Science & Mathematics

Haptic teleoperation requires low-latency and reliable communication to preserve stable and responsive interaction between a human operator and a remote environment. However, network congestion can strongly degrade teleoperation performance, particularly when haptic traffic competes with other data flows for limited radio resources. This work investigates a deep reinforcement learning (DRL)-assisted teleoperation framework over an Ericsson 5G standalone (SA) testbed under different congestion and quality-of-service (QoS) configurations. In the evaluated task, a human operator uses a haptic device to steer a spaceship through a remote virtual game. The DRL agent runs inside the remote environment, hosted at the network edge, and assists the operator by blending its own actions with the operator's commands received over the 5G network. This placement gives the agent direct access to the current state of the environment, unaffected by network delay. Experimental results show that DRL assistance improves task performance under all network conditions, with the largest benefit under congestion, where it reduces mean task completion time by 20.6%. Under congestion, assisted operation even outperforms unassisted operation with QoS prioritisation, which restores latency close to the uncongested baseline.

High-fidelity 4D physical simulation requires accurate physical parameter assignments that align with diverse material properties. Previous methods struggle with critical bottlenecks: they either rely on computationally intensive per-scene optimization or predict parameters from purely visual inputs. The latter suffers from inherent ambiguity, e.g., the inability to distinguish the stiffness of rubber from its appearance alone. To bridge this gap, we propose AutoPhyX, a text-conditioned framework for predicting spatially-varying physical properties. Since training robust feed-forward models requires fine-grained supervision, we first introduce a novel part-controllable data generation pipeline that decomposes complex 3D assets into semantically distinct components and pairs them with physically plausible, diverse parameters and corresponding text descriptions. Leveraging this dataset, AutoPhyX employs a cross-modal modulation mechanism where text features dynamically modulate visual features for precise physical grounding. By formulating property prediction within a voxel field, AutoPhyX ensures compatibility with diverse 3D representations, including meshes, point clouds, Gaussian Splatting, and NeRF. Experiments demonstrate that our method enables physically plausible, text-driven parameter assignment in a single forward pass. It achieves high accuracy and robust generalization to in-the-wild objects, paving the way for future physics-intensive embodied and robotic applications.

Curriculum learning orders samples by difficulty, but difficulty alone does not establish supervision reliability for dense prediction. Easy samples can expose shortcuts, hard samples can be informative, and noisy or ambiguous samples can mislead training. Building on our conference method CurriSeg, we present PaceShift, a stabilize-then-challenge paradigm combining supervision-adaptive curriculum selection with guarded spectral post-training. A learning-dynamics view motivates separating supervision reliability from temporal update value and applying spectral challenges after stabilization. The first phase estimates reliability from available supervision, augmentation consistency, model disagreement, and prediction certainty. Temporal statistics guide sample weighting, while pixel-uncertainty weights reduce the early influence of uncertain regions. The second phase ranks predictions from multiple spectral views using supervision agreement, robustness, reference consistency, and penalties. A pairwise preference objective measured against the frozen Phase-I reference, together with an anchor, refines the prediction. The framework supports full, weak, semi-supervised, and model-derived supervision. Experiments across context-entangled content segmentation (CECS), broader dense-prediction tasks, and foundation-model and cross-modal adaptations show accuracy gains. Targeted diagnostics indicate improved pooled calibration and corruption robustness in the evaluated settings. PaceShift preserves the deployed architecture and adds no inference computation. Code will be publicly released.

In this paper, we propose a geometric approach to deriving attention mechanisms and exploring potential new transformer architectures. We begin by formalizing the notions of knowledge worlds and attention pairings, then demonstrate how this framework naturally leads to the architectures of standard attention, causal attention, linear attention, tensor attention, and recurrent neural networks. Finally, we introduce several new geometric spaces that may inspire novel neural network architectures.

Residual-based causal discovery assumes that each variable is generated from its parents and an independent noise source. It estimates this noise and tests its independence from candidate causes. For identifiable functions such as additive-noise models (ANMs) and the broader class of location-scale noise models (LSNMs), this principle identifies the causal direction, as only the causal model admits this independence. Existing LSNM methods rely on parametric assumptions to obtain standardized residuals, risking model misspecification. In contrast, the RESIT-framework allows for nonparametric estimation of residuals to iteratively identify sink nodes, but was proposed for ANMs. To close this gap, we propose Loscar, an extension of RESIT to LSNMs that estimates the conditional mean and scale via quantile regression, enabling pretrained tabular foundation models as plug-in estimators. We compare it with a feasible generalized least squares (FGLS) variant, which is consistent given suitable basis functions. Across bivariate and multivariate causal-discovery benchmarks, in-context quantile regression substantially outperforms FGLS with flexible function classes, particularly for multivariate causes.

