Search arXiv⌕ Search

arXiv subjects

Bing Wang

Publications and source records attributed to Bing Wang.

At least 19 recordsLinked to original sources
arXiv2026

EmbodiExp: Compositional Experience Transfer for Embodied Agents

Experience can help embodied agents turn high-level plans into grounded actions, but transferring it across tasks remains challenging: previously effective strategies may be inapplicable to the current state or fail to produce their intended outcomes. We present EmbodiExp, a framework for constructing transferable experiences and composing them online during embodied task execution. Our key observation is that tasks often share subgoals whose completion can be assessed independently of overall task success. We therefore introduce an outcome-grounded subgoal experience that specifies a subgoal, applicability conditions, an adaptable policy, and a verifiable outcome. During execution, applicable experiences guide action generation, while verified outcomes can establish the conditions required by subsequent experiences, enabling online composition. Subgoal-level outcome attribution further enables failure utilization: failed trajectories can still contribute verified local successes and condition-specific guidance on actions to avoid. Experiments on multiple embodied benchmarks under a fold-based protocol with frozen experience banks demonstrate the effectiveness of EmbodiExp.

cs.RO↗
arXiv2026

PhyMo: Learning Physical Dynamics with Accurate and Continuous Motion from Multi-View Videos

Recovering dynamic 3D scene geometry, appearance, and the physical motion states that govern scene evolution from multi-view videos is important yet challenging. A key difficulty is that appearance can be deceptive. Under rendering supervision alone, a model may fit the observed images by changing color or opacity to compensate for inaccurate deformation, rather than recovering the true evolving geometry and motion. This issue is especially severe in scenes with fast or locally complex motion, where inaccurate trajectories can still produce plausible images over the observed frames, but lead to unreliable reconstruction and discontinuous future prediction. In this paper, we propose PhyMo, a framework for learning evolving dynamics from multi-view videos. We introduce a Motion-Aware Trajectory Representation that drives the model to recover accurate motion from deformation, rather than relying on appearance shortcuts to explain observed motion. On top of this, we propose a Continuous Motion Evolution module with bidirectional kinematic continuity constraint to promote temporally consistent evolution of displacement, velocity, and acceleration. Together, these designs yield geometrically faithful interpolation and continuous motion extrapolation. Experiments on four dynamic scene benchmarks demonstrate state-of-the-art performance.

cs.CV↗
arXiv2026

Towards Spatio-Temporal Intelligence Systems in Urban Space: A Twin-Agent Perspective

Cities must coordinate domains like infrastructure, mobility, environmental management, emergency response, and public services as conditions evolve. An urban Spatio-Temporal Intelligence (STI) system helps the city monitor citywide states, analyze problems, plan and execute interventions, and adapt through feedback, making urban governance more timely, effective, and transparent. Recent urban twinning and agentic AI techniques provide foundations for such systems. From a twin-agent perspective, this survey takes a system-level view of how these disparate techniques can be coherently integrated into an urban STI system. Specifically, we review how the twin reconstructs and represents a persistent, information-enriched urban environment, and how the agent understands the twin via interfaces, reasons over it, acts reliably, and continuously evolves with the city. Built upon this synthesis, we summarize a two-loop blueprint, where an inner agent loop for grounding, reasoning, and verification, and an outer system loop linking data, twin, agentic action, feedback, and update. We then use this to structure an STI research agenda and show how a shared prototype supports diverse urban domains.

