Searcharxiv⌕ Search

arXiv subjects

Chen Gao

Publications and source records attributed to Chen Gao.

At least 55 records · Page 3Linked to original sources
arXiv2026

Dreaming when Necessary: Advancing World Action Models with Adaptive Multi-Modal Reasoning

World Action Models (WAMs) offer a promising approach to embodied intelligence, yet existing methods rely heavily on video prediction as action priors and lack adaptive multimodal reasoning, limiting their effectiveness on long-horizon, complex tasks. We observe that WAMs require different multimodal reasoning modes under different execution contexts: textual reasoning is essential during task transitions to guide high-level action prediction, while visual reasoning is critical during fine-grained manipulation for precise control. Motivated by this observation, we propose \textbf{AdaWAM}, a world action model with adaptive multimodal reasoning abilities. AdaWAM integrates a lightweight dynamic router that autonomously triggers textual or visual reasoning as needed during task execution. Experiments on both simulated and real-world embodied tasks show that AdaWAM substantially improves inference efficiency while outperforming state-of-the-art embodied policies. Codes and demos are available at: https://adawam.github.io/.

cs.RO↗
arXiv2026

WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigation

End-to-end Vision-Language-Action (VLA) models have shown promise in UAV navigation. However, existing approaches typically rely on historical observations to directly predict actions, often struggling in dense urban environments where severe occlusions and sharp turns result in drastic viewpoint transitions. We argue that the ability to "imagine" future states -- inherent in World Models -- is critical for robust decision-making under such partial observability. To address this, we construct a challenging Urban Canyon Traversal Benchmark, specifically designed to evaluate spatial understanding in scenarios characterized by severe occlusions and drastic viewpoint transitions. To this end, we propose WorldFly, a novel world-model-based VLA framework that employs a dual-branch coupled flow matching mechanism to jointly generate future video predictions and navigation actions, thereby explicitly guiding the agent's policy via spatial imagination. Extensive evaluations on our benchmark demonstrate that WorldFly outperforms other baselines, particularly in unseen environments, validating the effectiveness of integrating world models into embodied aerial agents.

cs.AI↗
arXiv2026

Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation

Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens. To accelerate inference, the KV cache is used to avoid redundant recomputation across generation steps. Nevertheless, its growth with generation length introduces increasing memory and error accumulation, limiting the scalability of AR models to even longer sequences. Existing KV cache compression methods mitigate this issue by selectively retaining only video tokens deemed important. However, most existing methods assess token importance using short-horizon signals derived from the current or historical generation context, making these methods prone to overlooking tokens that appear unimportant at early steps but later become critical for future frames. In this work, we identify an important property of trained AR video models: although RoPE-modulated queries evolve across autoregressive steps, the underlying canonical pre-RoPE query distribution remains remarkably stable throughout the video generation process. This approximate stationarity implies that future query distributions are estimable from historical statistics, enabling principled future-aware cache decisions without any additional training. Building on this insight, we propose Future Forcing, a training-free future-aware KV cache policy for AR video generation. Specifically, Future Forcing first constructs a future query proxy from historical statistics, then scores KV cache tokens by their importance under this proxy, and finally merges redundant token pairs within the affine subspace induced by the future query. Extensive experiments show that Future Forcing improves long-horizon consistency under limited KV caches, achieving up to 1.49 improvement in subject consistency on VBench-Long for 60s generation over existing AR video KV cache policies.

cs.CV↗
arXiv2026

The Point, the Vision and the Text: Does Point Cloud Boost Spatial Reasoning of Large Language Models? A Bias-Controlled Study

3D Large Language Models (LLMs) leveraging spatial information in point clouds for 3D spatial reasoning attract great attention. Despite some promising results, the advantages of point clouds over other modalities remain unclear. Moreover, existing 3D benchmarks are insufficient for fairly evaluating the ability of multimodal LLMs to comprehend spatial concepts. To address these challenges, we introduce ScanReQA, a 3D spatial reasoning benchmark encompassing text, vision, and point cloud modalities. We then evaluate the performance of text, 2D, and 3D LLMs on the benchmark to compare the effectiveness of different modalities in understanding spatial concepts. Furthermore, we analyze the reasoning mechanisms behind 3D LLMs using point clouds. Our findings reveal that: 1) binary spatial reasoning remains challenging for current 3D LLMs, 2) MLLMs based on point cloud and visual modalities demonstrate stronger spatial reasoning capabilities than LLMs, and 3) 3D LLMs exhibit the attention sink phenomenon similar to that in 2D LLMs, impairing spatial reasoning. We think these conclusions can help the next step of 3D LLMs and also offer insights for foundation models in other modalities. We release datasets and codes in the project page: https://github.com/EmbodiedCity/ScanReQA.code.

