Searcharxiv⌕ Search

arXiv subjects

Wei Gao

Publications and source records attributed to Wei Gao.

At least 37 records · Page 2Linked to original sources
arXiv2026

VLBiMan++: Expanding the Generalization Boundary of Vision-Language Anchored One-Shot Bimanual Manipulation

Generalizable bimanual robotic manipulation requires a reusable task prior that can persist across increasingly diverse tasks, objects, scenes, embodiments, and execution conditions, thus avoiding the prohibitive cost of large-scale teleoperated demonstrations and policy retraining. In this work, we present VLBiMan++, an extended framework that expands the generalization boundary of vision-language anchored one-shot bimanual manipulation. Starting from a single human demonstration, VLBiMan++ performs task-aware decomposition to identify reusable and adaptable skill components, and employs vision-language grounded geometric adaptation to transfer these skills to novel configurations without retraining. Building on this foundation, we systematically extend generalization along five dimensions: task generalization through diverse and long-horizon skill compositions; object generalization across unseen categories, varying geometries, and more complex articulated or deformable objects; scene generalization under clutter, occlusion, and dynamic interference; embodiment generalization across heterogeneous dual-arm robotic platforms; and deployment generalization through prolonged closed-loop execution under repeated external perturbations. To support this broader scope, we further introduce object-state-aware adaptation and lightweight trajectory optimization mechanisms that accommodate changes beyond simple rigid 6-DoF pose variations while preserving reliable bimanual coordination. Extensive real-world experiments demonstrate that VLBiMan++ maintains strong task success and adaptation capability across these increasingly challenging settings. Overall, VLBiMan++ advances one-shot bimanual manipulation from demonstrating isolated transferability toward a more systematic and scalable framework for generalization across tasks, objects, scenes, embodiments, and long-term deployment conditions.

cs.RO↗
arXiv2026

Spatial sparse sampling-based iterative optimization framework for GNSS Direct Position Estimation

Direct position estimation (DPE), a promising technique in Global Navigation Satellite Systems (GNSS) receivers, enables estimation of position, velocity, and time (PVT) solutions directly from correlator outputs. The conventional grid search (GS)-based DPE is computationally intensive, as it relies solely on locating the peak of the cross ambiguity function (CAF), and it does not fully leverage the PVT information present in the correlation values. This paper proposes an iterative optimization DPE framework that capitalizes on spatial coherence and spatial gradient via spatial sparse sampling (SS). In SS-DPE framework, the correlation outputs of spatial sampled PVT points all serve as measurements, where the spatial gradient and spatial coherence are derived to capture the information density and diversity of different correlation values. The analytical Cramér-Rao Bound (CRB) is derived and indicates that both spatial coherence and gradient determine the theoretical performance limit via the noise covariance and Jacobian matrices analysis. The proposed theoretical framework not only validates the feasibility of sparse sampling but also guides weight optimization to distinct correlation values, effectively integrating these insights with a general gradient-based optimization. Theoretical derivations are validated via Monte Carlo simulations. Field experiments further demonstrate the practical feasibility of the proposed SS-DPE optimization framework. Comparative analysis shows that the proposed SS-DPE achieves comparable PVT estimation accuracy to the conventional GS-DPE while consumes only sparsely sampled correlation values, improving the information utilization efficiency and reducing the computation load.

eess.SP↗
arXiv2026

Efficient LOS-Sampled GNSS Direct Position Estimation: An Information-Loss CRB Analysis

Conventional Global Navigation Satellite System (GNSS) Direct Position Estimation (DPE) exploits raw intermediate-frequency (IF) data and provides a full-information Cramér-Rao Bound (CRB) benchmark, but its accumulated-correlation objective requires dense evaluations over a common Position, Velocity, and Time (PVT) search space. This paper proposes an efficient Line-of-Sight (LOS)-sampled DPE, where each satellite channel independently retains only PVT sample points aligned with its LOS direction. A residual-minimization estimator is formulated to resolve the mismatch between accumulated-correlation metrics and per-satellite LOS sampling. The Fisher information matrix (FIM) and information-loss CRB of LOS-sampled DPE are derived, quantifying the information loss determined by LOS sampling parameters. Theoretical analysis, Monte Carlo simulations, and real experiments show that proper LOS sampling approaches the full-information CRB and practical performance of conventional DPE, while reducing the number of correlation evaluations from exponential to linear growth.

eess.SP↗
arXiv2026

OctoPipe: Reducing Pipeline Bubbles for Heterogeneous Models via Co-Optimizing Partitioning, Placement, and Scheduling

