Search arXiv⌕ Search

arXiv subjects

Yue Hu

Publications and source records attributed to Yue Hu.

At least 19 recordsLinked to original sources
arXiv2026

TCM-DiagCommit: A TCM-SD-Derived Benchmark for Evidence-Conditioned Syndrome Selection and Commitment

Traditional Chinese Medicine (TCM) syndrome differentiation is usually evaluated as static final-label selection over complete clinical records. This setting hides three diagnostic behaviors: whether a model distinguishes semantic-neighbor syndrome labels from easy random distractors, whether it updates predictions as evidence fields are revealed, and whether it should commit under uncertainty. We introduce TCM-DiagCommit, a benchmark derived from the public TCM-SD/ZY-BERT resource while retaining its source syndrome labels; it converts 1,834 source cases into 23,842 task rows over 148 syndrome labels. The benchmark combines random, profile-neighbor, and full-vocabulary candidate ladders with staged t1/t2/t3 evidence. It also includes fixed-label tongue/pulse perturbations and insufficient-evidence variants. A benchmark-defined action contract scores commit, acquire, defer, and abstain. Across five zero-shot DirectLLM calibrations, random10 top-1 accuracy is 63.2% to 66.4%, but hard20 falls to 24.7% to 30.3% and full148 to 14.8% to 22.3%; on hard20, WT(all) wrong-terminal commits remain 62.2% to 74.3%. These results show that final-answer accuracy alone is insufficient for diagnostic benchmark evaluation: answer selection, evidence use, and benchmark commitment scoring should be measured separately.

cs.AI↗
arXiv2026

Mapping the Solution-Set Structure of Grokking on Latin Squares

Grokking is a delayed transition from memorisation to generalisation. A network first fits observed examples while remaining near chance on held-out inputs, then generalises abruptly. Prior work has focused mainly on this delay, finding that the network's main loss becomes weight decay after the fitting phase. We name the solution to this optimization problem as the minimum-norm endpoint, and study which tasks make all minimum-norm endpoints generalise from partial observations. Specifically, we model pairwise input tasks as edge colourings of $K_{q,q}$, with Latin colourings as our structured family, and classify each observed instance as all-good, mixed, or no-good by its endpoint set. Furthermore, we prove two contrasting results: (1) Finite-abelian-group families are asymptotically all-good from partial observations; (2) Under a uniform random Latin square, all-good tasks become asymptotically rare for observation-based learners, leaving mixed or no-good behaviour. Moreover, experiments show that relabellings of addition generalise despite their dense polynomial representations. Finally, on tasks of composite order, finite-training results suggest that predictors learn a coarse part of the output before the full label.

cs.LG↗
arXiv2026

How High Can GPT-6 Astra Climb in Contact-Rich Manipulation? PhysLadder: A Hierarchical, Matched Sim-Real Benchmark for Physical Interaction

We introduce PhysLadder, a hierarchical Sim-Real benchmark for evaluating physical interaction capabilities in contact-rich manipulation. Its 16 household tasks span three cumulative levels: contact selection and geometric alignment (L1), force regulation within sustained contact (L2), and coordinated contact reconfiguration and force regulation (L3). Each task is instantiated in physically and visually matched simulated and real-world environments, with shared task definitions and success criteria. We evaluate GPT-6 Astra zero-shot with three trials per task in each environment. Real-world success rates decline from 80.0% at L1 to 47.6% at L2 and 0.0% at L3, with corresponding simulation rates of 66.7%, 47.6%, and 0.0%. Ten of the 16 tasks have identical success counts across environments; the remaining six differ by one success out of three trials. Across both environments, recurring difficulties in spatial reasoning, contact selection, force regulation, and coordination often prevent local physical progress from accumulating into task completion. These findings characterize Astra's observed capability boundary across increasing interaction demands and, for this model, support matched simulation as a repeatable, scalable testbed for studying the sustained, coordinated physical interactions that limit reliable manipulation.

cs.RO↗
arXiv2026

Think Before You Transcribe: Context-Steered Reasoning for Hotword-Aware Speech Recognition

