In this paper we show that visual diffusion models can serve as effective geometric solvers: they can directly reason about geometric problems by working in pixel space. We first demonstrate this on the Inscribed Square Problem, a long-standing problem in geometry that asks whether every Jordan curve contains four points forming a square. We then extend the approach to two other well-known hard geometric problems: the Steiner Tree Problem and the Simple Polygon Problem. Our method treats each problem instance as an image and trains a standard visual diffusion model that transforms Gaussian noise into an image representing a valid approximate solution that closely matches the exact one. The model learns to transform noisy geometric structures into correct configurations, effectively recasting geometric reasoning as image generation. Unlike prior work that necessitates specialized architectures and domain-specific adaptations when applying diffusion to parametric geometric representations, we employ a standard visual diffusion model that operates on the visual representation of the problem. This simplicity highlights a surprising bridge between generative modeling and geometric problem solving. Beyond the specific problems studied here, our results point toward a broader paradigm: operating in image space provides a general and practical framework for approximating notoriously hard problems, and opens the door to tackling a far wider class of challenging geometric tasks.

AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, there are now many such agents, ranging from general-purpose "deep research" systems to specialized science-specific agents, such as AI Scientist and AIGS. Rigorous evaluation of these agents is critical for progress. Yet existing benchmarks fall short on several fronts: they (1) fail to provide holistic, product-informed measures of real-world use cases such as science research; (2) lack reproducible agent tools necessary for a controlled comparison of core agentic capabilities; (3) do not account for confounding variables such as model cost and tool access; (4) do not provide standardized interfaces for quick agent prototyping and evaluation; and (5) lack comprehensive baseline agents necessary to identify true advances. In response, we define principles and tooling for more rigorously benchmarking agents. Using these, we present AstaBench, a suite that provides the first holistic measure of agentic ability to perform scientific research, comprising 2400+ problems spanning the entire scientific discovery process and multiple scientific domains, and including many problems inspired by actual user requests to deployed Asta agents. Our suite comes with the first scientific research environment with production-grade search tools that enable controlled, reproducible evaluation, better accounting for confounders. Alongside, we provide a comprehensive suite of nine science-optimized classes of Asta agents and numerous baselines. Our extensive evaluation of 57 agents across 22 agent classes reveals several interesting findings, most importantly that despite meaningful progress on certain individual aspects, AI remains far from solving the challenge of science research assistance.

Designing incentives for a multi-agent system to induce a desirable Nash equilibrium is both a crucial and challenging problem appearing in many decision-making domains, especially for a large number of agents $N$. Under the exchangeability assumption, we formalize this incentive design (ID) problem as a parameterized mean-field game (PMFG), aiming to reduce complexity via an infinite-population limit. We first show that when dynamics and rewards are Lipschitz, the finite-$N$ ID objective is approximated by the PMFG at rate $\mathscr{O}(\frac{1}{\sqrt{N}})$. Moreover, beyond the Lipschitz-continuous setting, we prove the same $\mathscr{O}(\frac{1}{\sqrt{N}})$ decay for the important special case of sequential auctions, despite discontinuities in dynamics, through a tailored auction-specific analysis. Built on our novel approximation results, we further introduce our Adjoint Mean-Field Incentive Design (AMID) algorithm, which uses explicit differentiation of iterated equilibrium operators to compute gradients efficiently. By uniting approximation bounds with optimization guarantees, AMID delivers a powerful, scalable algorithmic tool for many-agent (large $N$) ID. Across diverse auction settings, the proposed AMID method substantially increases revenue over first-price formats and outperforms existing benchmark methods.