cs.CV↗
arXiv2026

GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation

We introduce GE-Sim 2.0 (Genie Envisioner World Simulator 2.0), a closed-loop video world simulator for robotic manipulation. Building on the action-conditioned video generation framework of Genie Envisioner, GE-Sim 2.0 is re-trained on thousands of hours of real-world robot data spanning teleoperation, contact-rich interaction, and on-robot policy deployment, substantially improving action-following fidelity and trajectory coverage. On top of this foundation, three new modules close the loop from video simulation to policy learning: a state expert that decodes proprioceptive state from video latents to support next-chunk prediction by downstream VLA policies; a world judge that scores generated rollouts against task instructions, yielding machine-verifiable success signals and rewards in place of manual inspection; and an acceleration framework that delivers a 25-frame rollout in 2.3 seconds on a single H100, with up to 4* frame skipping at inference for long-horizon evaluation. GE-Sim 2.0 tops the public WorldArena leaderboard at only 2B parameters, outperforming both dedicated robotic world models and closed-source general video generators, and policies trained against its rollouts and rewards translate into measurable real-world gains, establishing GE-Sim 2.0 as a practical platform for scalable evaluation and closed-loop learning of manipulation policies.

cs.RO↗
arXiv2026

EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning

First-person dynamic spatial reasoning requires models to track continuous motion and precise geometric structure, but the quadratic attention cost of Transformer-based Video-LLMs makes dense visual tokens computationally expensive. Existing token pruning paradigms predominantly rely on discrete static snapshots, failing to preserve the motion and geometric cues essential for reasoning. We propose Event Cascade Pruning (ECP), to our knowledge the first training-free framework that leverages the high-frequency motion cues from event cameras as a continuous event-guided motion prior to guide token selection. ECP combines three stages: Event-Triggered Causal Sampling to anchor motion-informative keyframes, Event-guided Motion Saliency Filtering to suppress event-inactive visual tokens, and Event-Attention Ranking Fusion to calibrate spatial attention with motion-salient dynamics. With 80% visual token reduction, ECP outperforms the full-token baseline (37.62% vs. 36.31%) while achieving 1.89x inference speedup and 52% GFLOPs reduction. We further introduce ESR-Real, the first real-world RGB-event benchmark for first-person spatial reasoning, where ECP improves accuracy by 2.68 percentage points over full-token baselines.

cs.CV↗
arXiv2026

WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform

World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about environmental dynamics. However, existing embodied world model benchmarks are still largely confined to vision-only prediction, offline embodied applications, and simulator-based evaluation, making them insufficient for assessing increasingly comprehensive world models. In this work, we introduce WorldArena 2.0, an expanded benchmark that systematically broadens embodied world model evaluation along three dimensions: modality, functionality, and platform. Along the modality dimension, WorldArena 2.0 extends evaluation from vision-only to visuotactile modalities, enabling assessment of multimodal perception and prediction. Along the functionality dimension, it extends beyond policy evaluation and planning to assess world models as interactive RL environments for policy optimization. Along the platform dimension, it moves beyond simulator-only evaluation to a diverse suite of simulated and real-world robotic settings across multiple embodiments. Under a standardized protocol, WorldArena 2.0 comprehensively evaluates perceptual quality, interactive utility, and cross-platform performance, providing a comprehensive testbed for tracking progress toward embodied world models. The benchmark is available at: https://world-arena.ai.

cs.RO↗
arXiv2026

ManiSoft: Towards Vision-Language Manipulation for Soft Continuum Robotics

Most existing vision-language manipulation research targets rigid robotic arms, whose fixed morphology limits adaptability in cluttered or confined spaces. Soft robotic arms offer an appealing alternative due to their deformability, but confront challenges such as unreliable proprioception and distributed low-level actuation. To investigate these challenges, we introduce \ManiSoft, a benchmark for vision-language manipulation with soft arms. ManiSoft features a tailored simulator that couples realistic soft-body dynamics with contact-rich interactions via an elastic force constraint. On this basis, ManiSoft defines four tasks, each highlighting distinct aspects of deformable control, from basic end-effector coordination to obstacle avoidance. To support policy training and evaluation, \ManiSoft{} includes an automated pipeline that generates $6{,}300$ diverse scenes and corresponding expert trajectories. To produce high-quality trajectories at scale, we first employ a high-level planner to decompose each task into a sequence of waypoints, followed by a low-level reinforcement learning policy that generates torque commands to track waypoints. Benchmarking three representative policy models shows relatively promising results in clean scenes but substantial performance drop under randomization. Visualization analysis indicates that failures stem primarily from inaccurate visual estimation of proprioceptive state and limited exploitation of deformability for adaptive obstacle avoiding. We anticipate ManiSoft to serve as a valuable testbed, bridging the gap between rigid and soft arms in the context of vision-language manipulation. Out codes and datasets are released at https://buaa-colalab.github.io/ManiSoft.