Pipeline parallelism is widely used to train large language models (LLMs). However, increasing heterogeneity in model architectures exacerbates pipeline bubbles, thereby reducing training efficiency. Prior approaches typically optimize a single phase of the pipeline schedule (i.e., partitioning, placement, or scheduling), leaving substantial pipeline bubbles. While promising, co-optimization poses three key challenges: (1) complex performance modeling, (2) a combinatorial search space, and (3) irregular execution orders. To address these challenges, we propose OctoPipe, a pipeline parallelism system to jointly optimize partitioning, placement, and scheduling. First, we build a graph-based pipeline simulator to model heterogeneous pipeline execution for co-optimization. Second, on top of the simulator, we develop an iterative bubble-aware tuner to efficiently explore the combinatorial search space. Third, we implement a unified pipeline executor that dynamically orchestrates computation and communication to support irregular execution orders without deadlocks while maximizing communication-computation overlap. Experiments show that OctoPipe achieves 1.09--1.49$\times$ throughput improvement over the state-of-the-art pipeline parallelism approaches across various heterogeneous model configurations and GPU cluster scales.

cs.DC↗
arXiv2026

ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation

Value signals are aggregated user-level moral representations that capture users' inferred value-related tendencies from their online discourse. User behavior on social media is shaped not only by what users say or whom they interact with, but also by the value signal through which they express attitudes. Existing user representation methods largely miss this value-relevant dimension. We propose ValueGraph, a graph pre-training framework that uses automatically inferred moral-value signals as noisy auxiliary signals for contextualized user representation. From post-reply graphs, ValueGraph learns semantic and structural representations and further aligns users through relative value similarity with contrastive and clustering objectives. Rather than treating inferred values as gold psychological labels, ValueGraph uses them as soft constraints for representation learning. Experiments on stance detection and twitter bot detection show consistent gains over strong text-based, graph-based, and text-only LLM baselines, highlighting value-signal guidance as a useful inductive bias for socially informed user modeling.

cs.CL↗
arXiv2026

MIMONet: Multi-scale Input and Multi-scale Output Network for Salient Object Detection

The existing methods for saliency detection task focus on the application of multi-level features, aiming to take advantage of the respective strengths of high- and low-level features. However, because the inputs of these models are single-size images, their multi-level features have difficulty in learning the knowledge of size variations of salient objects. Object-scale variation learning has great potential for detecting multi-scale objects, which has not been fully explored by existing methods. To improve the recognition ability of a model for objects with different sizes, we are inspired by the image pyramid to propose a Multi-scale Input and Multi-scale Output Network (MIMONet). In MIMONet, we extract multi-level features for three images with different resolutions to form three encoder branches, and information will be exchanged between the branches. The advantage of this approach is that the features of one branch can learn the knowledge of target size variation from the features of the other two branches. In addition, we design a Multi-scale Perception (MSP) module, in which the input feature layer is divided into several sub-layers with different resolutions. Capturing the multi-level structure information of the objects in these sub-layers can make the objects more fully perceived. For network training, we propose a Joint Saliency Loss (JSL), which can constrain multiple saliency maps output by the network to identify the same foreground objects, and induce their boundaries to be preserved clearly. Experimental results show that MIMONet has stronger detection capabilities and harvests better evaluation scores on multiple datasets compared to existing models. The code of our model will be released.

cs.CV↗
arXiv2026

Predicting Consequences and Reinforcing Navigation Policies with Latent World Models

World models enable agents to reason about future outcomes and learn policies from their knowledge of state transition, but existing approaches primarily focus on reconstructing future observations or features, which introduces unnecessary complexity and limits their effectiveness for decision making. In this work, we propose a compatibility prediction Latent World Model (LWM) for robot navigation that predicts action-conditioned latent feature compatibility rather than reconstructing observations. Our key insight is that spatial proximity correlates with latent feature similarity, enabling action consequences to be evaluated directly in latent space. To support counterfactual training, our model leverages action sequences sampled across trajectories and learns to predict which sequences lead closer to the goal. Furthermore, we demonstrate how the learned world model can supervise policy learning from unlabeled video data and further improve policies through reinforcement learning entirely within the world model. This imagination-driven framework eliminates the need for action annotations and additional environment interaction. Extensive experiments on multiple real-world robot navigation datasets show that our approach significantly outperforms prior world model and imitation learning methods in prediction accuracy, policy learning, and real-world navigation performance. The code, pretrained models, and additional materials are available at https://wzm206.github.io/latent-world-model-nav.

