Searcharxiv⌕ Search

arXiv subjects

Siao Liu

Publications and source records attributed to Siao Liu.

At least 19 recordsLinked to original sources
arXiv2026

Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context

Dynamic graph learning models how entities and their relations evolve from historical observations to predict future graph states. Existing methods do not fully address dynamic graph world modelling, which requires learning transitions from temporal context to future latent graph states. This is difficult for three reasons: nodes and relations rely on different historical evidence, structural evolution is path-dependent, and future snapshots provide sparse and realization-specific targets. We propose Dynamic Graph World Modelling (DyG-WM), the first framework to jointly predict future node and relation representations from temporal context by answering three questions: what has evolved, how it evolved, and what will evolve next. To capture what has evolved, a historical node-relation context encoder summarizes node-neighborhood trajectories and pair-specific histories. To characterize how it evolved, a node-relation path-signature encoder captures ordered structural changes. To predict what will evolve next, a dual-level joint-embedding objective predicts target-snapshot node and relation representations without reconstructing the raw graph. Experiments on 12 link-prediction and two node-classification datasets demonstrate the effectiveness of DyG-WM across both tasks.

cs.LG↗
arXiv2026

Predict in Chunks, Revise in Spans: History-conditioned Action Regeneration for Robotic Manipulation

Action chunking improves temporal coherence in visuomotor imitation learning by jointly predicting sequences of future actions. However, many existing policies regenerate entire action chunks even when errors are localized, potentially replacing otherwise valid predictions. We introduce Contextual Masked Action Policy (CMAP), a visuomotor policy that refines continuous action chunks through history-conditioned local regeneration. Specifically, CMAP introduces a history-conditioned action tape that combines executed commands with masked future positions to produce coarse action predictions and per-step uncertainty scores. An uncertainty-guided span regeneration mechanism then selects a high-uncertainty contiguous span and reconstructs it using the executed history and retained future predictions as context. By jointly reconstructing neighboring actions, CMAP models local temporal dependencies while preserving all predictions outside the selected span. Extensive experiments on nine simulated and four real-world manipulation tasks demonstrate that CMAP achieves superior overall performance over several competitive baselines. Ablation studies validate the complementary contributions of its key components, while held-out trajectory analysis shows that local regeneration reduces prediction errors within selected spans.

cs.RO↗
arXiv2026

Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented Tuning

Post-training quantization has been shown to preserve VLA performance under standard evaluation conditions, but whether it preserves the full-precision model's robustness and generalization remains underexplored. In this study, we systematically study the robustness and generalization of post-quantized VLA policies under environmental disturbances. Empirical results show that quantized policies can become fragile to subtle environmental variations despite retaining comparable in-distribution performance. We further observe that action discrepancies are concentrated in a small subset of rollout states, while teacher guidance has opposite effects depending on discrepancy: it improves generalization at high-discrepancy states but can degrade it at low-discrepancy states. These findings reveal that effective post-quantization recovery requires selectively intervening on vulnerable states rather than globally distilling the student. We therefore propose Policy-Induced Vulnerability-Oriented Tuning (PIVOT-Q), a vulnerability-aware On-Policy Distillation (OPD) framework that selectively corrects vulnerable states encountered during quantized-student rollouts using the frozen full-precision policy as a teacher. PIVOT-Q identifies vulnerable states using discounted accumulated discrepancies over a short horizon, applies phase-balanced sparse supervision, and uses a Behavioral Anchor to prevent unnecessary changes. Experiments under seven LIBERO-Plus environmental variations demonstrate consistent recovery across multiple VLA backbones and quantization methods. Notably, PIVOT-Q consistently outperforms full-state distillation across all settings while using only 7.4% of its state-level distillation budget. Our code is available at https://github.com/ruanruan-andy/PIVOT-Q.

cs.LG↗
arXiv2026

Assessing the Marginal Utility of Exocentric Head Views in UMI-Style Large-FoV Wrist-Camera Manipulation

