PhyCo: Learning Controllable Physical Priors for Generative Motion

/in /by

Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a framework that introduces continuous, interpretable, and physically grounded control into video generation. Our approach integrates three key components: (i) a large-scale dataset of over 100K photorealistic simulation videos where friction, restitution, deformation, and force are systematically varied across diverse scenarios; (ii) physics-supervised fine-tuning of a pretrained diffusion model using a ControlNet conditioned on pixel-aligned physical property maps; and (iii) VLM-guided reward optimization, where a fine-tuned vision-language model evaluates generated videos with targeted physics queries and provides differentiable feedback. This combination enables a generative model to produce physically consistent and controllable outputs through variations in physical attributes–without any simulator or geometry reconstruction at inference. On the Physics-IQ benchmark, PhyCo significantly improves physical realism over strong baselines, and human studies confirm clearer and more faithful control over physical attributes. Our results demonstrate a scalable path toward physically consistent, controllable generative video models that generalize beyond synthetic training environments.

Read more

LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents

/in /by

LangDriveCTRL is a natural-language-controllable framework for editing real-world driving videos to synthesize diverse traffic scenarios. It represents each video as an explicit 3D scene graph, decomposing the scene into a static background and dynamic object nodes. To enable fine-grained editing and realism, it introduces a feedback-driven agentic pipeline. An Orchestrator converts user instructions into executable graphs that coordinate specialized multi-modal agents and tools. An Object Grounding Agent aligns free-form text with target object nodes in the scene graph; a Behavior Editing Agent generates multi-object trajectories from language instructions; and a Behavior Reviewer Agent iteratively reviews and refines the generated trajectories. The edited scene graph is rendered and harmonized using a video diffusion tool, and then further refined by a Video Reviewer Agent to ensure photorealism and appearance alignment. LangDriveCTRL supports both object node editing (removal, insertion, and replacement) and multi-object behavior editing from natural-language instructions. Quantitatively, it achieves nearly higher instruction alignment than the previous SoTA, with superior photorealism, structural preservation, and traffic realism.

Read more

HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes

/in /by

Ensuring safety in autonomous driving requires scalable generation of realistic, controllable driving scenes beyond what real-world testing provides. Yet existing instruction guided image editors, trained on object-centric or artistic data, struggle with dense, safety-critical driving layouts. We propose HorizonWeaver, which tackles three fundamental challenges in driving scene editing: (1) multi-level granularity, requiring coherent object- and scene-level edits in dense environments; (2) rich high-level semantics, preserving diverse objects while following detailed instructions; and (3) ubiquitous domain shifts, handling changes in climate, layout, and traffic across unseen environments. The core of HorizonWeaver is a set of complementary contributions across data, model, and training: (1) Data: Large-scale dataset generation, where we build a paired real/ synthetic dataset from Boreas [4], nuScenes [5], and Argoverse2 [26] to improve generalization; (2) Model: Lang- Masks for fine-grained editing, where semantics-enriched masks and prompts enable precise, language-guided edits; and (3) Training: Content preservation and instruction alignment, where joint losses enforce scene consistency and instruction fidelity. Together, HorizonWeaver provides a scalable framework for photorealistic, instruction-driven editing of complex driving scenes, collecting 255K images across 13 editing categories and outperforming prior methods in L1, CLIP, and DINO metrics, achieving +46.4% user preference and improving BEV segmentation IoU by +33%. Project website: https://msoroco.github.io/horizonweaver/

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 Splatting delivers substantially higher fidelity than alternative 3D representations, and that temporal priors from video diffusion are essential for coherent synthesis. Combining these finding, HorizonSuite 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.

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

NEC Labs America Attends CVPR 2026 in Denver, CO June 3-7, 2026

/in /by

NEC Labs America headed to Denver for CVPR 2026, one of the most prestigious gatherings in computer vision, machine learning, and pattern recognition. The IEEE/CVF Conference on Computer Vision and Pattern Recognition brought innovators from around the world to share breakthroughs.

Read more

Exact PDL-Induced SNR Statistics in Dual-Polarization Coherent Optical Communication Systems

/in /by

We derive the exact probability density function of the signal to noise ratio (SNR) impairment caused by polarization dependent loss (PDL) in coherent optical systems. Using thehinge model for PDL statistics, we construct a sequence of variable transformations that yields the expression of the SNR probability density function by means of a sequence of nested recursive integrals. Monte Carlo simulations validate the analytical formulation assuming realistic PDL levels and link configurations, showing excellent agreement. The model accurately captures SNR variability introduced by cascaded PDL elements and provides a foundation for statistical margin assessment, digital twin modeling, and quality of transmission estimation in flexible, low marginoptical networks.

Read more

Automated Negotiation and Multimodal Time-Series Forecasting for Efficient Procurement

/in /by

Procurement is a key function in supply chain management that involves acquiring goods and services to meet organizational needs. Efficient procurement is crucial for minimizing costs, ensuring timely delivery, and maintaining quality standards. This paper explores the integration of automated negotiation and multimodal time-series forecasting to enhance procurement processes. Automated negotiation can streamline interactions with suppliers, while multimodal time-series forecasting can improve demand prediction accuracy by leveraging diverse data sources leading to better negotiation outputs. By combining these approaches, organizations can optimize procurement strategies, reduce costs, and improve overall supply chain efficiency. We present two case studies using simulations based on real-world data for procurement that show the effectiveness of the proposed framework.

Read more

Training Small AI Models Without Blindly Trusting Big Teacher Models

/in /by

Machine learning is shifting from learning from data alone to learning from both data and teacher models. Beta-KD uses uncertainty-aware Bayesian weighting to train compact multimodal AI without blindly trusting every teacher signal.

Read more

Which Should We Test Next? Performance Gap Discovery for Driving VLMs

/in /by

Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs), yet verificationremains sparse: many slices are missing, making empirical failure rates unreliable. We propose SLICESCORER, a deterministic scoring rule for missing-slicerecommendation that combines (i) an exposure-based coverage prior to prioritize rare, under-tested regions, and (ii) a neighbor-failure prior that propagatesrisk from similar tested conditions. SLICESCORER is deliberately simple- interpretable, auditable, and conservative- properties essential for safety-criticalvalidation. For stress testing beyond the declared ODD, we embed SLICESCORER within SLICENAV, an LLM-orchestrated verification pipeline where the modelinterprets developer queries to select relevant operators (triage, scoring, acquisition, evaluation) and vocabulary extensions, composing verification workflows whilekeeping all scoring deterministic and auditable. Experiments on three driving VLMs(WiseAD, DriveMM, Cosmos-Reason2-2B) show that SLICENAV surfaceshigh-risk coverage gaps more effectively than prior slice-discovery methods while maintaining diverse recommendations across the condition space. Ablations confirm both scoring components contribute, and qualitative analysis demonstrates end-to-end workflows from developer query to targeted evaluation.

Read more