Logical Guidance for the Exact Composition of Diffusion Models

/in /by

We propose LOGDIFF (Logical Guidance for the Exact Composition of Diffusion Models), a guidance framework for diffusion models that enables principled constrained generation with complex logical expressions at inference time. We study when exact score-based guidance for complex logical formulas can be obtained from guidance signals associated with atomic properties. First, we derive an exact Boolean calculus that provides a sufficient condition for exact logical guidance. Specifically, if a formula admits a circuit representation in which conjunctions combine conditionally independent subformulas and disjunctions combine subformulas that are either conditionally independent or mutually exclusive, exact logical guidance is achievable. In this case, the guidance signal can be computed exactly from atomic scores and posterior probabilities using an efficient recursive algorithm.Moreover, we show that, for commonly encountered classes of distributions, any desired Boolean formula is compilable into such a circuit representation. Second, by combining atomic guidance scores with posterior probability estimates, we introduce a hybrid guidance approach that bridges classifier guidance and classifier-free guidance, applicable to both compositional logical guidance and standard conditional generation. We demonstrate the effectiveness of our framework on multiple image and protein structure generation tasks.

Read more

HorizonForge: Driving Scene Editing with Any Trajectories and Any Vehicles

/in /by

Controllable driving scene generation is critical for realistic and scalable autonomous driving simulation, yet existing approaches struggle to jointly achieve photorealism and precise control. We introduce HorizonForge, a unified framework that reconstructs scenes as editable Gaussian Splats and Meshes, enabling fine-grained 3D manipulation and language-driven vehicle insertion. Edits are rendered through a noise-aware video diffusion process that enforces spatial and temporal consistency, producing diverse scene variations in a single feed-forward pass without per-trajectory optimization. To standardize evaluation, we further propose HorizonSuite, a comprehensive benchmark spanning ego- and agent-level editing tasks such as trajectory modifications and object manipulation. Extensive experiments show that Gaussian-Mesh representation delivers substantially higher fidelity than alternative 3D representations, and that temporal priors from video diffusion are essential for coherent synthesis. Combining these findings, HorizonForge establishes a simple yet powerful paradigm for photorealistic, controllable driving simulation, achieving an 83.4% user-preference gain and a 25.19% FID improvement over the second-best state-of-the-art method. Project page: https://horizonforge.github.io/.

Read more

Manhole Localization and Condition Diagnostics in Telecom Networks Using Distributed Acoustic and Temperature Sensing

/in /by

We present methods and field trial results demonstrating an integrated distributed acoustic sensing (DAS) and distributed temperature sensing (DTS) system for manhole localization, condition diagnostics, and anomaly detection in pre-deployed telecommunication fiber networks. The proposed system leverages ambient environmental signals, such as vibrational patterns from traffic and day-night temperature fluctuations, and machine learning techniques for automated detection. By combining DAS waterfall traces with temperature measurements from DTS, we achieve improved classification accuracy. Experimental results from three real-world testbeds in Texas and New Jersey show a significant improvement in classification accuracy—from 78.9% and 89.5% using DAS and DTS alone, respectively, to 94.7% via cross-referenced analysis. We propose a structured prediction formulation for manhole localization based on a U-Net architecture with a gated attention mechanism, where the label of each fiber location in the waterfall image is predicted using both its neighboring context and within-patch discriminative features. The method also supports cross-route generalization for manhole localization and enables condition diagnostics, identifying issues such as cable exposure and water ingress. These results highlight the potential for scalable deployment of fiber sensing solutions for real-time, continuous monitoring of telecom infrastructure.

Read more

Field Trial of High-Sensitivity Forward-Transmission Sensing for Real-World Event Detection Over Live Urban Fiber Networks

/in /by

Vibration sensing based on forward transmission is an emerging topic for network protection and environmental monitoring, especially in long-haul submarine cables and urban fiber networks. However, previous field trials of this approach have mainly focused on localizing strong events under controlled or relatively quiet conditions. In this work, we investigate the capability of forward-transmission vibration sensing to detect weak signals in noisy environments. We demonstrate a high-sensitivity vibration sensing system operating over an 80-km deployed live urban fiber loop without optical amplifiers. The system is enhanced by adaptive time-frequency masking and in-band laser phase noise suppression techniques to improve sensitivity and noise robustness. It has successfully identified and localized weak real-world vibration events with peak-to-peak amplitude lower than 20 rad, such as construction activity near a manhole and even footsteps on handhole lids. Field trial results confirm its robust performance under dynamic environments, including road traffic-induced ground vibrations and aerial cable disturbances. To the best of our knowledge, this is the first demonstration of weak vibration event detection using forward transmission in urban fiber networks. It remarks a significant step towards practical distributed vibration sensing in smart city applications.

Read more

MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discovery

/in /by

Uncovering causal structures from observational data is crucial for understanding complex systems and making informed decisions. While reinforcement learning (RL) has shown promise in identifying these structures in the form of a directed acyclic graph (DAG), existing methods often lack efficiency, making them unsuitable for online applications. In this paper, we propose MARLIN, an efficient multi-agent RL-based approach for incremental DAG learning. MARLIN uses a DAG generation policy that maps a continuous real-valued space to the DAG space as an intra-batch strategy, then incorporates two RL agents — state-specific and state-invariant — to uncover causal relationships and integrates these agents into an incremental learning framework. Furthermore, the framework leverages a factored action space to enhance parallelization efficiency. Extensive experiments on synthetic and real datasets demonstrate that MARLIN out-performs state-of-the-art methods in terms of both efficiency and effectiveness.