Facial Landmark Detection (FLD) in thermal imagery is critical for applications in challenging lighting conditions, but it is hampered by the lack of rich visual cues. Conventional cross-modal solutions, like feature fusion or image translation from RGB data, are often computationally expensive or introduce structural artifacts, limiting their practical deployment. To address this, we propose Multi-Level Cross-Modal Knowledge Distillation (MLCM-KD), a novel framework that decouples high-fidelity RGB-to-thermal knowledge transfer from model compression to create both accurate and efficient thermal FLD models. A central challenge during knowledge transfer is the profound modality gap between RGB and thermal data, where traditional unidirectional distillation fails to enforce semantic consistency across disparate feature spaces. To overcome this, we introduce Dual-Injected Knowledge Distillation (DIKD), a bidirectional mechanism designed specifically for this task. DIKD establishes a connection between modalities: it not only guides the thermal student with rich RGB features but also validates the student's learned representations by feeding them back into the frozen teacher's prediction head. This closed-loop supervision forces the student to learn modality-invariant features that are semantically aligned with the teacher, ensuring a robust and profound knowledge transfer. Experiments show that our approach sets a new state-of-the-art on public thermal FLD benchmarks, notably outperforming previous methods while drastically reducing computational overhead.

Abstract-- T o address the need for high-precision localization of climbing robots in complex high-altitude environments, this paper proposes a multi-sensor fusion system that overcomes the limitations of single-sensor approaches. Firstly, the localization scenarios and the problem model are analyzed. An integrated architecture of Attention Mechanism-based Fusion Algorithm (AMF A) incorporating planar array Ultra-Wideband (UWB), GPS, Inertial Measurement Unit (IMU), and barometer is designed to handle challenges such as GPS occlusion and UWB Non-Line-of-Sight (NLOS) problem. Then, End-to-end neural network inference models for UWB and barometer are developed, along with a multimodal attention mechanism for adaptive data fusion. An Unscented Kalman Filter (UKF) is applied to refine the trajectory, improving accuracy and robustness. Finally, real-world experiments show that the method achieves 0.48 m localization accuracy and lower MAX error of 1.50 m, outperforming baseline algorithms such as GPS/INS-EKF and demonstrating stronger robustness.

Efficiently solving constrained optimization problems is crucial for numerous real-world applications, yet traditional solvers are often computationally prohibitive for real-time use. Machine learning-based approaches have emerged as a promising alternative to provide approximate solutions at faster speeds, but they struggle to strictly enforce constraints, leading to infeasible solutions in practice. To address this, we propose the Feasibility-Seeking Neural Network (FSNet), which integrates a feasibility-seeking step directly into its solution procedure to ensure constraint satisfaction. This feasibility-seeking step solves an unconstrained optimization problem that minimizes constraint violations in a differentiable manner, enabling end-to-end training and providing guarantees on feasibility and convergence. Our experiments across a range of different optimization problems, including both smooth/nonsmooth and convex/nonconvex problems, demonstrate that FSNet can provide feasible solutions with solution quality comparable to (or in some cases better than) traditional solvers, at significantly faster speeds.

The success of the machine learning field has reliably depended on training on large datasets. While effective, this trend comes at an extraordinary cost. This is due to two deeply intertwined factors: the size of models and the size of datasets. While promising research efforts focus on reducing the size of models, the other half of the equation remains fairly mysterious. Indeed, it is surprising that the standard approach to training remains to iterate over and over, uniformly sampling the training dataset. In this paper we explore a series of alternative training paradigms that leverage insights from hard-data-mining and dropout, simple enough to implement and use that can become the new training standard. The proposed Progressive Data Dropout reduces the number of effective epochs to as little as 12.4% of the baseline. This savings actually do not come at any cost for accuracy. Surprisingly, the proposed method improves accuracy by up to 4.82%. Our approach requires no changes to model architecture or optimizer, and can be applied across standard training pipelines, thus posing an excellent opportunity for wide adoption. Code can be found here: https://github.com/bazyagami/LearningWithRevision