cs.CV↗
arXiv2026

AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving

While reasoning technology like Chain of Thought (CoT) has been widely adopted in Vision Language Action (VLA) models, it demonstrates promising capabilities in end to end autonomous driving. However, recent efforts to integrate CoT reasoning often fall short in simple scenarios, introducing unnecessary computational overhead without improving decision quality. To address this, we propose AdaThinkDrive, a novel VLA framework with a dual mode reasoning mechanism inspired by fast and slow thinking. First, our framework is pretrained on large scale autonomous driving (AD) scenarios using both question answering (QA) and trajectory datasets to acquire world knowledge and driving commonsense. During supervised fine tuning (SFT), we introduce a two mode dataset, fast answering (w/o CoT) and slow thinking (with CoT), enabling the model to distinguish between scenarios that require reasoning. Furthermore, an Adaptive Think Reward strategy is proposed in conjunction with the Group Relative Policy Optimization (GRPO), which rewards the model for selectively applying CoT by comparing trajectory quality across different reasoning modes. Extensive experiments on the Navsim benchmark show that AdaThinkDrive achieves a PDMS of 90.3, surpassing the best vision only baseline by 1.7 points. Moreover, ablations show that AdaThinkDrive surpasses both the never Think and always Think baselines, improving PDMS by 2.0 and 1.4, respectively. It also reduces inference time by 14% compared to the always Think baseline, demonstrating its ability to balance accuracy and efficiency through adaptive reasoning.

cs.CV↗
arXiv2026

Yb/Sr optical clock comparison at 2.2E-18 uncertainty over a 1350-km fiber link

Redefining the International system of Units (SI) second requires independent frequency-ratio measurements between clocks based on different laboratories, with an overall uncertainty below 5E-18, to validate individual clock evaluations through consistency checks. Reaching this uncertainty over long distances has remained challenging. So far, comparisons at this level have been achieved only a few times, between co-located clocks, and their results disagree markedly. Previous high-precision comparisons have therefore been limited to local or kilometre-scale links. Here we compare a ytterbium optical lattice clock in Wuhan with a strontium optical lattice clock in Shanghai over a phase-stabilized fiber link spanning 1350 km, and determine the Yb/Sr frequency ratio to be 1.207 507 039 343 337 716 0(26), with a Bayesian statistical uncertainty of 1.14E-18 and a total uncertainty of 2.18E-18. To our knowledge, this is the first intercity long distance frequency-ratio measurement, whose total uncertainty reaches the level required by the redefinition roadmap. The measured ratio exhibits a significant correlation with Earth tides and its response agree with the model within the statistical uncertainty. At intercity scale, this comparison demonstrates the capability of an optical-clock network for frequency comparison and Earths gravitational-potential sensing, a key step toward a wide-area optical-clock network.

physics.optics↗
arXiv2026

PocketGS: High-Fidelity On-Device Training for 3D Gaussian Splatting

Although 3D Gaussian Splatting (3DGS) supports real-time rendering, training relies on offline geometry, long-horizon densification, and memory-intensive differentiation. We cast post-capture static-scene training as resource-constrained finite-horizon optimization, where terminal quality depends jointly on the initial representation and reference-consistent gradient execution. To the best of our knowledge, PocketGS is the first publicly documented pipeline to complete geometry construction, Gaussian initialization, and 3DGS optimization on a commodity smartphone. Its I, G warm start combines refined poses, a filtered dense prior, and surface-aligned anisotropic Gaussians. Its T operator replays compositing interactions and scatters gradients to canonical parameters, matching a numerical reference at the reported precision. Controlled 500-step experiments on LLFF, Mip-NeRF 360, and MobileScan show high-quality reconstruction at the device horizon. Across MobileScan, every scene remains below 3 GB peak memory and post-capture processing averages 255.2 s, enabling an on-device capture-to-render workflow. Separate 30k experiments characterize native-schedule behavior.

cs.CV↗
arXiv2026

PointForward V2: Point-Aligned Interaction for Feedforward Driving Reconstruction

Feedforward reconstruction of dynamic driving scenes requires integrating observations across multiple views and time steps into a coherent 3D representation. PointForward established state-of-the-art feedforward driving reconstruction by lifting image observations into sparse 3D queries, demonstrating the effectiveness of point-aligned scene representations. However, these queries are largely processed independently, limiting information exchange across space and time, while direct global attention among tens of thousands of point queries is computationally prohibitive. In this work, we present \textbf{PointForward V2}, which advances point-aligned representation to point-aligned interaction. Our key idea is to mediate query interaction through compact, scene-structured registers. For the static background, frame-wise Static Scene Registers compress point information, communicate across frames, and propagate the aggregated context back to the queries. For each dynamic instance, queries from different frames are aligned in an object-centric canonical space and interact through instance-specific Dynamic Instance Registers. We further employ 4D positional encoding that combines aligned spatial coordinates with original timestamps, enabling spatially aligned yet temporally distinguishable interactions. In this way, PointForward V2 enables scalable spatio-temporal reasoning directly among lifted 3D queries without dense global attention. Experiments on Waymo, nuScenes, and Argoverse 2 demonstrate state-of-the-art performance across large-scale driving benchmarks.