Contextual automatic speech recognition (ASR) improves rare-entity recognition by supplying candidate hotwords, but retrieved candidates may be incomplete or incorrect. A reliable system must therefore exploit a relevant candidate without allowing unsupported alternatives to override the acoustic evidence. We propose a context-steered reasoning framework that generates a short, audio-grounded caption before transcription. This task-specific representation lets the model assess candidate relevance before making a lexical decision. Supervised fine-tuning establishes the structured caption-to-transcription behavior, while targeted trajectory injection strengthens group relative policy optimization when difficult utterances yield only unsuccessful rollouts. Experiments across diverse context conditions show that the proposed method consistently improves both transcription quality and hotword recognition while remaining robust to irrelevant candidates.

cs.CL↗
arXiv2026

Integral forms for Yangians of classical type

Let $\mathfrak g$ be a simple Lie algebra of classical type. We construct a $\mathbb Z[1/2]$-integral form of the Yangian $Y(\mathfrak g)$ generated by divided powers of the positive and negative Drinfeld generators, and establish its triangular decomposition and PBW basis. Under the loop filtration, its associated graded algebra is the current algebra part of Garland's integral form. As applications, over an algebraically closed field of characteristic $p>3$, we identify the small Yangian with the restricted Yangian and classify their finite dimensional simple modules in terms of restricted Drinfeld polynomials.

math.QA↗
arXiv2026

Intermittency in the Multiphase ISM --- I. Extreme Density, Velocity, and Magnetic Fluctuations

Intermittency is a fundamental property of astrophysical turbulence because it concentrates strong gradients, dissipation, and transport into rare, localized structures. In the multiphase interstellar medium (ISM), turbulent driving is especially important because the balance between compressive and solenoidal motions can regulate how extreme fluctuations are distributed among thermal phases. Yet conventional increment statistics quantify intermittency without identifying the structures that host it. We analyze three matched ideal-MHD simulations of a thermally multiphase neutral medium that differ only in the compressive fraction of the driving. Density, velocity, and magnetic-field increments are non-Gaussian in every thermal phase. Increasing compressive driving redistributes density and magnetic fluctuations preferentially into the cold gas rather than uniformly enhancing them across phases. We identify the structures associated with extreme increments using local, scale-matched diagnostics of compression, thermal gradients, vorticity, strain, magnetic curl, and magnetic tension. Extreme magnetic increments preferentially occur where magnetic curl and magnetic tension are simultaneously enhanced, more strongly than extreme velocity increments are associated with their kinematic hosts. Extreme velocity increments show comparable enrichment in vorticity and strain, whereas extreme density increments preferentially trace converging flows and thermal gradients only in the unstable medium. These associations weaken beyond a phase-dependent coherence scale. Our results show that turbulent driving controls how intermittency is partitioned among thermal phases, while distinct physical structures host extreme density, velocity, and magnetic fluctuations.

astro-ph.GA↗
arXiv2026

Intermittency in the Multiphase ISM --- II. Non-Gaussian Dust Polarization and Foreground Variance

Interstellar turbulence produces non-Gaussian polarized Galactic dust emission whose higher-order statistics depend on thermal phase and turbulent forcing. We synthesize optically thin dust polarization from three thermally multiphase diffuse interstellar medium (ISM) simulations with compressive, mixed, and solenoidal forcing. We characterize the resulting non-Gaussian structure in the warm, unstable, and cold phases using $E$- and $B$-mode spectra, one-point distributions, scale-dependent increments, and Minkowski functionals. Both $E$ and $B$ modes are intermittent. Warm-phase emission remains closest to Gaussian, whereas cold gas shows flatter intermediate-scale spectra, broader non-Gaussian tails, and the strongest departures from Gaussian morphology. Compressive forcing generally produces the strongest projected intermittency, particularly in the cold phase and total emission, while mixed and solenoidal forcing show weaker signatures. These higher-order structures also enhance spatial fluctuations in polarized dust power: Gaussian fields matched to the same two-point covariance underestimate the region-to-region scatter by factors of up to $\sim2.6$. Our results show that thermal phase and turbulent forcing regulate not only the mean polarized dust spectrum but also the field-to-field distribution of foreground power, with implications for modeling Galactic foreground in CMB polarization measurements.

astro-ph.GA↗
arXiv2026

SearchWorld: Spatial Value-Grounded Imagination for UAV Object Search via World Models