Abstract--Visual degradation caused by limited visibility, insufficient lighting, and feature scarcity in underwater environments presents significant challenges to visual-inertial simultaneous localization and mapping (SLAM) systems. The key innovation lies in the tight integration of four distinct sensor modalities to ensure reliable operation, even under degraded visual conditions. To mitigate DVL drift and improve measurement efficiency, we propose a novel velocity-bias-based DVL preintegration strategy. At the frontend, hybrid tracking strategies and acoustic-inertial-depth joint optimization enhance system stability. Additionally, multi-source hybrid residuals are incorporated into a graph optimization framework. Extensive quantitative and qualitative analyses of the proposed system are conducted in both simulated and real-world underwater scenarios. The results demonstrate that our approach outperforms current state-of-the-art stereo visual-inertial SLAM systems in both stability and localization accuracy, exhibiting exceptional robustness, particularly in visually challenging environments. UMAN activities in the fields of ocean engineering and marine science are increasing steadily, encompassing scientific expeditions to study underwater hydrothermal vents and archaeological sites, inspections and maintenance of subsea pipelines and reservoirs, and salvage operations for wrecked aircraft and vessels. Shuoshuo Ding, Tiedong Zhang and Dapeng Jiang are with School of Ocean Engineering and T echnology & Southern Marine science and Engineering Guangdong Laboratory (Zhuhai), Sun Y at-sen University, Zhuhai 519082, China, with Guangdong Provincial Key Laboratory of Information T echnology for Deep Water Acoustics, Zhuhai 519082, China, and also with Key Laboratory of Comprehensive Observation of Polar Environment (Sun Y at-sen University), Ministry of Education, Zhuhai 519082, China (e-mail: dingshsh5@mail2.sysu.edu.cn,

This paper presents SolarBoost, a novel approach for forecasting power output in distributed photovoltaic (DPV) systems. While existing centralized photovoltaic (CPV) methods are able to precisely model output dependencies due to uniformity, it is difficult to apply such techniques to DPV systems, as DPVs face challenges such as missing grid-level data, temporal shifts in installed capacity, geographic variability, and panel diversity. SolarBoost overcomes these challenges by modeling aggregated power output as a composite of output from small grids, where each grid output is modeled using a unit output function multiplied by its capacity. This approach decouples the homogeneous unit output function from dynamic capacity for accurate prediction. Efficient algorithms over an upper-bound approximation are proposed to overcome computational bottlenecks in loss functions. We demonstrate the superiority of grid-level modeling via theoretical analysis and experiments. SolarBoost has been validated through deployment across various cities in China, significantly reducing potential losses and provides valuable insights for the operation of power grids. The code for this work is available at https://github.com/DAMO-DI-ML/SolarBoost.

Abstract--Despite rapid advancements in sensor networks, conventional battery-powered sensor networks suffer from limited operational lifespans and frequent maintenance requirements that severely constrain their deployment in remote and inaccessible environments. As such, wireless rechargeable sensor networks (WRSNs) with mobile charging capabilities offer a promising solution to extend network lifetime. In this paper, we investigate a typical scenario where mobile chargers move and charge the sensor, thereby maintaining the network connectivity while minimizing the energy waste. Specifically, we formulate a multi-objective optimization problem that simultaneously maximizes the network node survival rate and mobile charger energy usage efficiency across multiple time slots, which presents NP-hard computational complexity with long-term temporal dependencies that make traditional optimization approaches ineffective. T o address these challenges, we propose an enhanced evolutionary multi-objective deep reinforcement learning algorithm, which integrates a long short-term memory (LSTM)-based policy network for temporal pattern recognition, a multilayer perceptron-based prospective increment model for future state prediction, and a time-varying Pareto policy evaluation method for dynamic preference adaptation. Extensive simulation results demonstrate that the proposed algorithm significantly outperforms existing approaches in balancing node survival rate and energy efficiency while generating diverse Pareto-optimal solutions. Moreover, we reveal that the LSTM-enhanced policy network achieves 25% faster convergence compared to conventional neural networks, and the time-varying evaluation method adapts effectively to changing network conditions with improved long-term performance stability. Bowei Tong, Hui Kang, and Jiahui Li are with the College of Computer Science and Technology, Jilin University, Changchun 130012, China (e-mails: tongbw25@mails.jlu.edu.cn; Geng Sun is with the College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China, and also with the College of Computing and Data Science, Nanyang Technological University, Singapore 639798 (e-mail: sungeng@jlu.edu.cn). Jiacheng Wang and Dusit Niyato are with the College of Computing and Data Science, Nanyang Technological University, Singapore 639798 (e-mail: jiacheng.wang@ntu.edu.sg; Bo Xu is with the School of Information and Communication Engineering, Hainan University, Haikou 570228, China (e-mail: 996458@hainanu.edu.cn).