Robotic manipulation is challenging due to discontinuous dynamics, as well as high-dimensional state and action spaces. Data-driven approaches that succeed in manipulation tasks require large amounts of data and expert demonstrations, typically from humans. Existing manipulation planners are restricted to specific systems and often depend on specialized algorithms for using demonstration. Therefore, we introduce a flexible motion planner tailored to dexterous and whole-body manipulation tasks. Our planner creates readily usable demonstrations for reinforcement learning algorithms, eliminating the need for additional training pipeline complexities. With this approach, we can efficiently learn policies for complex manipulation tasks, where traditional reinforcement learning alone only makes little progress. Furthermore, we demonstrate that learned policies are transferable to real robotic systems for solving complex dexterous manipulation tasks.

Abstract-- To work in unknown outdoor environments, autonomous sampling machines need the ability to target samples despite limited visibility and robotic arm reach distance. We design a heuristic guided search method to speed up the search process and more efficiently localize the approximate center of soil regions. Through simulation experiments, we assess the effectiveness of the proposed algorithm and discover superior performance in terms of speed, distance traveled, and success rate compared to naive baselines. I. INTRODUCTION In this paper, we address the problem of autonomous sample collection in outdoor, unknown environments. While Figure 1: In this example, a robot--perhaps a camera mounted collecting soil or similar organic material, there are no end effector of a robotic arm--uses a heuristic method to guarantees that samples will be reachable, visible, or even search for the center of a soil region in a sample distribution. For this reason, a robot needs an effective search task The circle is the start position, and the star indicates the to locate and move sufficiently close to the samples prior to center which the agent aims to reach.

In recent years, there has been renewed interest in closing the performance gap between state-of-the-art planning solvers and generalized planning (GP), a research area of AI that studies the automated synthesis of algorithmic-like solutions capable of solving multiple classical planning instances. One of the current advancements has been the introduction of Best-First Generalized Planning (BFGP), a GP algorithm based on a novel solution space that can be explored with heuristic search, one of the foundations of modern planners. This paper evaluates the application of parallel search techniques to BFGP, another critical component in closing the performance gap. We first discuss why BFGP is well suited for parallelization and some of its differentiating characteristics from classical planners. Then, we propose two simple shared-memory parallel strategies with good scaling with the number of cores.

This paper explores a novel paradigm in low-bit (i.e. 4-bits or lower) quantization, differing from existing state-of-the-art methods, by framing optimal quantization as an architecture search problem within convolutional neural networks (ConvNets). Our framework, dubbed \textbf{CoRa} (Optimal Quantization Residual \textbf{Co}nvolutional Operator Low-\textbf{Ra}nk Adaptation), is motivated by two key aspects. Firstly, quantization residual knowledge, i.e. the lost information between floating-point weights and quantized weights, has long been neglected by the research community. Reclaiming the critical residual knowledge, with an infinitesimal extra parameter cost, can reverse performance degradation without training. Secondly, state-of-the-art quantization frameworks search for optimal quantized weights to address the performance degradation. Yet, the vast search spaces in weight optimization pose a challenge for the efficient optimization in large models. For example, state-of-the-art BRECQ necessitates $2 \times 10^4$ iterations to quantize models. Fundamentally differing from existing methods, \textbf{CoRa} searches for the optimal architectures of low-rank adapters, reclaiming critical quantization residual knowledge, within the search spaces smaller compared to the weight spaces, by many orders of magnitude. The low-rank adapters approximate the quantization residual weights, discarded in previous methods. We evaluate our approach over multiple pre-trained ConvNets on ImageNet. \textbf{CoRa} achieves comparable performance against both state-of-the-art quantization-aware training and post-training quantization baselines, in $4$-bit and $3$-bit quantization, by using less than $250$ iterations on a small calibration set with $1600$ images. Thus, \textbf{CoRa} establishes a new state-of-the-art in terms of the optimization efficiency in low-bit quantization.