Multi-view perception is often treated as a safe design choice for robot manipulation: if one camera is useful, more cameras should be better. We revisit that assumption in tabletop bimanual manipulation by comparing policies trained with two large-field-of-view (FoV) wrist cameras against policies that additionally receive a head view, using controlled-variable experiments on a real bimanual platform. Across three tabletop tasks, adding a head view does not consistently improve task completion or execution quality: when the wrist cameras already observe the objects, grippers, and goal regions, wrist-only policies form a strong baseline. Restricting the wrist-camera FoV increases the potential value of a head view, but performance improves most reliably when the added view supplies concentrated, task-relevant information: region-of-interest (ROI) cropping yields more consistent head-view gains than the uncropped image, which is dominated by background and task-irrelevant regions. The data-scaling results further suggest an interaction between FoV and demonstration count: wide observations improve coverage but may require more data to stabilize, and they may reach a higher performance ceiling once enough demonstrations are available. These results suggest that camera design should be framed as a task-relevance and information-density problem rather than as a simple count of input views.

cs.RO↗
arXiv2026

Scope-WM: Scoped Computation for Efficient Visual World Models

Visual world models enable robotic planning by predicting future observations, but dense latent-state propagation and sample-intensive trajectory optimization incur high inference latency and peak memory usage, limiting real-time deployment on resource-constrained platforms. Existing sparse world-model acceleration methods either rely on unguided token sparsification, which may discard planning-relevant information and restrict achievable sparsity, or introduce heavy auxiliary modules and cumbersome multi-stage training pipelines. In this work, we present Scope-WM, an efficient visual world model that scopes computation to prediction-relevant latent regions and promising action sequences. Scope-WM distills prediction relevance into a lightweight action-conditioned selector and applies full dynamics prediction only to a compact subset of selected tokens. It updates the remaining tokens using a compact summary of foreground states and their changes, allowing the background to perceive foreground dynamics without costly token-to-token interactions. During planning, Scope-WM preserves and reuses high-quality action sequences discovered during the initial MPC search, focusing subsequent search under reduced rollout budgets. The resulting pipeline requires only a one-off selector distillation followed by a single joint training stage for the sparse world model. On the challenging Push-T task, Scope-WM reduces peak GPU memory usage and planning time to $18.1\%$ and $14.3\%$ of those of dense DINO-WM, respectively, corresponding to a $6.97\times$ planning speedup, while maintaining competitive task performance. Further evaluations across five diverse visual planning tasks demonstrate the general applicability of Scope-WM. Code is available at https://github.com/ChunZheng2022/Scope-WM.

cs.CV↗
arXiv2026

Uncertainty-Guided Sparse Refinement for Action Chunking Transformer Policies

Learning chunk-based visuomotor policies for long-horizon robot manipulation remains challenging. Recent action-chunking methods have shown promising performance by predicting temporally extended action sequences. However, their failures are often dominated by prediction errors at a small number of critical timesteps rather than uniformly poor predictions across the entire action chunk, making uniform refinement inefficient and insufficiently targeted. To address this bottleneck, we propose Uncertainty-Guided Refinement (UGR), a sparse refinement framework for chunk-based visuomotor policies. Specifically, UGR follows a coarse-to-refine design: it first predicts a full action chunk, estimates per-step temporal uncertainty from the coarse hidden states, and applies residual correction only to the most uncertain timesteps selected by a binary mask. The uncertainty branch is decoupled from the coarse action predictor, enabling clean attribution of the refinement gains to uncertainty-guided correction rather than additional predictor capacity. Extensive experiments on five dual-arm manipulation tasks from the RoboTwin benchmark show that UGR achieves the best success rate on four tasks, improves over the ACT baseline by up to 13% absolute, and outperforms both full-chunk and position-agnostic block refinement in ablation studies.

cs.RO↗
arXiv2026

Move What Matters: Parameter-Efficient Domain Adaptation via Optimal Transport Flow for Collaborative Perception

Efficient domain adaptation remains a fundamental challenge for deploying multi-agent systems across diverse environments in Vehicle-to-Everything (V2X) collaborative perception. Despite the success of Parameter-Efficient Fine-Tuning (PEFT) in natural language processing and conventional vision tasks, directly applying PEFT to collaborative perception recovers only a limited portion of the performance lost to domain shift. In this work, we identify two complementary bottlenecks that limit this recovery: (i) inter-frame redundancy within a collaborative sequence, which makes the effectiveness of scarce labels sensitive to frame selection, and (ii) foreground cues that become less linearly decodable in deeper-stage representations of a frozen backbone. To address these issues, we propose FlowAdapt, a parameter-efficient framework grounded in optimal transport. Wasserstein Greedy Sampling casts frame selection as minimizing the $W_{\infty}$ distance from the sequence to the retained subset, which equals its covering radius, so a farthest first traversal returns a subset provably within twice the optimum. Progressive Knowledge Transfer then routes compressed early-stage features into the deeper stages, gating each stage-local correction by that early evidence. Extensive experiments across target domains and fusion architectures show that FlowAdapt achieves state-of-the-art adaptation performance with about 1\% trainable parameters, and maintains this lead under localization noise.