cs.AI↗
arXiv2026

Cyclops: LiDAR as a Camera That Dreams in Color

Conventionally, robotic perception relies heavily on cameras due to the rich semantic texture they provide. However, their performance degrades significantly in low-light or high-dynamic-range environments. Conversely, while Light Detection and Ranging (LiDAR) captures illumination-invariant geometric and intensity properties, the resulting data are typically single-channel and sparse, creating a significant modality gap when applying vision models pre-trained on RGB datasets. In this paper, we propose Cyclops, a framework that translates sparse Non-Repetitive Scanning LiDAR (NRS-LiDAR) intensity into RGB video, enabling camera-free inference for all-day perception tasks. Our approach first converts sparse LiDAR intensity projections into dense representations via a frozen pre-trained densification module, serving as a geometrically rich source condition. The dense intensity latent is then transported toward the target RGB distribution through Latent Bridge Matching (LBM) with a learned velocity field in a few ODE integration steps. To mitigate inter-frame flickering, we inject prior-frame context via temporal attention layers and further formulate the velocity field as a policy optimized by a differentiable terminal reward that encourages terminal fidelity through backpropagation along the ODE trajectory. Extensive experiments demonstrate that the synthesized RGB, including those generated under near-dark conditions, enable standard RGB-based perception models to substantially outperform both LiDAR baselines and conventional cameras on semantic segmentation, lane detection, and point cloud colorization across diverse lighting conditions.

cs.RO↗
arXiv2026

ParaJSCC: A Parameterized Framework for Reusable Multimodal Joint Source-Channel Coding

Multimodal signals, such as visual, audio, and tactile data, are increasingly maintained as persistent digital assets in immersive communication systems and digital twins. In these settings, the same multimodal content is repeatedly accessed by heterogeneous receivers with varying modality and bandwidth requirements. Existing compression and Joint Source-Channel Coding (JSCC) methods typically follow a per-request encoding paradigm, resulting in redundant computation and low efficiency during repeated access. To address this issue, we propose ParaJSCC, a multimodal JSCC framework designed for reusable representation serving. ParaJSCC converts each multimodal sample offline at the cloud/content server into a compact, quantized parameter package, which is then stored at the edge serving node for low-latency access. During serving, only the subset required by the current request is transmitted over the wireless channel, followed by lightweight decoding at the receiver. The framework employs a progressive shared-private parameterization to support modality-selective transmission and scalable reconstruction under varying bandwidth constraints. Experiments on multimodal datasets show that ParaJSCC significantly reduces online latency (e.g., from 17.18~ms to 4.34~ms for image-only requests and from 43.96~ms to 11.21~ms for full multimodal requests) and transmission rate (by 47.8\%--51.2\% for selective requests), while maintaining strong reconstruction quality under noisy channels.

eess.SP↗
arXiv2026

CoDS: Robust Collaborative Perception via Expert-driven Detection and BEV Segmentation

Collaborative perception breaks through single-view limitations via multi-agent information exchange. However, multi-source noise such as pose errors and communication delays degrades fusion feature quality, constraining perception performance. Joint training of detection and BEV segmentation provides a natural remedy, where segmented road regions help constrain target distributions and detection bounding boxes help recover ambiguous segmentation boundaries. To this end, we propose a robust Collaborative perception framework with expert-driven Detection and bev Segmentation (CoDS). To address spatial inconsistency in fusion quality, we first introduce the Collaborative Reliability Map (CoRM) to explicitly quantify feature quality distribution. Based on CoRM, we design the Semantic Mixture-of-Experts (S-MoE) module to extract differentiated features for inconsistent feature demands. Finally, to further mitigate feature noise degradation, the Bidirectional Task Complementary Interaction (BTCI) refines task-aware features through bidirectional injection. Extensive experiments on OPV2V and V2V4Real datasets show that our CoDS surpasses existing baselines on both tasks and maintains stable robustness under multi-source noise. Code: https://github.com/JinlongW128/CoDS and https://openi.pcl.ac.cn/OpenAIDriving/CoDS.