Autonomous unmanned aerial vehicle (UAV) object search involves a closed loop of perception, decision-making, and action under partial observability. Urban environments pose several challenges: large search areas and narrow egocentric views limit coverage, dense 3D geometry constrains safe motion, and open-world instructions require identifying a specific target among distractors. Many existing methods mitigate partial observability through explicit maps or memory representations, yet remain largely reactive, reasoning over past observations without explicitly predicting future states. World models enable prospective reasoning through imagined rollouts. However, image-generating world models can incur high inference latency, while spatially grounded planning remains challenging for latent world models. We propose SearchWorld, a recurrent state-space world model that connects explicit spatial memory with value-guided imagination. The model maintains BEV exploration and obstacle memory and decodes a task-aware spatial value layer to guide search. A cognition-action network uses this learned spatial value prior to improve the policy through imagined rollouts, without training a separate scalar critic. Training progresses from world-model learning to expert imitation and imagination-based exploration refinement. On UAV-ON, SearchWorld improves the success rate to 23.8% (19.5% for the strongest published agent) and raises oracle success to 35.5%, while remaining robust on unseen scenes (19.9% success rate). By grounding imagination in explicit spatial representations, SearchWorld enables UAV agents to plan prospectively rather than react.

cs.AI↗
arXiv2026

A photonic integrated comb engine for ultracold quantum gases

Cold atoms underpin quantum sensing, simulation and computation, but their coherent control demands highly stable optical fields whose generation, referencing and power scaling remain formidable integration challenges. While photonic integrated circuits have yielded compact visible lasers and high-$Q$ microresonators have enabled chip-scale optical frequency combs, these crucial technologies have largely remained functionally fragmented. Consequently, the coherent manipulation of ultracold quantum gases using a fully integrated laser-comb source has yet to be realized. Here we demonstrate a scalable, hybrid-integrated microcomb engine at 780 nm that seamlessly bridges frequency synthesis, atomic referencing and power amplification to achieve quantum state control of a Bose--Einstein condensate. By self-injection locking of electrically driven III--V lasers to high-$Q$ Si$_3$N$_4$ microresonators, we generate coherent platicon microcombs featuring 20- and 100-GHz mode spacings. Absolute referencing of the microcomb to an $^{85}$Rb transition actively suppresses long-term frequency drift from over 200 MHz to the 100-kHz level across 2,000 s. A selected comb tooth is subsequently injection-amplified to 102 mW, entirely preserving the microcomb's pristine coherence and stability. We utilize this synthesized field to construct an optical lattice, drive coherent two-photon Raman transitions, and prepare stationary spin--orbit-coupled and Raman-lattice states within an $^{87}$Rb condensate. By providing a synchronized optical grid, this atom-referenced microcomb can allow multiple optical-control channels to scale without a proportional multiplication of independent frequency references. Our work establishes a fully integrated frequency-synthesis architecture essential for realizing deployable, large-scale atomic quantum systems.

physics.optics↗
arXiv2026

CSIR: Contextually and Socially Informed Robots for Efficient Person Goal Navigation

We address the Person Goal Navigation (PersonNav) problem, enabling robots to search for people under realistic constraints on information accessibility and language uncertainty. This tackles the current solutions revolving around rigid person finding systems requiring exact knowledge of the individual for item-delivery in indoor settings. While the focus in literature is on learned methods using unavailable public or sparse data due to human privacy. We propose a planning framework that combines distance and semantic information about the recipient (habits and intent) weighted by the trust of the user-provided information. A synthetic benchmark of scenarios is also developed including actors, items, and requests to evaluate performance before real-world deployment aiming to simulate natural language human-robot interactions. Results show our informed search outperforms classical distance-based graph baselines, while semantics alone lead to ungrounded, sporadic search. Our method achieves strong gains over baselines, with an LLM-based variant performing comparably, and its explicit belief representation naturally supports future Bayesian filtering. Hardware tests demonstrate our method supports real-world embodiment able to leverage between semantic and distance information in a real setting. This work moves toward more intelligent mobile service agents capable of human-like, informed search in realistic environments to be leveraged in day-to-day use. https://anonymous.4open.science/r/personnavsite-4ED2/index.html.

cs.RO↗
arXiv2026

A visual large language foundational model for medical image recognition using clinician-contributed online resources

