As autonomous systems are increasingly deployed in open and uncertain settings, there is a growing need for trustworthy world models that can reliably predict future high-dimensional observations. The learned latent representations in world models lack direct mapping to meaningful physical quantities and dynamics, limiting their utility and interpretability in downstream planning, control, and safety verification. In this paper, we argue for a fundamental shift from physically informed to physically interpretable world models -- and crystallize four principles that leverage symbolic knowledge to achieve these ends: (1) structuring latent spaces according to the physical intent of variables, (2) learning aligned invariant and equivariant representations of the physical world, (3) adapting training to the varied granularity of supervision signals, and (4) partitioning generative outputs to support scalability and verifiability. We experimentally demonstrate the value of each principle on two benchmarks. This paper opens several intriguing research directions to achieve and capitalize on full physical interpretability in world models.

Autonomous robots depend crucially on their ability to perceive and process information from dynamic, ever-changing environments. Traditional simultaneous localization and mapping (SLAM) approaches struggle to maintain consistent scene representations because of numerous moving objects, often treating dynamic elements as outliers rather than explicitly modeling them in the scene representation. In this paper, we present a novel hierarchical 3D scene graph-based SLAM framework that addresses the challenge of modeling and estimating the pose of dynamic objects and agents. We use fiducial markers to detect dynamic entities and to extract their attributes while improving keyframe selection and implementing new capabilities for dynamic entity mapping. We maintain a hierarchical representation where dynamic objects are registered in the SLAM graph and are constrained with robot keyframes and the floor level of the building with our novel entity-keyframe constraints and intra-entity constraints. By combining semantic and geometric constraints between dynamic entities and the environment, our system jointly optimizes the SLAM graph to estimate the pose of the robot and various dynamic agents and objects while maintaining an accurate map. Experimental evaluation demonstrates that our approach achieves a 27.57% reduction in pose estimation error compared to traditional methods and enables higher-level reasoning about scene dynamics.

Large Reasoning Models(LRMs) such as OpenAI o1 and DeepSeek-R1 have shown remarkable reasoning capabilities by scaling test-time compute and generating long Chain-of-Thought(CoT). Distillation--post-training on LRMs-generated data--is a straightforward yet effective method to enhance the reasoning abilities of smaller models, but faces a critical bottleneck: we found that distilled long CoT data poses learning difficulty for small models and leads to the inheritance of biases (i.e. over-thinking) when using Supervised Fine-tuning(SFT) and Reinforcement Learning(RL) methods. To alleviate this bottleneck, we propose constructing tree-based CoT data from scratch via Monte Carlo Tree Search(MCTS). We then exploit a set of CoT-aware approaches, including Thoughts Length Balance, Fine-grained DPO, and Joint Post-training Objective, to enhance SFT and RL on the construted data.

To go from (passive) process monitoring to active process control, an effective AI system must learn about the behavior of the complex system from very limited training data, forming an ad-hoc digital twin with respect to process in- and outputs that captures the consequences of actions on the process's world. We propose a novel methodology based on learning world models that disentangles process parameters in the learned latent representation, allowing for fine-grained control. Representation learning is driven by the latent factors that influence the processes through contrastive learning within a joint embedding predictive architecture. This makes changes in representations predictable from changes in inputs and vice versa, facilitating interpretability of key factors responsible for process variations, paving the way for effective control actions to keep the process within operational bounds. The effectiveness of our method is validated on the example of plastic injection molding, demonstrating practical relevance in proposing specific control actions for a notoriously unstable process.

CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive T ask Solving and Reasoning in UA Vs Artem Lykov, V alerii Serpiva, Muhammad Haris Khan, Oleg Sautenkov, Artyom Myshlyaev, Grik Tadevosyan, Y asheerah Y aqoot, and Dzmitry Tsetserukou Abstract -- This paper introduces CognitiveDrone, a novel Vision-Language-Action (VLA) model tailored for complex Unmanned Aerial V ehicles (UA Vs) tasks that demand advanced cognitive abilities. Trained on a dataset comprising over 8,000 simulated flight trajectories across three key categories--Human Recognition, Symbol Understanding, and Reasoning--the model generates real-time 4D action commands based on first-person visual inputs and textual instructions. T o further enhance performance in intricate scenarios, we propose CognitiveDrone-R1, which integrates an additional Vision-Language Model (VLM) reasoning module to simplify task directives prior to high-frequency control. Experimental evaluations using our open-source benchmark, CognitiveDroneBench, reveal that while a racing-oriented model (RaceVLA) achieves an overall success rate of 31.3%, the base CognitiveDrone model reaches 59.6%, and CognitiveDrone-R1 attains a success rate of 77.2%. These results demonstrate improvements of up to 30% in critical cognitive tasks, underscoring the effectiveness of incorporating advanced reasoning capabilities into UA V control systems. Our contributions include the development of a state-of-the-art VLA model for UA V control and the introduction of the first dedicated benchmark for assessing cognitive tasks in drone operations.