cs.CV↗
arXiv2026

Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training

Vision-language models (VLMs) enable embodied agents to reason and act from visual observations and language instructions. Reinforcement learning (RL) post-training enhances these capabilities using task feedback, but current on-policy RL runtimes execute rollout, reference scoring, and actor training in strict serial phases. While effective for text-only RL, this phase-granular execution is wasteful for VLMs, where processing dense video inputs and prompt prefixes occupies a large fraction of each phase. Because prefix processing is independent of the generated response, it can be run alongside rollout decoding, which leaves GPU compute capacity underutilized, without breaking synchronous on-policy semantics. We present Rollplex, a runtime that decomposes the reference and training phase and moves the prefix computation into the rollout decode window. Realizing this schedule requires more than concurrent kernel launches: naive colocation of Qwen2.5-VL-32\,B requires roughly 165\,GiB per GPU, while rollout and training prefer different tensor-parallel (TP) degrees and weight layouts. Rollplex addresses these constraints with two mechanisms. Phase-aware memory management controls HBM residency according to producer--consumer lifetimes. Parallelism-aware weight sharing uses the same physical storage for layout-compatible tensors across distinct TP degrees and reconstructs only incompatible tensors, avoiding a complete second actor copy. On 32 H800 GPUs, Rollplex achieves $1.23\times$--$1.30\times$ speedup over serial colocation and $1.57\times$--$2.24\times$ over disaggregation under the same GPU budget, while preserving the synchronous RL update.

cs.LG↗
arXiv2026

CausalSplat: Towards Comprehensive Hierarchical Reasoning in 3D Gaussian Splatting

While 3D Gaussian Splatting (3DGS) has advanced open vocabulary scene understanding, existing methods remain confined to explicit queries. They struggle to interpret implicit intents, complex spatial constraints, and commonsense reasoning required for practical embodied interactions. To address this gap, we introduce the task of reasoning 3D Gaussian segmentation and construct two benchmarks, Causal-LERF and Causal-ScanNet. These benchmarks systematically evaluate commonsense, spatial, affordance, and counterfactual reasoning. Evaluations reveal that current state of the art methods perform poorly on these reasoning challenges. Therefore, we propose CausalSplat, a framework that integrates vision-language models with 3D scene graphs to disentangle explicit structural perception from implicit logical inference. Extensive experiments demonstrate that CausalSplat achieves state of the art performance on our reasoning benchmarks while showing strong generalizability on standard referring and open vocabulary 3D segmentation tasks. Project Page: https://jiayuding031020.github.io/CausalSplat

cs.CV↗
arXiv2026

Visual Geometry Foundation-Aware Gaussians for Single-Frame Surround-View Driving Reconstruction

Single-frame surround-view reconstruction faces severe geometric instability and rendering artifacts due to minimal inter-camera overlap. While existing methods rely on complex decoders or auxiliary cues, they remain bottlenecked by the weak geometric capacity of upstream features. We argue that leveraging pretrained visual geometry priors strengthens upstream representations and alleviates the geometric ambiguity in sparse surround views. To this end, we propose VGGD, a visual geometry foundation-aware 3D Gaussian Splatting framework for feed-forward surround-view driving reconstruction, which shifts geometric modeling to the frontend and adapts foundation priors to the driving camera setting. First, VGGD leverages VGGT to provide transferable multi-view geometric prior tokens. Next, we introduce a Dual-Path Neck to decouple geometry-consistent and appearance-aware representations, improving appearance completion in weakly observed regions. We further apply Scale Warmup to stabilize early geometry learning and suppress scale drift under ego-pose changes. Finally, we use a hybrid pixel--volume Gaussian decoder to produce a renderable 3D Gaussian scene for novel-view synthesis. Experiments on the nuScenes single-frame benchmark show that VGGD achieves the best overall rendering quality among the compared methods and improves relative geometric consistency.

cs.CV↗
arXiv2026

DRL-Based Secure Transmission for Rotatable Antenna-Enabled Low-Altitude ISAC Systems

The development of the low-altitude economy has driven innovation in intelligent antenna systems within ISAC systems. In this paper, we investigate a Rotatable Antenna (RA)-enabled low-altitude integrated sensing and communication (ISAC) system. In practical terms, the RA array can flexibly adjust the three-dimensional (3D) beam direction of each antenna to enhance array directional gain, thereby improving the communication security of legitimate mobile users against potential eavesdropping risks from the unmanned aerial vehicle (UAV). Our objective is to maximize the minimum secrecy rate (SR) by jointly optimizing transmit beamforming matrix, transmit and receive RAs' pointing matrices. To this end, an multi-agent proximal policy optimization with three improvement mechanisms (MAPPO-T) algorithm is proposed to cope with the issue of complex multi-agent collaborative decision-making problem. Simulation results show that the introduction of RAs can effectively improve SR performance compared to the traditional fixed orientation antenna (FOA)-based system. In addition, the proposed MAPPO-T algorithm validate the superiority compared to the standard MAPPO algorithm.