Large language models (LLMs) have demonstrated strong capabilities across diverse domains, showing considerable potential in medicine. However, their application in medical settings remains limited by the scarcity of visual question answering (VQA) datasets that capture clinical reasoning and explicit image-text alignment. Here, we leverage de-identified medical images and expert commentaries shared through clinician-oriented online resources. By combining an advanced LLM with clinician-in-the-loop verification, we established a rigorous pipeline to construct ThoughtMed-1M, a long-form medical VQA dataset containing over one million VQA pairs and designed to capture structured clinical reasoning and medical image-text alignment. To demonstrate its utility, we developed a FOundational LLM Trained on ThoughtMed-1M (FOLTMed). FOLTMed achieved state-of-the-art performance across 42 medical VQA benchmark datasets, with a macro accuracy of 85.4 percent. It also generated more clinically coherent responses on the ThoughtMed-1M test set, outperforming state-of-the-art models by 3 to 5 percent across factuality and similarity metrics, highlighting a scalable paradigm for advancing research on clinically grounded multimodal LLMs.

cs.AI↗
arXiv2026

CityToolVQA: Tool-Augmented Visual Question Answering for 3D Spatial Cognition in Urban Low-Altitude Environments

CityToolVQA addresses the weak performance of Vision-Language Models (VLMs) on quantitative tasks in urban low-altitude visual question answering. We divide the seven tasks into qualitative and quantitative groups: qualitative questions are answered directly by the VLM, whereas quantitative questions are handled by an external visual-geometric toolchain that performs object grounding, segmentation, depth back-projection, and spatial computation. The toolchain can be attached to different VLMs in a zero-shot manner; a Depth-Assisted Prompt Inference (DAPI) fallback is triggered when the main-chain detection is invalid or unreliable, and CityToolVQA-SFT adapts the 8B backbone to tool-conditioned inputs. On the 73,324-question Open3D-VQA-v2 test set, CityToolVQA-SFT (Qwen3-VL-8B) reaches 67.6% overall accuracy, and attaching the toolchain to ten open-source VLMs improves quantitative-task accuracy by 12.7-36.9 percentage points. These results indicate that externalizing explicit 3D geometric computation effectively complements the limited ability of RGB-only VLMs to estimate metric distances and object sizes.

cs.CV↗
arXiv2026

Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation

Semantic navigation requires an agent to navigate toward a specified target in an unseen environment. Employing an imaginative navigation strategy that predicts future scenes before taking action, can empower the agent to find target faster. Inspired by this idea, we propose SGImagineNav, a novel imaginative navigation framework that leverages symbolic world modeling to proactively build a global environmental representation. SGImagineNav maintains an evolving hierarchical scene graph and uses large vision language models to predict and explore unseen parts of the environment. While existing methods solely relying on past observations, this imaginative scene graph provides richer semantic context, enabling the agent to proactively estimate target locations. Building upon this, SGImagineNav adopts an adaptive navigation strategy that exploits semantic shortcuts when promising and explores unknown areas otherwise to gather additional context. This strategy continuously expands the known environment and accumulates valuable semantic contexts, ultimately guiding the agent toward the target. SGImagineNav is evaluated in both real-world scenarios and simulation benchmarks. SGImagineNav consistently outperforms previous methods, improving the success rate to 65.4% and 66.8% on HM3D and HSSD, and demonstrating cross-floor and cross-room navigation in real-world environments. All source code is open-sourced at https://github.com/UMich-CURLY/SGImagineNav.

cs.RO↗
arXiv2026

LongNav-R1: Horizon-Adaptive Multi-Turn RL for Long-Horizon VLA Navigation

This paper develops LongNav-R1, an end-to-end multi-turn reinforcement learning (RL) framework designed to optimize Visual-Language-Action (VLA) models for long-horizon navigation. Unlike existing single-turn paradigm, LongNav-R1 reformulates the navigation decision process as a continuous multi-turn conversation between the VLA policy and the embodied environment. This multi-turn RL framework offers two distinct advantages: i) it enables the agent to reason about the causal effects of historical interactions and sequential future outcomes; and ii) it allows the model to learn directly from online interactions, fostering diverse trajectory generation and avoiding the behavioral rigidity often imposed by human demonstrations. Furthermore, we introduce Horizon-Adaptive Policy Optimization. This mechanism explicitly accounts for varying horizon lengths during advantage estimation, facilitating accurate temporal credit assignment over extended sequences. Consequently, the agent develops diverse navigation behaviors and resists collapse during long-horizon tasks. Experiments on object navigation benchmarks validate the framework's efficacy: With 4,000 rollout trajectories, LongNav-R1 boosts the Qwen3-VL-2B success rate from 64.3% to 73.0%. These results demonstrate superior sample efficiency and significantly outperform state-of-the-art methods. The model's generalizability and robustness are further validated by its zero-shot performance in long-horizon real-world navigation settings. All source code is open-sourced at https://github.com/UMich-CURLY/LongNav-R1.

