Abstract-- Since vision-based manipulation policies are typically trained from data gathered from a single viewpoint, their performance drops when the view changes during deployment. Naively aggregating demonstrations from numerous random views is not only costly but also known to destabilize learning, as excessive visual diversity acts as noise. We present V antage, a viewpoint selection framework to fine-tune any pre-trained policy on a small, strategically chosen set of camera poses to induce viewpoint-agnostic behavior . Instead of relying on costly brute-force search over viewpoints, V antage formulates camera placement as an information gain optimization problem in a continuous space. This approach balances exploration of novel poses with exploitation of promising ones, while also providing theoretical guarantees about convergence and robustness. Across manipulation tasks and policy families, V antage consistently improves success under viewpoint shifts compared to fixed, grid, or random data selection strategies with only a handful of fine-tuning steps. Experiments conducted on simulated and real-world setups show that V antage increases the task success rate by 25% for diffusion policies, and yields robust gains in dynamic-camera settings. I. INTRODUCTION Modern robot manipulation policies trained with visual inputs have achieved levels of precision and adaptability that were once considered far-fetched.

Multi-objective optimization problems, which require the simultaneous optimization of multiple objectives, are prevalent across numerous applications. Existing multi-objective optimization methods often rely on manually-tuned aggregation functions to formulate a joint optimization objective. The performance of such hand-tuned methods is heavily dependent on careful weight selection, a time-consuming and laborious process. These limitations also arise in the setting of reinforcement-learning-based motion tracking methods for physically simulated characters, where intricately crafted reward functions are typically used to achieve high-fidelity results. Such solutions not only require domain expertise and significant manual tuning, but also limit the applicability of the resulting reward function across diverse skills. To bridge this gap, we present a novel adversarial multi-objective optimization technique that is broadly applicable to a range of multi-objective reinforcement-learning tasks, including motion tracking. Our proposed Adversarial Differential Discriminator (ADD) receives a single positive sample, yet is still effective at guiding the optimization process. We demonstrate that our technique can enable characters to closely replicate a variety of acrobatic and agile behaviors, achieving comparable quality to state-of-the-art motion-tracking methods, without relying on manually-designed reward functions. Code and results are available at https://add-moo.github.io/.

With the slowing of Moores Law and increasing impact of power constraints, processor designs rely on architectural innovation to achieve differentiating performance. However, the innovation complexity has simultaneously increased the design space of modern high performance processors. Specifically, we identify two key challenges in prior Design Space Exploration (DSE) approaches for modern CPU design - (a) cost model (prediction method) is either slow or microarchitecture-specific or workload-specific and single model is inefficient to learn the whole design space (b) optimization (exploration method) is slow and inaccurate in the large CPU parameter space. This work presents a novel solution called OneDSE to address these emerging challenges in modern CPU design. OneDSE is a unified cost model (metric predictor) and optimizer (CPU parameter explorer) with three key techniques - 1. Transformer-based workload-Aware CPU Estimation (TrACE) framework to predict metrics in the parameter space (TrACE-p) and parameters in the in the metric space (TrACE-m). TrACE-p outperforms State of The Art (SOTA) IPC prediction methods by 5.71x and 28x for single and multiple workloads respectively while being two orders of magnitude faster. 2. We also propose a novel Metric spAce Search opTimizer (MAST) that leverages TrACE-m and outperforms SoTA metaheuristics by 1.19x while being an order of magnitude faster. 3. We propose Subsystem-based Multi-Agent Reinforcement-learning based fine-Tuning (SMART)-TrACE that achieves a 10.6% reduction in prediction error compared to TrACE, enabling more accurate and efficient exploration of the CPU design space.

AI safety has emerged as a critical priority as these systems are increasingly deployed in real-world applications. We propose the first domain-agnostic AI safety ensuring framework that achieves strong safety guarantees while preserving high performance, grounded in rigorous theoretical foundations. Our framework includes: (1) an optimization component with chance constraints, (2) a safety classification model, (3) internal test data, (4) conservative testing procedures, (5) informative dataset quality measures, and (6) continuous approximate loss functions with gradient computation. Furthermore, to our knowledge, we mathematically establish the first scaling law in AI safety research, relating data quantity to safety-performance trade-offs. Experiments across reinforcement learning, natural language generation, and production planning validate our framework and demonstrate superior performance. Notably, in reinforcement learning, we achieve 3 collisions during 10M actions, compared with 1,000-3,000 for PPO-Lag baselines at equivalent performance levels -- a safety level unattainable by previous AI methods. We believe our framework opens a new foundation for safe AI deployment across safety-critical domains.

In this paper, we propose a new mathematical optimization model for multiclass classification based on arrangements of hyperplanes. Our approach preserves the core support vector machine (SVM) paradigm of maximizing class separation while minimizing misclassification errors, and it is computationally more efficient than a previous formulation. We present a kernel-based extension that allows it to construct nonlinear decision boundaries. Furthermore, we show how the framework can naturally incorporate alternative geometric structures, including classification trees, $\ell_p$-SVMs, and models with discrete feature selection. To address large-scale instances, we develop a dynamic clustering matheuristic that leverages the proposed MIP formulation. Extensive computational experiments demonstrate the efficiency of the proposed model and dynamic clustering heuristic, and we report competitive classification performance on both synthetic datasets and real-world benchmarks from the UCI Machine Learning Repository, comparing our method with state-of-the-art implementations available in scikit-learn.

