed visual-token target and uses it to guide response-to-image attention during RL training, but only on high-reward trajectories. The annotations are used solely as privileged training labels, while inference requires only the original image and question. Across Qwen2.5-VL-7B, Qwen3-VL-4B, and Qwen3-VL-8B, EASE raises average scores over DAPO by 2.5 to 3.1 points on perception, hallucination, visual math, and multimodal reasoning benchmarks. Diagnostics and ablations show that EASE better aligns visual attention with annotated evidence regions.

cs.CV↗
arXiv2026

Revisiting Topological Graphs for Macro Action based Closed-loop Reinforcement Learning of Vision Language Navigation in Continuous Environment

Vision-Language Navigation in Continuous Environments (VLN-CE) requires an agent to follow natural language instructions through unseen environments. Existing imitation learning (IL) pipelines struggle in this closed-loop setting: behavior cloning suffers from distribution shift, and DAgger's expert actions become ambiguous upon trajectory deviation. While Reinforcement Learning (RL) offers a natural paradigm to address this, directly applying RL to micro action spaces is sample-inefficient due to reward sparsity. To overcome this bottleneck, we reformulate VLN-CE as a Hierarchical Markov Decision Process (MDP), explicitly decoupling high-level planning from low-level control. By abstracting the environment into a topological graph, our high-level policy operates on a macro action space of frontier nodes, with a training-free low-level controller acting as its state transition, which significantly compresses the decision horizon and makes closed-loop RL tractable. To support RL optimization on the macro MDP, we propose an action-aware value head to effectively evaluate state values under the dynamic frontier action space, powering a graph-based PPO. Extensive experiments demonstrate the effectiveness of our architecture. Finally, our model achieves state-of-the-art performance on the R2R-CE and RxR-CE benchmarks.

cs.RO↗