cs.CV↗
arXiv2026

TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination

Multi-agent LLM systems have shown promise for complex reasoning, yet recent evaluations reveal they often underperform single-model baselines. We identify a structural failure mode in sequential fine-tuning of shared-context teams: updating one agent shifts the team's context distribution, and when subsequent updates are evaluated on cached rollouts, this mismatch compounds. We formalize this as the compounding occupancy shift and prove that stale-occupancy evaluation incurs a penalty that scales quadratically with the number of agents. In contrast, intermediate-occupancy evaluation reduces this to linear scaling. We propose TeamTR, a trust-region framework that resamples trajectories after each component update and enforces per-agent divergence control, yielding rigorous per-update and per-stage improvement lower bounds. Experiments show that TeamTR outperforms single-agent and sequential baselines with 7.1% on average, mitigates coordination regressions, and supports plug-and-play component replacement. Code is available at https://github.com/Yydc/TeamTR.

cs.LG↗
arXiv2026

ARP: Enhancing Quantized Skill Abstractions via Visual Alignment and Iterative Refinement for Robotic Manipulation

Learning visuomotor policies for long-horizon manipulation remains a fundamental challenge. Recent skill-based imitation learning methods based on discrete quantization have shown promising results by representing complex behaviors as temporally extended skills. However, most existing approaches primarily encode action trajectories into latent skills, yielding weak visual-semantic grounding and limiting the ability to leverage visual observations for skill selection. Moreover, discrete tokenization inevitably incurs precision errors during continuous action generation. To alleviate these issues, we propose Aligned Refinement Policy (ARP), a discrete-skill framework that couples semantic grounding with execution-level refinement. Specifically, ARP introduces (i) a visual--action alignment objective that contrastively aligns visual embeddings with pre-quantized action representations in a shared latent space while preserving a state-independent skill decoder, and (ii) a lightweight Iterative Residual Head (IRH) that performs a two-step refinement to recover fine-grained control for precise execution. Extensive experiments show that ARP achieves state-of-the-art performance on the LIBERO and Meta-World benchmarks. Moreover, real-robot experiments on the Kuavo 4 Pro humanoid platform further validate its effectiveness, yielding consistent performance gains over several baselines on two challenging manipulation tasks.

cs.RO↗
arXiv2026

UMI-Bench 1.0: An Open and Reproducible Real-World Benchmark for Tabletop Robotic Manipulation with UMI Data

Real-robot evaluation is essential for understanding whether learned manipulation policies can operate reliably outside curated demonstrations. This need is particularly pressing for Universal Manipulation Interface (UMI)-style policies, whose performance depends on the coupling between wrist-view observations, action representation, data collection, and physical deployment. Existing real-world benchmarks have made important progress, but they are not designed around this UMI data-to-deployment setting. We present UMI-Bench 1.0, a local-first real-robot benchmark for standardized evaluation of UMI-style manipulation policies. To the best of our knowledge, this is the first benchmark dedicated to real-world evaluation of UMI-based manipulation models. UMI-Bench aligns data collection, scene reset, policy execution, result logging, and task-factor analysis within a unified protocol. By making the full evaluation process reproducible and auditable, UMI-Bench provides a practical testbed for measuring how UMI-trained policies generalize to real physical manipulation.

cs.RO↗
arXiv2026

Modality Dominance-Aware Optimization for Embodied RGB-Infrared Perception

RGB-Infrared (RGB-IR) multimodal perception is fundamental to embodied multimedia systems operating in complex physical environments. Although recent cross-modal fusion methods have advanced RGB-IR detection, the optimization dynamics caused by asymmetric modality characteristics remain underexplored. In practice, disparities in information density and feature quality introduce persistent optimization bias, leading training to overemphasize a dominant modality and hindering effective fusion. To quantify this phenomenon, we propose the Modality Dominance Index (MDI), which measures modality dominance by jointly modeling feature entropy and gradient contribution. Based on MDI, we develop a Modality Dominance-Aware Cross-modal Learning (MDACL) framework that regulates cross-modal optimization. MDACL incorporates Hierarchical Cross-modal Guidance (HCG) to enhance feature alignment and Adversarial Equilibrium Regularization (AER) to balance optimization dynamics during fusion. Extensive experiments on three RGB-IR benchmarks demonstrate that MDACL effectively mitigates optimization bias and achieves SOTA performance.