cs.RO↗
arXiv2026

WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation

Aerial vision-language navigation (VLN) requires agents to follow natural-language instructions through closed-loop perception and action in 3D environments. We argue that aerial VLN can be formulated as a prediction-driven world-action problem: the agent should anticipate latent world evolution and act according to the predicted consequences. To this end, we propose WorldVLN, the first autoregressive world action model for aerial VLN. Unlike full-sequence video-generation world models that generate an entire visual clip, WorldVLN adapts a latent autoregressive video backbone to predict short-horizon world-state transitions and directly decodes them into executable waypoint actions. After each action segment is executed, newly received observations are encoded back into the autoregressive context, enabling closed-loop world-action prediction. We further introduce a two-stage training framework that first grounds the video prior in instruction-conditioned navigation dynamics and then develops Action-aware GRPO, the first reinforcement learning method tailored to autoregressive WAMs, to optimize waypoint decisions through their downstream rollout consequences. On public outdoor and indoor benchmarks, WorldVLN consistently outperforms existing Vision-Language-Action baselines with 12\%+ success-rate gains and larger advantages on challenging cases. It further transfers zero-shot to real drone deployment, suggesting that the proposed WorldVLN offers a promising route for spatial action tasks. Demos and code are available at https://embodiedcity.github.io/WorldVLN/.

cs.RO↗
arXiv2026

UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs

Multimodal large language models are increasingly expected to perform thinking with images, yet existing visual latent reasoning methods still rely on explicit textual chain-of-thought interleaved with visual latent tokens. This interleaved design limits efficiency and keeps reasoning fragmented across separate text and vision channels. We propose UniVLR, a unified visual latent reasoning framework that treats textual reasoning and auxiliary visual evidence as a shared visual workspace. Instead of preserving text CoT as an independent inference-time path, UniVLR renders reasoning traces together with auxiliary images and learns to compress this unified representation into compact visual latent tokens. At inference time, the model reasons only through visual latents and directly decodes the final answer, avoiding both external tool calls and verbose text reasoning. Experiments on real-world perception and visual reasoning tasks show that UniVLR outperforms prior visual latent reasoning methods while using substantially fewer generated reasoning tokens, suggesting a more unified and efficient paradigm for visual thinking in MLLMs.

cs.CV↗
arXiv2026

Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering

Diffusion Transformers (DiTs) achieve strong video generation quality but suffer from high inference cost due to dense 3D attention, motivating sparse attention techniques for improving efficiency. However, existing training-free sparse attention methods for video generation still face two unresolved limitations: ignoring layer heterogeneity in attention pruning and ignoring query-key coupling in block partitioning, which hinder a better quality-speedup trade-off. In this work, we uncover a critical insight: attention sparsity is an intrinsic layer-wise property, with only minor variation across different inputs. Motivated by this observation, we propose SVOO, a training-free sparse attention framework for fast video generation via offline layer-wise sparsity profiling and online bidirectional co-clustering. Specifically, SVOO adopts a two-stage paradigm: (i) offline layer-wise sensitivity profiling to derive intrinsic per-layer pruning levels, and (ii) online block-wise sparse attention via a bidirectional co-clustering algorithm. Extensive experiments on seven widely used video generation models demonstrate that SVOO achieves a superior quality-speedup trade-off over state-of-the-art methods, delivering up to 1.93x speedup while maintaining a PSNR of up to 29 dB on Wan2.1. Code is available at: https://github.com/Mutual-Luo/SVOO.