cs.CV↗
arXiv2026

Topologically steerable ultra-flat electro-optic combs via non-Hermitian frequency lattices

Electro-optic (EO) frequency combs convert microwave signals to the optical domain with deterministic repetition rates, enabling applications in optical telecommunications, microwave photonics, and LiDAR. However, generating flat EO combs has remained a long-standing challenge due to exponential decay of the spectral envelope inherent to bidirectional frequency coupling within conventional schemes. Here we reveal the inherent correspondence between flat-comb generation and the topological energy bands of non-Hermitian nonreciprocal frequency lattices, and experimentally realize ultra-flat combs with topologically controlled spectral flow. We derive the exact analytical condition for flat-comb generation, and find that it maps precisely onto the complex energy band, thereby establishing a direct connection between comb-envelope engineering and non-Hermitian topology. Experimentally, we observe an ultra-flat comb whose frequency evolution direction is governed by the topological winding and remains robust against detuning and phase fluctuations. This scheme can be further extended to long-range coupling and multi-lattice architectures, underscoring its versatility for flat dual- and multi-comb generation. Our work establishes a topologically steerable approach for achieving ultra-flat EO combs, paving the way for chip-scale spectral engineering via non-Hermitian topology.

physics.optics↗
arXiv2026

Learning to Retrieve: Internalizing Memory Retrieval for Video World Models

Video world models aim to generate explorable, 3D-consistent scene videos conditioned on camera trajectories. Existing approaches often rely on external memory systems that explicitly retrieve previously observed content to mitigate scene drift during long-horizon generation. However, these auxiliary memory pathways operate outside the model's internal generative dynamics, preventing the model from intrinsically learning when and what historical information should be retrieved. We propose to internalize memory retrieval into the generation process, allowing retrieval to emerge as an intrinsic behavior of the video world model rather than relying on an external memory system. Based on this principle, we introduce \textbf{Learning-to-Retrieve (L2R)}, which repurposes the model's persistent internal state as a memory for historical context. A camera-conditioned retrieval gate selectively accesses relevant historical information from this state, determining \textit{what to retrieve}, while a retrieval trigger determines \textit{when to retrieve}. We further supervise the trigger with a 3D re-visibility signal, activating retrieval when previously observed content re-enters the current view while otherwise preserving the existing context. Together, these components enable the model to intrinsically acquire memory retrieval behavior and incorporate relevant historical observations into generation without a separate retrieval pathway. Across multiple base models and camera-revisit benchmarks, L2R improves long-term scene consistency while eliminating the need for an external memory bank or 3D conditions. https://jkhu29.github.io/l2r

cs.CV↗
arXiv2026

On the tangent flows of noncollapsed Ricci flow limit spaces

We study tangent flows of noncollapsed Ricci flow limit spaces in the sense of Fang-Li. We prove that the regular part of every negative time slice is geodesically convex: any minimizing geodesic that meets the regular part has its entire interior contained in it. We also identify each negative time slice with the metric completion of its regular Riemannian part, thereby identifying the negative-time tangent flow with its associated metric soliton.

math.DG↗
arXiv2026

Modeling Shared and Individual Structure for Cross-Subject Continuous Affect Regression from EEG-fNIRS