cs.CV↗
arXiv2025

CalFuse: Multi-Modal Continual Learning via Feature Calibration and Parameter Fusion

With the proliferation of multi-modal data in large-scale visual recognition systems, enabling models to continuously acquire knowledge from evolving data streams while preserving prior information has become increasingly critical. Class-Continual Learning (CCL) addresses this challenge by incrementally incorporating new class knowledge without revisiting historical data, making it essential for real-world big data applications. While traditional CCL methods rely solely on visual features, recent advances in Vision-Language Models (VLMs) such as CLIP demonstrate significant potential for CCL by leveraging pre-trained multi-modal knowledge. However, existing approaches face challenges in mitigating catastrophic forgetting while maintaining the cross-modal generalization capabilities of VLMs. To address these limitations, we propose CalFuse, a framework that synergizes feature Calibration with parameter Fusion to enable effective multi-modal knowledge integration in continual learning scenarios. CalFuse introduces a dynamic feature calibration mechanism that adaptively balances original CLIP visual representations with task-specific features, preserving the model's intrinsic cross-modal generalization while adapting to new classes. Concurrently, a QR decomposition-based parameter fusion strategy progressively integrates newly acquired knowledge with historical task parameters, maintaining equilibrium between learning new class representations and retaining prior knowledge across sequential tasks. Extensive experiments on benchmark datasets validate the effectiveness of our approach in large-scale multi-modal continual learning settings, demonstrating superior performance over state-of-the-art methods in both average accuracy and final task retention.

cs.CV↗
arXiv2025

Privacy-Preserving Video Anomaly Detection: A Survey

Video Anomaly Detection (VAD) aims to automatically analyze spatiotemporal patterns in surveillance videos collected from open spaces to detect anomalous events that may cause harm, such as fighting, stealing, and car accidents. However, vision-based surveillance systems such as closed-circuit television often capture personally identifiable information. The lack of transparency and interpretability in video transmission and usage raises public concerns about privacy and ethics, limiting the real-world application of VAD. Recently, researchers have focused on privacy concerns in VAD by conducting systematic studies from various perspectives including data, features, and systems, making Privacy-Preserving Video Anomaly Detection (P2VAD) a hotspot in the AI community. However, current research in P2VAD is fragmented, and prior reviews have mostly focused on methods using RGB sequences, overlooking privacy leakage and appearance bias considerations. To address this gap, this article is the first to systematically reviews the progress of P2VAD, defining its scope and providing an intuitive taxonomy. We outline the basic assumptions, learning frameworks, and optimization objectives of various approaches, analyzing their strengths, weaknesses, and potential correlations. Additionally, we provide open access to research resources such as benchmark datasets and available code. Finally, we discuss key challenges and future opportunities from the perspectives of AI development and P2VAD deployment, aiming to guide future work in the field.

cs.CV↗
arXiv2025

Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation

Building a lifelong robot that can effectively leverage prior knowledge for continuous skill acquisition remains significantly challenging. Despite the success of experience replay and parameter-efficient methods in alleviating catastrophic forgetting problem, naively applying these methods causes a failure to leverage the shared primitives between skills. To tackle these issues, we propose Primitive Prompt Learning (PPL), to achieve lifelong robot manipulation via reusable and extensible primitives. Within our two stage learning scheme, we first learn a set of primitive prompts to represent shared primitives through multi-skills pre-training stage, where motion-aware prompts are learned to capture semantic and motion shared primitives across different skills. Secondly, when acquiring new skills in lifelong span, new prompts are appended and optimized with frozen pretrained prompts, boosting the learning via knowledge transfer from old skills to new ones. For evaluation, we construct a large-scale skill dataset and conduct extensive experiments in both simulation and real-world tasks, demonstrating PPL's superior performance over state-of-the-art methods.