Fine-grained multimodal intelligence requires models to both understand a designated region and localize it from language. Existing methods learn these directions with separate objectives and task-specific annotations. We present Generalized CycleGRPO, the first unified reinforcement learning framework coupling region understanding and localization across spatial, temporal, and spatio-temporal domains. Given a region, a multimodal large language model generates candidate descriptions and then localizes each description to reconstruct the input region. Reconstruction overlap provides a verifiable reward for captioning, while individual localization rewards improve the inverse mapping. A common region-space formulation extends this cycle from image masks and boxes to video intervals and timestamped spatial evidence, without reference captions or an external language-model judge during reinforcement learning. In videos, the cycle encourages descriptions that distinguish a target event from similar recurrences. We introduce DOVE (Distinctive Occurrence-level Video-caption Evaluation), a human-verified contrastive benchmark for this temporal distinctiveness. CycleGRPO improves SAMTok's overall gIoU from 57.5% to 68.2% on GroundingSuite and average gIoU from 71.2% to 78.7% on GRES. For temporal tasks, it achieves 51.9% tIoU on Charades and 33.3% Temporal Evidence Coverage on DOVE, compared with 45.6% and 14.8% for the Qwen3-VL initialization. These results establish region-text cycle consistency as a general self-evaluation principle for multimodal understanding and localization. Models, code, and DOVE are available at https://devinxzhang.github.io/Generalized-CycleGRPO-Page/.

Aligned large language models are trained to comply with benign requests while refusing harmful ones. However, recent work shows that this refusal behavior is fragile and can often be disrupted by simple activation- or weight-space interventions. In particular, refusal has been shown to be largely mediated by a single residual-stream direction, typically computed as a difference-of-means vector between harmful and harmless prompts. However, this standard construction aggregates heterogeneous harmful prompts into one uniform average, potentially conflating distinct refusal-related phenomena. In this work, we study whether refusal interventions can be strengthened by learning how to combine prompt-specific refusal directions. We propose Weighted Refusal Direction Optimization (WRDO), a procedure that constructs a composite refusal direction from a bank of per-prompt directions using learned aggregation weights. This approach allows different harmful prompts to contribute unequally to the final intervention direction. We evaluate WRDO against prior single-direction methods on three open-weight language models using three guard judges and HarmBench as an external evaluator. We further measure the effect of the intervention on general model capability through standard utility benchmarks. Finally, we investigate a defense-oriented setting in which the same optimization machinery is used in reverse to restore refusal behavior in an abliterated model checkpoint. Our results show that weighted aggregation provides a more effective and flexible mechanism for manipulating refusal representations.

One of the enduring challenges in online platforms is recommendation. Both communities and advertisers face difficulties in analyzing complex user behavior, identifying habits and evolving preferences, and providing timely recommendations that are relevant to user interests. In particular, point of interest recommendation poses the additional challenge of identifying the factors that influence user behavior, capturing user tendencies, and generating accurate, personalized recommendations for each individual. In this work, we propose SOAR, a Social and Opinion Aware Recommendation model that incorporates both the user's friendship network and textual reviews to assess whether a location is suitable for a specific user, with a particular emphasis on the sentiment of shared reviews. Experimental results in real-world datasets demonstrate that incorporating reviews into the recommendation process improves the precision of the recommendation.

Vision-language-action (VLA) models achieve strong performance across embodied manipulation tasks by unifying visual understanding, language conditioning, and action generation. However, long-horizon tasks can involve non-Markovian dependencies: successful decisions may require retaining task progress and past interaction outcomes, while partial observability and execution errors compound over time. Existing work has begun to address these challenges by augmenting foundation-model policies with memory and by introducing hierarchical architectures that separate high-level planning from low-level execution. We organize the high-level VLM as a robotic agent through an editable harness to maintain task context and improve planning through execution experience. We instantiate this approach as SERA (Self-Evolving Robotic Agent), with a fixed VLA executor providing low-level control. The harness maintains and updates task context using observations and execution feedback to guide subsequent planning. Self-evolution uses environment rollouts to propose and evaluate harness revisions, with the selected configuration fixed before held-out testing. On RoboMME, SERA achieves 51.38% overall success with autonomous selection, compared with 44.38% without self-evolution. Our exploration suggests that agentic planning is a promising direction for history-dependent robotic manipulation.

Teleoperation enables intuitive control of remote engineering robots for precision tasks. Existing direct joint-mapping methods have two limitations: independent motor saturation disrupts pitch-roll coordination in differential wrists, while fixed mappings struggle with abrupt tracking changes caused by gravitational loads and actuation constraints. We propose an actuator-constraint-aware leader-follower teleoperation method that jointly models leader gravity compensation, leader-follower joint mapping, and follower differential-wrist control. Specifically, we perform coordinated saturation in motor space according to the available gravity margin and integrate continuous angle unwrapping, feedback-state monitoring, and feasible-reference updates. This preserves the operator's motion direction, reduces coordination distortion, and suppresses recovery transients during saturation or brief communication failures. Real-robot experiments demonstrate smoother wrist trajectories and more continuous recovery than direct mapping.