Continuous, second-by-second valence-arousal estimation from physiological signals is typically studied in a subject-dependent setting, where the model sees labeled data from the same person it is later evaluated on. We study the harder zero-shot cross-subject variant on a synchronized EEG-fNIRS dataset: predict raw-scale ([1, 255]) valence and arousal trajectories for subjects whose labels the model never observes, given only their unlabeled EEG/fNIRS recordings while watching the same video stimuli as a disjoint set of training subjects. We decompose the affect trajectory into a structure shared across subjects who watch the same stimuli and an individual structure estimated for each test subject from a label-free EEG marker (alpha-band cross-channel synchrony), which rescales the shared trajectory around the scale midpoint. We validate the per-subject calibration mechanism on four independent axes: leave-one-subject-out correlation between the marker and each subject's true optimal gain, a functional-form comparison against non-linear alternatives, a repeated leave-4-out component ablation isolating each part of the pipeline's contribution, and a ceiling analysis bounding the remaining headroom for per-subject scaling. On held-out subjects, the model reaches an overall MAE of 25.96 / 22.80 across two evaluation batches (valence 21.94 / 19.6, arousal 29.98 / 26.0), well below EEGNet and ASAC-Net baselines reported for the same subject-independent split (raw scale score 60.6 and 55.0 respectively). We further report a systematic negative-result search across model architectures, feature representations, and prediction targets that found no signal able to improve on the single alpha-synchrony marker.

cs.AI↗
arXiv2026

PocketSplat: Mobile Gaussian Reconstruction via World-Space Latent Allocatio

Mobile Gaussian reconstruction must satisfy two requirements: the reconstruction model must execute within a device resource envelope, and the resulting Gaussian asset must expose a representation size suited to downstream mobile use. Existing feed-forward Gaussian reconstructors commonly decode dense, image-aligned candidates whose final cardinality is implicitly determined by the input resolution and number of views. We present PocketSplat, a feed-forward framework for budgeted mobile Gaussian asset construction. Given a prescribed output budget, PocketSplat organizes dense geometry-aware latent candidates in predicted world space, allocates exact integer capacity across local latent cells, and decodes complete Gaussian attributes only for retained candidates. Cell-conditioned latent fusion aggregates repeated multi-view evidence before decoding, while spatial responsibility decoding adapts Gaussian support after local sparsification. Experiments on DL3DV and out-of-distribution benchmarks establish a strong quality--budget trade-off against feed-forward Gaussian reconstruction baselines. On Mip-NeRF 360, PocketSplat executes directly on a target iPhone and constructs compact, higher-quality Gaussian assets substantially faster than a deployable streamed MVSplat variant; native MVSplat and DepthSplat exceed the device memory budget.

cs.CV↗
arXiv2026

Beyond Retrieval Relevance: Scene-Grounded Risk Entailment for Vision-Language Driving

Retrieval-augmented generation (RAG) gives vision--language driving systems access to external safety knowledge, yet a retrieved risk rule may be relevant without applying to the current scene. A vision--language model (VLM) receiving such knowledge must ground objects, bind entities across time, and verify relations before deciding how to act, leaving the support for risk conclusions implicit. We address this relevance--applicability gap with a Driving-Risk Knowledge Graph (DRKG) and Semantic Web Rule Language (SWRL) reasoning stage before VLM decision-making. Structured perception instantiates scene facts, from which SWRL rules derive events and directed risk relations when their antecedents are jointly satisfied. Recognized events, bound risk relations, and semantic descriptions of activated rules form compact evidence that conditions the VLM and diffusion planner. In matched comparisons on nuReasoning, our method improved the nuReasoning planning score (NPS) by 1.30 points and the non-at-fault collision score (NC) by 2.76 points over the relevance retrieval-based baseline. These gains indicate that scene-applicable risk evidence improves safety-weighted planning relative to semantically retrieved risk knowledge.

cs.RO↗
arXiv2026

A Vision-Language Foundation Model for Precise and Comprehensive Brain Tumor Diagnosis from Preoperative Multimodal Data