We consider the problem of the existence of an envy-free allocation up to any good (EFX) for linear valuations and establish new results by connecting this problem to a fixed point framework. Specifically, we first use randomized rounding to extend the discrete EFX constraints into a continuous space and show that an EFX allocation exists if and only if the optimal value of the continuously extended objective function is nonpositive. In particular, we demonstrate that this optimization problem can be formulated as an unconstrained difference of convex (DC) program, which can be further simplified to the minimization of a piecewise linear concave function over a polytope. Leveraging this connection, we show that the proposed DC program has a nonpositive optimal objective value if and only if a well-defined continuous vector map admits a fixed point. Crucially, we prove that the reformulated fixed point problem satisfies all the conditions of Brouwer's fixed point theorem, except that self-containedness is violated by an arbitrarily small positive constant. To address this, we propose a slightly perturbed continuous map that always admits a fixed point. This fixed point serves as a proxy for the fixed point (if it exists) of the original map, and hence for an EFX allocation through an appropriate transformation. Our results offer a new approach to establishing the existence of EFX allocations through fixed point theorems. Moreover, the equivalence with DC programming enables a more efficient and systematic method for computing such allocations (if one exists) using tools from nonlinear optimization. Our findings bridge the discrete problem of finding an EFX allocation with two continuous frameworks: solving an unconstrained DC program and identifying a fixed point of a continuous vector map.

The growing demand for efficient deep learning has positioned dataset distillation as a pivotal technique for compressing training dataset while preserving model performance. However, existing inner-loop optimization methods for dataset distillation typically rely on random truncation strategies, which lack flexibility and often yield suboptimal results. In this work, we observe that neural networks exhibit distinct learning dynamics across different training stages-early, middle, and late-making random truncation ineffective. To address this limitation, we propose Automatic Truncated Backpropagation Through Time (AT-BPTT), a novel framework that dynamically adapts both truncation positions and window sizes according to intrinsic gradient behavior. AT-BPTT introduces three key components: (1) a probabilistic mechanism for stage-aware timestep selection, (2) an adaptive window sizing strategy based on gradient variation, and (3) a low-rank Hessian approximation to reduce computational overhead. Extensive experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet-1K show that AT-BPTT achieves state-of-the-art performance, improving accuracy by an average of 6.16% over baseline methods. Moreover, our approach accelerates inner-loop optimization by 3.9x while saving 63% memory cost.

Existing GFlowNet-based methods for vehicle routing problems (VRPs) typically employ Trajectory Balance (TB) to achieve global optimization but often neglect important aspects of local optimization. While Detailed Balance (DB) addresses local optimization more effectively, it alone falls short in solving VRPs, which inherently require holistic trajectory optimization. To address these limitations, we introduce the Hybrid-Balance GFlowNet (HBG) framework, which uniquely integrates TB and DB in a principled and adaptive manner by aligning their intrinsically complementary strengths. Additionally, we propose a specialized inference strategy for depot-centric scenarios like the Capacitated Vehicle Routing Problem (CVRP), leveraging the depot node's greater flexibility in selecting successors. Despite this specialization, HBG maintains broad applicability, extending effectively to problems without explicit depots, such as the Traveling Salesman Problem (TSP). We evaluate HBG by integrating it into two established GFlowNet-based solvers, i.e., AGFN and GFACS, and demonstrate consistent and significant improvements across both CVRP and TSP, underscoring the enhanced solution quality and generalization afforded by our approach.

This paper introduces a methodology for task-specific design optimization of multirotor Micro Aerial Vehicles. By leveraging reinforcement learning, Bayesian optimization, and covariance matrix adaptation evolution strategy, we optimize aerial robot designs guided exclusively by their closed-loop performance in a considered task. Our approach systematically explores the design space of motor pose configurations while ensuring manufacturability constraints and minimal aerodynamic interference. Results demonstrate that optimized designs achieve superior performance compared to conventional multirotor configurations in agile waypoint navigation tasks, including against fully actuated designs from the literature. We build and test one of the optimized designs in the real world to validate the sim2real transferability of our approach.

Bayesian optimization has emerged as a prominent methodology for optimizing expensive black-box functions by leveraging Gaussian process surrogates, which focus on capturing the global characteristics of the objective function. However, in numerous practical scenarios, the primary objective is not to construct an exhaustive global surrogate, but rather to quickly pinpoint the global optimum. Due to the aleatoric nature of the sequential optimization problem and its dependence on the quality of the surrogate model and the initial design, it is restrictive to assume that all observed samples contribute equally to the discovery of the optimum in this context. In this paper, we introduce Counterfactual Credit Guided Bayesian Optimization (CCGBO), a novel framework that explicitly quantifies the contribution of individual historical observations through counterfactual credit. By incorporating counterfactual credit into the acquisition function, our approach can selectively allocate resources in areas where optimal solutions are most likely to occur. We prove that CCGBO retains sublinear regret. Empirical evaluations on various synthetic and real-world benchmarks demonstrate that CCGBO consistently reduces simple regret and accelerates convergence to the global optimum.