eess.SP↗
arXiv2026

Learning When to Trust via Selective Context Preference Optimization

Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong. The obvious remedy, training models to resist such signals, hides a failure mode: a model that ignores all context looks robust yet is useless when the context is worth trusting. We recast the problem as selective trust and introduce MIST, a human-annotated benchmark that renders each reasoning item under four matched conditions (clean, misleading, correct-context, and irrelevant-context), together with SC2W, a paired metric counting how often a misleading signal flips a clean-correct answer to wrong. Across a comprehensive benchmark study, we observe that such a susceptibility is universal. We then propose SCOPE, which mines clean-correct/misleading-wrong failures and optimizes a standard Direct Preference Optimization (DPO) objective over matched preference pairs balanced equally across all four conditions, rather than over misleading items alone. Our approach substantially reduces SC2W on popular open-sourced models while preserving accuracy when the added context is clean, correct, or irrelevant. With this work, we argue that models should be judged on selective trust, not on resistance alone.

cs.CL↗
arXiv2026

SpatialQ: Understanding 3D Gaussian Splatting Scene Quality via Visual-based MLLM

3D Gaussian Splatting (3DGS) has emerged as an effective representation for novel view synthesis and 3D scene reconstruction, creating an increasing demand for reliable quality assessment. Unlike conventional image quality assessment (IQA), the quality of a 3DGS scene depends not only on the perceptual fidelity of rendered views, but also on scene-level factors such as spatial structure and cross-view consistency. Existing IQA methods are limited by their reliance on 2D perceptual cues, whereas general multimodal large language models (MLLMs) are not designed for stable quality regression and may produce unreliable judgments. To address these limitations, a multimodal quality assessment framework is developed for 3DGS scene understanding. First, a 3D-aware quality representation learning framework is introduced by augmenting a VGGT-based encoder with a dedicated quality head. Multi-view images are encoded into view-specific features and aggregated to capture cross-view consistency, while geometric cues are incorporated through joint modeling of depth and point-cloud-related structural information, enabling the learning of structure-aware quality representations beyond appearance-driven features. Second, a grounded multimodal reasoning mechanism is constructed by jointly feeding original images, depth maps, point cloud renderings, and camera parameters into a Qwen-based MLLM.

cs.CV↗
arXiv2026

Wave2Body: Rethinking mmWave Human Pose Estimation as Radar-to-Body Token Translation

Millimeter-wave (mmWave) radar enables privacy-friendly human sensing, but its sparse point clouds are physical measurements of view-dependent electromagnetic reflections and only indirectly characterize body articulation. Recovering a complete 3D pose from such partial, geometry-dependent observations is therefore under-constrained. Existing methods directly regress joint coordinates from paired radar-pose data, relying on the same limited paired supervision to learn radar perception, human-body structure, and their alignment. This coupling can encourage dataset-specific shortcuts under ambiguous radar observations. We propose Wave2Body, a radar-to-body token translation framework that decouples these learning targets using a self-supervised mmWave tokenizer, a pretrained compositional body tokenizer that defines the output space, and a lightweight translator between them. Experiments on M4Human and mmBody show that Wave2Body achieves stronger cross-domain generalization than previous methods while incurring much lower computational costs for training and inference. All the code and experiment results are publicly available at https://github.com/Galaxywalk/Wave2Body.

cs.CV↗
arXiv2026

AI for Auto-Research: Roadmap & User Guide

AI-assisted research is crossing a threshold: fully automated systems can now generate research papers for as little as $15, while long-horizon agents can execute experiments, draft manuscripts, and simulate critique with minimal human input. Yet this productivity frontier exposes a deeper integrity problem: under scientific pressure, even frontier LLMs still fabricate results, miss hidden errors, and fail to judge novelty reliably. Studying developments through April 2026, we present an end-to-end analysis of AI across the complete research lifecycle, organized into four epistemological phases: Creation (idea generation, literature review, coding & experiments, tables & figures), Writing (paper writing), Validation (peer review, rebuttal & revision), and Dissemination (posters, slides, videos, social media, project pages, and interactive agents). We identify a sharp, stage-dependent boundary between reliable assistance and unreliable autonomy: AI excels at structured, retrieval-grounded, and tool-mediated tasks, but remains fragile for genuinely novel ideas, research-level experiments, and scientific judgment. Generated ideas often degrade after implementation, research code lags far behind pattern-matching benchmarks, and end-to-end autonomous systems have not yet consistently reached major-venue acceptance standards. We further show that greater automation can obscure rather than eliminate failure modes, making human-governed collaboration the most credible deployment paradigm. Finally, we provide a structured taxonomy, benchmark suite, and tool inventory, cross-stage design principles, and a practitioner-oriented playbook, with resources maintained at our project page.

cs.AI↗