cs.RO↗
arXiv2024

Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Training

Learning a self-supervised Monocular Depth Estimation (MDE) model with great generalization remains significantly challenging. Despite the success of adversarial augmentation in the supervised learning generalization, naively incorporating it into self-supervised MDE models potentially causes over-regularization, suffering from severe performance degradation. In this paper, we conduct qualitative analysis and illuminate the main causes: (i) inherent sensitivity in the UNet-alike depth network and (ii) dual optimization conflict caused by over-regularization. To tackle these issues, we propose a general adversarial training framework, named Stabilized Conflict-optimization Adversarial Training (SCAT), integrating adversarial data augmentation into self-supervised MDE methods to achieve a balance between stability and generalization. Specifically, we devise an effective scaling depth network that tunes the coefficients of long skip connection and effectively stabilizes the training process. Then, we propose a conflict gradient surgery strategy, which progressively integrates the adversarial gradient and optimizes the model toward a conflict-free direction. Extensive experiments on five benchmarks demonstrate that SCAT can achieve state-of-the-art performance and significantly improve the generalization capability of existing self-supervised MDE methods.

cs.CV↗
arXiv2024

Sampling to Distill: Knowledge Transfer from Open-World Data

Data-Free Knowledge Distillation (DFKD) is a novel task that aims to train high-performance student models using only the pre-trained teacher network without original training data. Most of the existing DFKD methods rely heavily on additional generation modules to synthesize the substitution data resulting in high computational costs and ignoring the massive amounts of easily accessible, low-cost, unlabeled open-world data. Meanwhile, existing methods ignore the domain shift issue between the substitution data and the original data, resulting in knowledge from teachers not always trustworthy and structured knowledge from data becoming a crucial supplement. To tackle the issue, we propose a novel Open-world Data Sampling Distillation (ODSD) method for the DFKD task without the redundant generation process. First, we try to sample open-world data close to the original data's distribution by an adaptive sampling module and introduce a low-noise representation to alleviate the domain shift issue. Then, we build structured relationships of multiple data examples to exploit data knowledge through the student model itself and the teacher's structured representation. Extensive experiments on CIFAR-10, CIFAR-100, NYUv2, and ImageNet show that our ODSD method achieves state-of-the-art performance with lower FLOPs and parameters. Especially, we improve 1.50\%-9.59\% accuracy on the ImageNet dataset and avoid training the separate generator for each class.

cs.CV↗
arXiv2024

De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts

Data-Free Knowledge Distillation (DFKD) is a promising task to train high-performance small models to enhance actual deployment without relying on the original training data. Existing methods commonly avoid relying on private data by utilizing synthetic or sampled data. However, a long-overlooked issue is that the severe distribution shifts between their substitution and original data, which manifests as huge differences in the quality of images and class proportions. The harmful shifts are essentially the confounder that significantly causes performance bottlenecks. To tackle the issue, this paper proposes a novel perspective with causal inference to disentangle the student models from the impact of such shifts. By designing a customized causal graph, we first reveal the causalities among the variables in the DFKD task. Subsequently, we propose a Knowledge Distillation Causal Intervention (KDCI) framework based on the backdoor adjustment to de-confound the confounder. KDCI can be flexibly combined with most existing state-of-the-art baselines. Experiments in combination with six representative DFKD methods demonstrate the effectiveness of our KDCI, which can obviously help existing methods under almost all settings, \textit{e.g.}, improving the baseline by up to 15.54\% accuracy on the CIFAR-100 dataset.

cs.CV↗
arXiv2023

Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation

Learning a policy with great generalization to unseen environments remains challenging but critical in visual reinforcement learning. Despite the success of augmentation combination in the supervised learning generalization, naively applying it to visual RL algorithms may damage the training efficiency, suffering from serve performance degradation. In this paper, we first conduct qualitative analysis and illuminate the main causes: (i) high-variance gradient magnitudes and (ii) gradient conflicts existed in various augmentation methods. To alleviate these issues, we propose a general policy gradient optimization framework, named Conflict-aware Gradient Agreement Augmentation (CG2A), and better integrate augmentation combination into visual RL algorithms to address the generalization bias. In particular, CG2A develops a Gradient Agreement Solver to adaptively balance the varying gradient magnitudes, and introduces a Soft Gradient Surgery strategy to alleviate the gradient conflicts. Extensive experiments demonstrate that CG2A significantly improves the generalization performance and sample efficiency of visual RL algorithms.

cs.CV↗