The integration of deep generative networks into generating Computer-Aided Design (CAD) models has garnered increasing attention over recent years. Traditional methods often rely on discrete sequences of parametric line/curve segments to represent sketches. Differently, we introduce RECAD, a novel framework that generates Raster sketches and 3D E xtrusions for CAD models. Representing sketches as raster images offers several advantages over discrete sequences: 1) it breaks the limitations on the types and numbers of lines/curves, providing enhanced geometric representation capabilities; 2) it enables interpolation within a continuous latent space; and 3) it allows for more intuitive user control over the output. Technically, RECAD employs two diffusion networks: the first network generates extrusion boxes conditioned on the number and types of extrusions, while the second network produces sketch images conditioned on these extrusion boxes. By combining these two networks, RECAD effectively generates sketch-and-extrude CAD models, offering a more robust and intuitive approach to CAD model generation. Experimental results indicate that RECAD achieves strong performance in unconditional generation, while also demonstrating effectiveness in conditional generation and output editing. Introduction The digital genesis of modern artifacts, from everyday consumer products to complex industrial machinery, is now deeply intertwined with Computer-Aided Design (CAD) systems. Central to many CAD workflows is sketch-based modeling, where 2D sketches imbued with geometric constraints and design intent are transformed into intricate 3D models through a series of feature-based modeling operations, ultimately giving rise to complex assemblies. Among these feature-based modeling operations, extrusion is the most prevalent, allowing designers to generate 3D shapes by extending 2D sketches along a defined path.

Despite significant advancements in Large Language Models (LLMs), developing advanced reasoning capabilities in LLMs remains a key challenge. Process Reward Models (PRMs) have demonstrated exceptional promise in enhancing reasoning by providing step-wise feedback, particularly in the context of mathematical reasoning. However, their application to broader reasoning domains remains understudied, largely due to the high costs associated with manually creating step-level supervision. In this work, we explore the potential of PRMs in graph reasoning problems - a domain that demands sophisticated multi-step reasoning and offers opportunities for automated step-level data generation using established graph algorithms. We introduce GraphSILO, the largest dataset for graph reasoning problems with fine-grained step-wise labels, built using automated Task-oriented Trajectories and Monte Carlo Tree Search (MCTS) to generate detailed reasoning steps with step-wise labels. Building upon this dataset, we train GraphPRM, the first PRM designed for graph reasoning problems, and evaluate its effectiveness in two key settings: inference-time scaling and reinforcement learning via Direct Preference Optimization (DPO). Experimental results show that GraphPRM significantly improves LLM performance across 13 graph reasoning tasks, delivering a 9% gain for Qwen2.5-7B and demonstrating transferability to new graph reasoning datasets and new reasoning domains like mathematical problem-solving. Notably, GraphPRM enhances LLM performance on GSM8K and Math500, underscoring the cross-domain applicability of graph-based reasoning rewards. Our findings highlight the potential of PRMs in advancing reasoning across diverse domains, paving the way for more versatile and effective LLMs.

While progress has been made in legal applications, law reasoning, crucial for fair adjudication, remains unexplored. We propose a transparent law reasoning schema enriched with hierarchical factum probandum, evidence, and implicit experience, enabling public scrutiny and preventing bias. Inspired by this schema, we introduce the challenging task, which takes a textual case description and outputs a hierarchical structure justifying the final decision. We also create the first crowd-sourced dataset for this task, enabling comprehensive evaluation. Simultaneously, we propose an agent framework that employs a comprehensive suite of legal analysis tools to address the challenge task. This benchmark paves the way for transparent and accountable AI-assisted law reasoning in the ``Intelligent Court''.

Inferring the affordance of an object and grasping it in a task-oriented manner is crucial for robots to successfully complete manipulation tasks. Affordance indicates where and how to grasp an object by taking its functionality into account, serving as the foundation for effective task-oriented grasping. However, current task-oriented methods often depend on extensive training data that is confined to specific tasks and objects, making it difficult to generalize to novel objects and complex scenes. In this paper, we introduce AffordGrasp, a novel open-vocabulary grasping framework that leverages the reasoning capabilities of vision-language models (VLMs) for in-context affordance reasoning. Unlike existing methods that rely on explicit task and object specifications, our approach infers tasks directly from implicit user instructions, enabling more intuitive and seamless human-robot interaction in everyday scenarios. Building on the reasoning outcomes, our framework identifies task-relevant objects and grounds their part-level affordances using a visual grounding module. This allows us to generate task-oriented grasp poses precisely within the affordance regions of the object, ensuring both functional and context-aware robotic manipulation. Extensive experiments demonstrate that AffordGrasp achieves state-of-the-art performance in both simulation and real-world scenarios, highlighting the effectiveness of our method. We believe our approach advances robotic manipulation techniques and contributes to the broader field of embodied AI. Project website: https://eqcy.github.io/affordgrasp/.

If we were to apply MCTS directly to this abstracted space, we would encounter two main issues: inefficient utilization of our pre-built search space, with the search potentially diverging prematurely into unexplored regions, and difficulty in building sufficiently deep trees for high-quality long-term decision-making, particularly in areas of high stochasticity or uncertainty (Cou etoux et al., 2011). Therefore, we use progressive widening to extend MCTS to incrementally expand the search tree. It balances the exploration of new states with the exploitation of already visited states based on two hyperparameters: α [0, 1] and ϵ R + . Let |C (s, z) | denote the number of children for the state-action pair (s, z) . The key idea is to alternate between adding new child nodes and selecting among existing child nodes, depending on the number of times a state-action pair ( s, z) has been visited. A new state is added to the tree if |C ( s, z)| < ϵ N (s, z) α, where N (s, z) is the number of times the state-action pair has been visited. The hyperparameter α controls the propensity to select among existing children, with α = 0 leading to always selecting among existing child and α = 1 leading to vanilla MCTS behavior (always adding a new child). In this way, we could enhance our approach by efficiently utilizing the pre-built search space, prioritizing the exploration of promising macro actions while allowing for incremental expansion of the search tree. This technique enables our method to make quick decisions in an anytime manner, leveraging the cached information, and further refine the planning tree if additional time is available.