We developed BrainVLM to classify all 12 World Health Organization (WHO) 2021 brain tumor types. BrainVLM integrates an uncertainty quantification strategy to indicate prediction reliability and a module for generating radiology reports to elucidate the clinical rationale. BrainVLM was trained on multi-modal data (MRI scans, demographics, and radiology reports) from 40,043 individuals. It was validated on 5,211 patients with pathologically confirmed brain tumors, including 3,877 held-out patients from the primary hospital and 1,334 patients from 11 independent hospitals. We further conducted two proof-of-concept studies to validate its clinical utility in AI-clinician workflows: 1) a blinded multireader study where 12 neuroradiologists across varying experience levels interpreted 248 retrospective cases with or without AI assistance, and 2) a real-world prospective study in which 1,009 patients were independently and blindly assessed by BrainVLM and radiologists before surgery. Additionally, we demonstrated BrainVLM's utility in preoperative molecular subgroup prediction for adult-type diffuse gliomas, using a multi-center cohort of 632 patients. In primary evaluation, BrainVLM achieved an area under the curve (macro-AUC) of 0.85 (95% CI: 0.84-0.86), and an F1 score of 0.82 (95% CI: 0.81-0.83), surpassing neuroradiologists (F1 = 0.80 (95% CI: 0.79-0.81)). In external validation across 11 centers, BrainVLM achieved an AUC = 0.80 (95% CI: 0.79-0.82) and F1 = 0.75 (95% CI: 0.73-0.78), compared with F1 = 0.71 (95% CI: 0.69-0.73) for neuroradiologists. In prospective real-world evaluation, BrainVLM maintained performance comparable to neuroradiologists. The BrainVLM project page is available at https://hku-healthai.github.io/brainvlm_project.github.io/.

cs.CV↗
arXiv2026

Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models

Continual fine-tuning is essential for large language models (LLMs) to dynamically adapt to real-world environments, yet it inevitably suffers from catastrophic forgetting, particularly the performance degradation of previous tasks and LLMs' general-purpose knowledge. Although existing methods, such as orthogonal gradient projection, mitigate the forgetting across various fine-tuning tasks, they fundamentally fail to preserve pre-training LLMs' inherent general-purpose knowledge because the original data and gradients of off-the-shelf pre-training LLMs required by these methods are strictly unknown and highly diverse. To bridge this critical gap, we propose EoupCT, a novel framework designed to Estimate and Orthogonalize Unknown Pre-training gradients for Continual LLM fine-Tuning. Specifically, EoupCT estimates pre-training gradients by dynamically generating pseudo data that is most susceptible to forgetting for new tasks through a learnable soft prompt equipped with Gumbel-Softmax relaxation. Furthermore, we formulate a multi-objective optimization problem and introduce a first-order efficient Pareto optimizer that jointly optimizes LLM parameters and the soft prompt, rigorously enforcing orthogonality between new task updates and the estimated pre-training gradients. Extensive experiments across multiple LLMs demonstrate that EoupCT effectively preserves both task-specific proficiency and inherent general-purpose knowledge, successfully mitigating the catastrophic forgetting.

cs.CL↗
arXiv2026

Ytterbium lattice clock with systematic uncertainty of $1.3\times 10^{-18}$ and instability at the $10^{-19}$ level

We report an optical lattice clock based on $^{171}$Yb atoms with a total systematic uncertainty of $1.3\times 10^{-18}$. An in-vacuum buildup cavity was employed to enhance the lattice light power. Differential frequency measurement between two identical clocks facilitates the evaluation of systematic shifts. Synchronous comparison of the two clocks reached a stability level of $2.7\times 10^{-19}$ in an averaging time of 216,000~s. The blackbody radiation (BBR) shield which is placed in vacuum provides a well-characterized BBR environment, enabling an uncertainty contribution of $8.7\times 10^{-19}$ from the BBR Stark shift. Lattice light shifts were measured at different lattice depths $U$, and fitted with a fourth-order polynomial of $U$. The zero-linear-shift frequency $ν_{\mathrm{zero}}$ was determined to be 394 798 260.6(3) MHz. The lattice light shift can be controlled at an uncertainty level of $6.3\times 10^{-19}$ under typical operating conditions. Other systematic shifts have also been evaluated. The two clocks will be used for remote frequency comparisons between Shanghai and Wuhan.

physics.atom-ph↗