Developed by a team of scientists at Seoul National University and Gachon University in South Korea, PB, or the Particle-armored liquid roBot, is designed to behave the way cells do, and imitate biological forms and functions. The morphing bot can ooze around tiny pillars, skim across water to reach a dry surface without bursting, merge with another PB, and swallow a glass bead, all without compromising structural integrity. The robot is still in the research stages, but the promising results so far raise hopes that PB could potentially help advance drug delivery and even tumor cell destruction in the future.

In this paper, we propose a novel maximum causal Tsallis entropy (MCTE) framework for imitation learning which can efficiently learn a sparse multi-modal policy distribution from demonstrations. We provide the full mathematical analysis of the proposed framework. First, the optimal solution of an MCTE problem is shown to be a sparsemax distribution, whose supporting set can be adjusted. The proposed method has advantages over a softmax distribution in that it can exclude unnecessary actions by assigning zero probability. Second, we prove that an MCTE problem is equivalent to robust Bayes estimation in the sense of the Brier score. Third, we propose a maximum causal Tsallis entropy imitation learning (MCTEIL) algorithm with a sparse mixture density network (sparse MDN) by modeling mixture weights using a sparsemax distribution. In particular, we show that the causal Tsallis entropy of an MDN encourages exploration and efficient mixture utilization while Shannon entropy is less effective.

In safety-critical robotic tasks, potential failures must be reduced, and multiple constraints must be met, such as avoiding collisions, limiting energy consumption, and maintaining balance. Thus, applying safe reinforcement learning (RL) in such robotic tasks requires to handle multiple constraints and use risk-averse constraints rather than risk-neutral constraints. To this end, we propose a trust region-based safe RL algorithm for multiple constraints called a safe distributional actor-critic (SDAC). Our main contributions are as follows: 1) introducing a gradient integration method to manage infeasibility issues in multi-constrained problems, ensuring theoretical convergence, and 2) developing a TD(λ) target distribution to estimate risk-averse constraints with low biases. We evaluate SDAC through extensive experiments involving multi-and single-constrained robotic tasks. While maintaining high scores, SDAC shows 1.93 times fewer steps to satisfy all constraints in multi-constrained tasks and 1.78 times fewer constraint violations in single-constrained tasks compared to safe RL baselines.

We propose the Mixture of Frozen Experts (MoFE) architecture, which integrates Parameter-efficient Fine-tuning (PEFT) and the Mixture of Experts (MoE) architecture to enhance both training efficiency and model scalability. By freezing the Feed Forward Network (FFN) layers within the MoE framework, MoFE significantly reduces the number of trainable parameters, improving training efficiency while still allowing for effective knowledge transfer from the expert models. This facilitates the creation of models proficient in multiple domains. We conduct experiments to evaluate the trade-offs between performance and efficiency, compare MoFE with other PEFT methodologies, assess the impact of domain expertise in the constituent models, and determine the optimal training strategy. The results show that, although there may be some trade-offs in performance, the efficiency gains are substantial, making MoFE a reasonable solution for real-world, resource-constrained environments.

InfoFusion Controller: Informed TRRT Star with Mutual Information based on Fusion of Pure Pursuit and MPC for Enhanced Path Planning Seongjun Choi Kyung-Hee University Autonomous Driving Lab, MODULABS, Republic of Korea Y oungbum Kim Korea Aviation University Autonomous Driving Lab, MODULABS, Republic of Korea Nam Woo Kim Unity T echnologies Autonomous Driving Lab, MODULABS, Republic of Korea Mansun Shin SP ACEEDUING Co., Ltd. Autonomous Driving Lab, MODULABS, Republic of Korea Byunggi Chae Auroka Pankyo Autonomous Driving Lab, MODULABS, Republic of Korea Sungjin Lee Dong Seoul University, Autonomous Driving Lab, MODULABS, Republic of Korea Abstract --In this paper, we propose the InfoFusion Controller, an advanced path planning algorithm that integrates both global and local planning strategies to enhance autonomous driving in complex urban environments. The global planner utilizes the informed Theta-Rapidly-exploring Random Tree Star (Informed-TRRT*) algorithm to generate an optimal reference path, while the local planner combines Model Predictive Control (MPC) and Pure Pursuit algorithms. Mutual Information (MI) is employed to fuse the outputs of the MPC and Pure Pursuit controllers, effectively balancing their strengths and compensating for their weaknesses. The proposed method addresses the challenges of navigating in dynamic environments with unpredictable obstacles by reducing uncertainty in local path planning and improving dynamic obstacle avoidance capabilities.