cs.RO↗
arXiv2026

Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method

Air-Ground Object Search (AGOS) in urban environments is a challenging embodied task, which requires an Unmanned Aerial Vehicle (UAV) and an Unmanned Ground Vehicle (UGV) to jointly search for and verify a specified target vehicle from multi-view visual references. To study this underexplored problem, we introduce AGOS-Bench, the first dedicated benchmark for evaluating whether general-purpose Vision-Language Models (VLMs) can integrate aerial discoveries and ground-level verification through UAV-UGV cooperation. We further provide AGOS-Dataset as the companion resource of exemplary trajectories constructed by an automatic pipeline. It consists of 7.7k episodes for searching objects of diverse categories and attributes, spanning three difficulty levels. To address the AGOS task, we propose AGOS-Agent, a training-free and tool-augmented approach. The agentic method relieves VLMs from complex and dynamic coordination via a deliberate search-handoff-verify cooperation protocol, only demanding VLMs for scene understanding and decision-making. Extensive experiments on nine VLMs show that AGOS-Agent improves overall success rate for eight of the nine evaluated backbones while reducing decision steps for all nine. On the hard split, the SR and SPL of Gemini-3.6-Flash increase from 8.6% to 55.7% and from 7.6% to 44.0%, respectively.

cs.CV↗
arXiv2026

Self-Trapping Enabled Highly Bright Momentum-Indirect Interlayer Excitons

Interlayer excitons in two dimensional material heterostructures exhibit large exciton binding energies and long lifetimes, making them ideal platforms for studying excitonic devices and many body quantum phenomena. However, the spatially separated electron and hole nature of IXs reduces their oscillator strength by two orders of magnitude compared to intralayer excitons. Achieving high efficiency IX emission remains challenging and requires optimal material selection with appropriate momentum matching and meticulous device fabrication. Here we demonstrate a highly bright momentum indirect IX emission within heterostructures formed between 2D perovskites and monolayer transition metal dichalcogenides. The quantum yield of IX emission reaches 35.2% on average, over 50 times higher than that of the corresponding constituent TMD monolayer, with the highest value exceeding 60%. Notably, the radiative recombination efficiency of this momentum indirect IX exceeds that of momentum direct IXs in monolayer TMD-based heterostructures by two orders of magnitude. We suggest that the remarkably bright IX emission in our heterostructure originates from IX self trapping, induced by strong exciton phonon coupling arising from the soft lattice nature of the 2D perovskite. Our findings provide new insights into achieving high IX emission efficiency and open new avenues for exploring long lifetime excitonic devices.

cond-mat.mes-hall↗
arXiv2026

Invariant Jacobian and the Center of a Homogeneous Form

We study homogeneous forms with invariant Jacobian under group actions. For finite-dimensional irreducible complex representations, we show that the canonical decomposition defined by the center of the form is either trivial or gives a system of imprimitivity, which determines the module structure of Jacobian $J(f)$. We apply the theory to symmetric groups and classify homogeneous forms with invariant Jacobian on the natural permutation module.

math.RT↗
arXiv2026

Map the Possibilities: Spatial Belief Fields for Language-Goal Aerial Navigation

Language-goal aerial navigation requires an agent to local- ize a potentially unobserved target from relational instruc- tions and partial observations, and translate this inference into metric actions in large-scale continuous environments. Existing methods often reduce language grounding to one single waypoint or action, prematurely collapsing the spatial uncertainty inherent in incomplete evidence and ambiguous relations. To address this limitation, we introduce SBFNav, a closed-loop navigation framework centered on a language- conditioned Spatial Belief Field (SBF). Unlike ego-centric maps that primarily record what has been observed, SBF rep- resents a task-conditioned distribution over plausible target locations, preserving multiple spatial hypotheses under par- tial evidence. At each step, this distribution is updated from accumulated observations as new evidence becomes avail- able. Built on this representation, SBFNav selects the goal that best aligns with the instruction and observations as a met- ric waypoint for control. Experiments on both the original and revised CityNav benchmarks achieve the best reported overall performance. On the Test Unseen split, our method improves SR from 25.91% to 32.29% and SPL from 19.63% to 30.43%. Ablation studies further confirm the advantages of spatial-belief modeling over single-point prediction.

cs.CV↗