cs.CV↗
arXiv2026

Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation

While Vision-Language-Action (VLA) models offer broad general capabilities, deploying them on specific hardware requires real-world adaptation to bridge the embodiment gap. Since robot demonstrations are costly, this adaptation must often occur under a strict data budget. In this work, we identify a critical diversity trap: the standard heuristic of "maximizing coverage" by collecting diverse, single-shot demonstrations can be self-defeating due to non-vanishing estimation noise. We formalize this phenomenon as a Coverage--Density Trade-off. By decomposing the policy error into estimation (density) and extrapolation (coverage) terms, we characterize an interior optimal allocation of unique conditions for a fixed budget. Guided by this analysis, we propose Anchor-Centric Adaptation (ACA), a two-stage framework that first stabilizes a policy skeleton through repeated demonstrations at core anchors, then selectively expands coverage to high-risk boundaries via teacher-forced error mining and constrained residual updates. Real-robot experiments validate our trade-off framework and demonstrate that ACA significantly improves task reliability and success rates over standard diverse sampling strategies under the same budget.

cs.RO↗
arXiv2026

iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework

Achieving Artificial General Intelligence (AGI) requires agents that learn and interact adaptively, with interactive world models providing scalable environments for perception, reasoning, and action. Yet current research still lacks large-scale datasets and unified benchmarks to evaluate their physical interaction capabilities. To address this, we propose iWorld-Bench, a comprehensive benchmark for training and testing world models on interaction-related abilities such as distance perception and memory. We construct a diverse dataset with 330k video clips and select 2.1k high-quality samples covering varied perspectives, weather, and scenes. As existing world models differ in interaction modalities, we introduce an Action Generation Framework to unify evaluation and design six task types, generating 4.9k test samples. These tasks jointly assess model performance across visual generation, trajectory following, and memory. Evaluating 14 representative world models, we identify key limitations and provide insights for future research. The iWorld-Bench model leaderboard is publicly available at iWorld-Bench.com.

cs.CV↗
arXiv2026

LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)

This paper reports on the LoViF 2026 PhyScore challenge, a competition on holistic quality assessment of world-model-generated videos across both 2D and 4D generation settings. The challenge is motivated by a central gap in current evaluation practice: perceptual quality alone is insufficient to judge whether generated dynamics are physically plausible, temporally coherent, and consistent with input conditions. Participants are required to build a metric that jointly predicts four dimensions, i.e., Video Quality, Physical Realism, Condition-Video Alignment, and Temporal Consistency. Depart from that, participants also need to localize physical anomaly timestamps for fine-grained diagnosis. The benchmark dataset contains 1,554 videos generated by seven representative world generative models, organized into three tracks (text-2D, image-to-4D, and video-to-4D) and spanning 26 categories. These categories explicitly cover physics-relevant scenarios, including dynamics, optics, and thermodynamics, together with diverse real-world and creative content. To ensure label reliability, scores and anomaly timestamps are produced through trained human annotation with an additional automated quality-control pass. Evaluation is based on both score prediction and anomaly localization, with a composite protocol that combines TimeStamp_IOU and SRCC/PLCC. This report summarizes the challenge design and provides method-level insights from submitted solutions.

cs.CV↗
arXiv2026

High-Precision Ground Characterization of Test-Mass Magnetic Properties for the Taiji Gravitational Wave Mission via a Physics-Informed Neural Framework

Taiji is a gravitational wave detection mission in space initiated by the Chinese Academy of Sciences, which will open the millihertz window through a heliocentric triangular constellation of three drag-free spacecraft. Its ultimate sensitivity is determined partly by the residual acceleration noise of the gravitational reference sensors (GRS), within which the coupling between the test-mass and the fluctuating environmental magnetic field constitutes one of the key stray-force contributions. Following the path established by the LISA and TianQin teams, high-precision ground characterization of remanent magnetic moment $\vec{m}_r$ and volume susceptibility $χ$ of the test masses is a central step in the Taiji pre-launch test program. A persistent challenge for this characterization is the non-stationary, colored background noise inherent to torsion-pendulum facilities, which systematically biases classical Ordinary Least Squares (OLS) and Kalman filter (KF) estimators. We propose an AI-enhanced Differentiable Weighted Least Squares (AI-WLS) framework that fuses a dilated one-dimensional residual network, acting as a dynamic noise evaluator, with a fully differentiable analytical physical solver. This architecture preserves the exact linear mapping from the magnetic parameters to the torque response while autonomously identifying and suppressing contaminated data segments. Validated on real measured noise from the Changchun Institute of Optics, Fine Mechanics and Physics torsion-pendulum facility developed for Taiji, which achieves a torque sensitivity of order $10^{-13}\,\mathrm{N\cdot m\,Hz^{-1/2}}$, the AI-WLS framework bounds the maximum absolute estimation errors at $4.46\times 10^{-10}\,\mathrm{A\cdot m^2}$ for $\vec{m}_r$ and $7.8\times 10^{-8}$ for $χ$, satisfying Taiji's ground-test requirements on all these parameters simultaneously.