Chinese artificial intelligence chatbot DeepSeek upended the global industry and wiped billions off U.S. tech stocks when it unveiled its R1 program, which it claims was built on cheap, less sophisticated Nvidia semiconductors. But governments from Rome to Seoul are cracking down on the user-friendly Chinese app, saying they need to prevent potential leaks of sensitive information through generative AI services. Here is a look at what's going on:

Multi-criteria (MC) recommender systems, which utilize MC rating information for recommendation, are increasingly widespread in various e-commerce domains. However, the MC recommendation using training-based collaborative filtering, requiring consideration of multiple ratings compared to single-criterion counterparts, often poses practical challenges in achieving state-of-the-art performance along with scalable model training. To solve this problem, we propose CA-GF, a training-free MC recommendation method, which is built upon criteria-aware graph filtering for efficient yet accurate MC recommendations. Specifically, first, we construct an item-item similarity graph using an MC user-expansion graph. Next, we design CA-GF composed of the following key components, including 1) criterion-specific graph filtering where the optimal filter for each criterion is found using various types of polynomial low-pass filters and 2) criteria preference-infused aggregation where the smoothed signals from each criterion are aggregated. We demonstrate that CA-GF is (a) efficient: providing the computational efficiency, offering the extremely fast runtime of less than 0.2 seconds even on the largest benchmark dataset, (b) accurate: outperforming benchmark MC recommendation methods, achieving substantial accuracy gains up to 24% compared to the best competitor, and (c) interpretable: providing interpretations for the contribution of each criterion to the model prediction based on visualizations.

Safety concerns are out, optimism is in: that was the takeaway from a major artificial intelligence summit in Paris this week, as leaders from the U.S., France, and beyond threw their weight behind the AI industry. Although there were divisions between major nations--the U.S. and the U.K. did not sign a final statement endorsed by 60 nations calling for an "inclusive" and "open" AI sector--the focus of the two-day meeting was markedly different from the last such gathering. Last year, in Seoul, the emphasis was on defining red-lines for the AI industry. The concern: that the technology, although holding great promise, also had the potential for great harm. The final statement made no mention of significant AI risks nor attempts to mitigate them, while in a speech on Tuesday, U.S. Vice President J.D. Vance said: "I'm not here this morning to talk about AI safety, which was the title of the conference a couple of years ago. I'm here to talk about AI opportunity."

The aim of this paper is the reconstruction of a smooth surface from an unorganized point cloud sampled by a closed surface, with the preservation of geometric shapes, without any further information other than the point cloud. Implicit neural representations (INRs) have recently emerged as a promising approach to surface reconstruction. However, the reconstruction quality of existing methods relies on ground truth implicit function values or surface normal vectors. In this paper, we show that proper supervision of partial differential equations and fundamental properties of differential vector fields are sufficient to robustly reconstruct high-quality surfaces. We cast the p-Poisson equation to learn a signed distance function (SDF) and the reconstructed surface is implicitly represented by the zero-level set of the SDF. For efficient training, we develop a variable splitting structure by introducing a gradient of the SDF as an auxiliary variable and impose the p-Poisson equation directly on the auxiliary variable as a hard constraint. Based on the curl-free property of the gradient field, we impose a curl-free constraint on the auxiliary variable, which leads to a more faithful reconstruction. Experiments on standard benchmark datasets show that the proposed INR provides a superior and robust reconstruction. The code is available at https://github.com/Yebbi/PINC.

At the AI Seoul Summit in 2024, a number o f AI developers signed on to the Frontier AI Safety Commitments, agreeing to develop a safety framework outlining how they will manage severe risks that their frontier AI systems may pose ( DSIT, 2024) . Since then, a research field has begun to emerge, with a diverse array of researchers from companies, governments, academi a and other third - party research organi s ations publishing work on how to write and implement an effective safety framework . S ignatories to the commitments are due to publish safety frameworks shortly, in time for the Paris AI Action Summit. This paper summarises emerging practice s - practices that appear promising and are gaining expert recognition - for safety frameworks as identified by this new research field. We draw on both the safety frameworks published so far, literature and standards on frontier AI risk management (as well as risk management more broadly), internal research by the UK AI Safety Institute, and the Frontier AI Safety Commitments themselves.