Malicious actors frequently obfuscate their code to hinder investigative reverse engineering efforts. Among the most formidable techniques is virtual machine (VM) obfuscation: programs are translated into bytecode for a custom VM, often with a randomized virtual instruction set and distributed alongside a corresponding interpreter. Manual analysis and deobfuscation scale poorly due to the complexity of VM obfuscation and the diversification techniques that render each VM and interpreter unique. Existing methods primarily focus on simplifying execution traces and identifying virtual execution boundaries. However, comparatively little attention has been given to recovering higher-level program semantics from VM-obfuscated code. To address this gap, we propose VMSpec, a novel decompiler-based approach that automates the construction of VM processor specifications, enabling existing, well-known decompilers to analyze the VM-obfuscated code. We evaluate our prototype of VMSpec on 147 programs from an established obfuscation benchmark, comprising hash functions, standard algorithms, and randomized functions, obfuscated with different configurations of the Tigress and Code Virtualizer obfuscators. To demonstrate real-world applicability, we additionally include six domain generation algorithms stemming from real-world malware. VMSpec completely strips VM-obfuscation from nearly all obfuscated samples, producing output comparable to Ghidra's decompilation of the original code. Furthermore, it is the first method capable of reconstructing the complete program behavior of VM-obfuscated programs with infinite, input-dependent paths and recursive calls.

In particle communication, particles released for different symbols can reach the receiver at overlapping times, making reliable detection difficult. This paper develops a digital communication framework that connects particle transport, pulse shaping, and receiver processing for three-dimensional free-space diffusion-advection channels. We derive the continuous-time and discrete-time frequency responses and explain how flow speed affects channel delay and bandwidth. Under advection-dominated conditions, the group delay approaches $R/V$, and the one-sided $3$-dB bandwidth scales as $V^{3/2}$. We design nonnegative, unit-energy transmit pulses using a packet-level SINR criterion that includes interference from both preceding and subsequent symbols under additive white Gaussian receiver noise. Simulations validate the analytical approximations and show that optimized pulses spread across more of the symbol interval when noise is substantial and become narrower as noise decreases. BER evaluations across SNR and symbol duration compare optimized, rectangular, and single-impulse pulses with several detection methods, identifying the operating conditions in which transmit-pulse design improves reliability.

In this article, we propose ContactFlowFilter, a novel approach for contact estimation that determines the number of active contacts, their locations, and the associated force vectors. We consider a robot manipulator equipped with joint torque sensors and a base force/torque sensor; such a proprioceptive-only setup presents a challenging inverse problem characterized by (i) multi-modality from non-unique solutions, (ii) temporal dependencies in state evolution, and (iii) discrete contact events involving contact addition/removal. Existing approaches, such as particle filters (PFs) and learning-based methods, often struggle to address these challenges simultaneously. To overcome this, ContactFlowFilter integrates a generative model into the PF framework. The recursive structure of the PF captures temporal dependencies, while the flow matching model serves as an auxiliary proposal distribution to track multi-modal beliefs and detect contact events. Extensive validation in both simulation and real-world experiments confirms the effectiveness of the proposed method. In real-world settings, ContactFlowFilter achieves the lowest dissimilarity from the target distribution, with errors of only 0.36 cm and 0.88 cm for single- and dual-contact scenarios, respectively, while operating at 0.69 ms and 2.69 ms.

Existing paired clean-degraded datasets have advanced learning-based underwater image enhancement, but they remain either limited in scale or difficult to acquire, and still fail to adequately cover the diverse degradations encountered in real-world underwater environments. Such scarce and insufficient data ultimately restrict the generalization of underwater image enhancement models, highlighting the need for realistic and controllable degradation modeling to better capture real underwater conditions and improve enhancement robustness. To this end, we propose a unified degradation-aware training framework for the underwater image enhancement task. A Text-Conditioned Degradation Augmentation Pipeline uses a text-guided diffusion model to synthesize diverse and semantically consistent degraded samples, providing paired data to support the subsequent curriculum learning strategy. The proposed Progressive Degradation Curriculum organizes training across multiple attributes and difficulty levels to promote balanced learning, and a Transmission-Guided One-Step Diffusion Model leverages this progressive process to better address the wide range of degradation severity and restoration ambiguity in underwater images. Extensive experiments on multiple underwater benchmarks demonstrate that our proposed method achieves superior performance. Our code and models will be released upon the publication of this work.

This article investigates the joint-angle invariance (JAI) of Jacobian-based performance indices for serial robotic manipulators. We identify kinematic conditions under which representative performance indices, including manipulability, stiffness, and other Jacobian-derived indices, remain independent of the first and last joint angles. This property allows a systematic reduction in the effective configuration-space dimensionality, thereby simplifying the performance evaluation. The utility of JAI is demonstrated through two application scenarios: workspace performance map construction and task layout optimization. Comparative results show that the proposed JAI-based strategy reduces computational effort and storage requirements without compromising the effectiveness.