Read more

Brownian Bridge Augmented Surrogate Simulation and Injection Planning for Geological CO2 Storage

/in /by

Geological CO2 storage (GCS) involves injecting captured CO2 into deep sub-surface formations to support climate goals. The effective management of GCS relies on adaptive injection planning to dynamically control injection rates and well pressures to balance both storage safety and efficiency. Prior literature, including numerical optimization methods and surrogate-optimization methods, is limited by real-world GCS requirements of smooth state transitions and goal-directed planning within limited time. To address these limitations, we propose a Brownian Bridge — augmented framework for surrogate simulation and injection planning in GCS and develop two insights (i) Brownian bridge as smooth state regularizer for better surrogate simulator; (ii) Brownian bridge as goal-time-conditioned planning guidance for better injection planning. Our method has three stages: (i) learning deep Brownian bridge representations with contrastive and reconstructive losses from historical reservoir and utility trajectories, (ii) incorporating Brownian bridge-based next state interpolation for simulator regularization (iii) guiding injection planning with Brownian utility-conditioned trajectories to generate high-quality injection plans. Experimental results across multiple datasets collected from diverse GCS settings demonstrate that our framework consistently improves simulation fidelity and planning effectiveness while maintaining low computational overhead.

Read more

Advances in Fiber Sensing

/in /by

In this talk, we will present recent technological advances in fiber sensing applications with long monitoring distances orextending multiple fiber spans. In forward-transmission-based sensing, adaptive beamforming techniques weredemonstrated to achieve multi-event vibration sensing in environments with interference and jamming with significantimprovements in signal reconstruction, noise reduction, and interference rejection from other locations. For sensing oversubmarine cables with many fiber spans with repeaters, it is shown that distributed reflection from Rayleigh scattering canbe detected with sufficient SNR for fiber sensing using HLLB paths. In particular, longitudinal averaging of receivedRayleigh scattered signals can facilitate state-of-polarization-based, multi-span sensing using eigenvalue method.

Read more

Object-Aware 4D Human Motion Generation

/in /by

Recent advances in video diffusion models have enabled the generation of high-quality videos. However, these videos still suffer from unrealistic deformations, semantic violations, and physical inconsistencies that are largely rooted in the absence of 3D physical priors. To address these challenges, we propose an object-aware 4D human motion generation framework grounded in 3D Gaussian representations and motion diffusion priors. With pre-generated 3D humans and objects, our method, Motion Score Distilled Interaction (MSDI), employs the spatial and prompt semantic information in large language models (LLMs) and motion priors through the proposed Motion Diffusion Score Distillation Sampling (MSDS). The combination of MSDS and LLMs enables our spatial-aware motion optimization, which distills score gradients from pre-trained motion diffusion models, to refine human motion while respecting object and semantic constraints. Unlike prior methods requiring joint training on limited interaction datasets, our zero-shot approach avoids retraining and generalizes to out-of-distribution object aware human motions. Experiments demonstrate that our framework produces natural and physically plausible human motions that respect 3D spatial context, offering a scalable solution for realistic 4D generation.

Read more

EditGRPO: Reinforcement Learning with Post-Rollout Edits for Clinically Accurate Chest X-Ray Report Generation

/in /by

Radiology report generation requires advanced medical image analysis, effective temporal reasoning, and accurate text generation. Although recent innovations, particularly multimodal large language models, have shown improved performance, their supervised fine-tuning (SFT) objective is not explicitly aligned with clinical efficacy. In this work, we introduce EditGRPO, a mixed-policy reinforcement learning algorithm designed specifically to optimize the generation through clinically motivated rewards. EditGRPO integrates on-policy exploration with off-policy guidance by injecting sentence-level detailed corrections during training rollouts. This mixed-policy approach addresses the exploration dilemma and sampling efficiency issues typically encountered in RL. Applied to a Qwen2.5-VL-3B, EditGRPO outperforms both SFT and vanilla GRPO baselines, achieving an average improvement of 3.4% in clinical metrics across four major datasets. Notably, EditGRPO also demonstrates superior out-of-domain generalization, with an average performance gain of5.9% on unseen datasets.

Read more

Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation

/in /by

Radiology Report Generation (RRG) is a critical step toward automating healthcare workflows, facilitating accurate patient assessments, and reducing the workload of medical professionals. Despite recent progress in Large Medical Vision-Language Models (Med-VLMs), generating radiology reports that are both visually grounded and clinically accurate remains a significant challenge. Existing approaches often rely on large labeled corpora for pre-training, costly task-specific preference data, or retrieval-based methods. However, these strategies do not adequately mitigate hallucinations arising from poor cross-modal alignment between visual and linguistic representations. To address these limitations, we propose VALOR:Visual Alignment of Medical Vision-Language Models for GrOunded Radiology Report Generation. Our method introduces a reinforcement learning-based post-alignment framework utilizing Group-Relative Proximal Optimization (GRPO). The training proceeds in two stages: (1) improving the Med-VLM with textual rewards to encourage clinically precise terminology, and (2) aligning the vision projection module of the textually grounded model with disease findings, thereby guiding attention toward image re gions most relevant to the diagnostic task. Extensive experiments on multiple benchmarks demonstrate that VALOR substantially improves factual accuracy and visual grounding, achieving significant performance gains over state-of-the-art report generation methods.

Read more