astro-ph.IM↗
arXiv2026

Beyond the Trigger: Learning Collaborative Context for Generalizable Trigger-Induced Recommendation

In e-commerce, Trigger-Induced Recommendation (TIR), recommending items after a user clicks a trigger, is an important task. However, modern platforms rely on a continuous stream of diverse and short-lived promotional scenarios (e.g., for Black Friday), creating a significant challenge. Existing methods are less effective here: they either fall into a trigger-dependency trap, recommending overly similar items, or a data-hungry trap, requiring long-term stable data for intent modeling that these ephemeral scenarios cannot provide. To address these limitations, we propose the Collaborative Contrastive Network (CCN), a general and robust framework that approaches the problem from a different perspective. Instead of modeling ambiguous entry intent, CCN learns a user's context-specific preferences by treating the user-trigger pair as a unique condition. It achieves this via a novel contrastive learning scheme, using the collaborative feedback of co-click/co-non-click as a positive signal and mono-click as a negative signal to structure the item representation latent space. To prove its real-world generality, CCN is trained on a heterogeneous dataset spanning over a dozen different scenarios from an entire year, and the online A/B test is conducted in a completely new, unseen scenario on Taobao, where CCN boosts CTR by 12.3\% and order volume by 12.7\%, demonstrating its effectiveness and generalization.

cs.IR↗
arXiv2026

All-domain Moveline Evolution Network for Click-Through Rate Prediction

E-commerce app users exhibit behaviors that are inherently logically consistent. A series of multi-scenario user behaviors interconnect to form the scene-level all-domain user moveline, which ultimately reveals the user's true intention. Traditional CTR prediction methods typically focus on the item-level interaction between the target item and the historically interacted items. However, the scene-level interaction between the target item and the user moveline remains underexplored. There are two challenges when modeling the interaction with preceding all-domain user moveline: (i) Heterogeneity between items and scenes: Unlike traditional user behavior sequences that utilize items as carriers, the user moveline utilizes scenes as carriers. The heterogeneity between items and scenes complicates the process of aligning interactions within a unified representation space. (ii) Temporal misalignment of linked scene-level and item-level behaviors: In the preceding user moveline with a fixed sampling length, certain critical scene-level behaviors are closely linked to subsequent item-level behaviors. However, it is impossible to establish a complete temporal alignment that clearly identifies which specific scene-level behaviors correspond to which item-level behaviors. To address these challenges and pioneer modeling user intent from the perspective of the all-domain moveline, we propose All-domain Moveline Evolution Network (AMEN). AMEN not only transfers interactions between items and scenes to homogeneous representation spaces, but also introduces a Temporal Sequential Pairwise (TSP) mechanism to understand the nuanced associations between scene-level and item-level behaviors, ensuring that the all-domain user moveline differentially influences CTR predictions for user's favored and unfavored items. Online A/B testing demonstrates that our method achieves a +11.6% increase in CTCVR.

cs.IR↗
arXiv2026

Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines

Click-Through Rate (CTR) prediction has long been dominated by discriminative paradigms that optimize local decision boundaries within candidate-specific subspaces. However, these models often fail to capture the global joint distribution and the continuous structural evolution of user intent across all-domain movelines. While generative approaches attempt to model global transition patterns, existing methods suffer from discretization-induced information collapse by remapping nuanced e-commerce signals into discrete linguistic or categorical spaces, failing to preserve the topological fidelity of interest trajectories. To overcome these limitations, we propose a novel generative pre-training paradigm that models user intent as a continuous evolutionary trajectory on a high-dimensional latent interest manifold, termed the Next Interest Flow (NIF). We introduce kinematic constraints to govern this flow: Interest Diversity is achieved via tangent space decomposition, while Evolution Velocity ensures trajectory smoothness through geodesic regularization. To bridge the objective mismatch between generative pre-training and discriminative fine-tuning, we propose a bidirectional alignment strategy to synchronize semantic spaces. Furthermore, we develop a Temporal Sequential Pairwise (TSP) mechanism to instill temporal causality within the discriminative framework. We present the All-domain Moveline Evolution Network (AMEN), a unified framework implementing this pipeline. Extensive experiments on a 6.7-billion instance industrial dataset and online A/B tests on Taobao validate AMEN's superiority, achieving +0.87pt AUC gain and +11.6\% CTCVR lift.

cs.IR↗