These studies have demonstrated how model performance is influenced by both the size of the model and the amount of training computation. However, there is limited knowledge on how varying the compute during inference affects model performance after the model has been trained. To improve the task performance of large language models (LLMs), inference techniques typically involve additional computation as a performance maximization step at inference time [Nye et al., 2021, Wei et al., 2022, Wang et al., 2022b, Yao et al., 2023, Chen et al., 2024b]. This cost must be taken into account for compute-optimal inference. For example, a Monte Carlo Tree Search (MCTS) method [Jones, 2021] may improve task performance, but potentially require much more compute than simply sampling solutions multiple times. Generally speaking, we need a comprehensive understanding of how various inference-time methods (e.g., Best-of-N, Majority Voting) trade off between performance and cost. To improve our understanding, this paper presents a thorough empirical evaluation with careful analysis over various configurations of representative LLMs and inference algorithms. Specifically, we explore how to select an optimal size for the language model and an effective inference strategy (e.g., Greedy Search, Majority Voting, Best-of-N, Weighted Voting, and their Tree Search variants) to maximize performance (i.e., accuracy) with a given compute budget.

Process models are, like event data, first-class citizens in most process mining approaches. Several process modeling formalisms have been proposed and used, e.g., Petri nets, BPMN, and process trees. Despite their frequent use, little research addresses the formal properties of process trees and the corresponding potential to improve the efficiency of solving common computational problems. Therefore, in this paper, we propose an invertible state space definition for process trees and demonstrate that the corresponding state space graph is isomorphic to the state space graph of the tree's inverse. Our result supports the development of novel, time-efficient, decomposition strategies for applications of process trees. Our experiments confirm that our state space definition allows for the adoption of bidirectional state space search, which significantly improves the overall performance of state space searches.

As a broadly applied technique in numerous optimization problems, recently, local search has been employed to solve Pseudo-Boolean Optimization (PBO) problem. A representative local search solver for PBO is LSPBO. In this paper, firstly, we improve LSPBO by a dynamic scoring mechanism, which dynamically strikes a balance between score on hard constraints and score on the objective function. Moreover, on top of this improved LSPBO , we develop the first parallel local search PBO solver. The main idea is to share good solutions among different threads to guide the search, by maintaining a pool of feasible solutions. For evaluating solutions when updating the pool, we propose a function that considers both the solution quality and the diversity of the pool. Furthermore, we calculate the polarity density in the pool to enhance the scoring function of local search. Our empirical experiments show clear benefits of the proposed parallel approach, making it competitive with the parallel version of the famous commercial solver Gurobi.

We present a game framework tailored for deduction games, enabling structured analysis from the perspective of Shannon entropy variations. Additionally, we introduce a new forward search algorithm, Information Set Entropy Search (ISES), which effectively solves many single-player deduction games. The ISES algorithm, augmented with sampling techniques, allows agents to make decisions within controlled computational resources and time constraints. Experimental results on eight games within our framework demonstrate the significant superiority of our method over the Single Observer Information Set Monte Carlo Tree Search(SO-ISMCTS) algorithm under limited decision time constraints. The entropy variation of game states in our framework enables explainable decision-making, which can also be used to analyze the appeal of deduction games and provide insights for game designers.

Recently, vision-language instruct-tuning models have made significant progress due to their more comprehensive understanding of the world. In this work, we discovered that large-scale 3D parallel training on those models leads to an imbalanced computation load across different devices. The vision and language parts are inherently heterogeneous: their data distribution and model architecture differ significantly, which affects distributed training efficiency. We rebalanced the computational loads from data, model, and memory perspectives to address this issue, achieving more balanced computation across devices. These three components are not independent but are closely connected, forming an omniverse balanced training framework. Specifically, for the data, we grouped instances into new balanced mini-batches within and across devices. For the model, we employed a search-based method to achieve a more balanced partitioning. For memory optimization, we adaptively adjusted the re-computation strategy for each partition to utilize the available memory fully. We conducted extensive experiments to validate the effectiveness of our method. Compared with the open-source training code of InternVL-Chat, we significantly reduced GPU days, achieving about 1.8x speed-up. Our method's efficacy and generalizability were further demonstrated across various models and datasets. Codes will be released at https://github.com/ModelTC/OmniBal.

Generative retrieval introduces a groundbreaking paradigm to document retrieval by directly generating the identifier of a pertinent document in response to a specific query. This paradigm has demonstrated considerable benefits and potential, particularly in representation and generalization capabilities, within the context of large language models. However, it faces significant challenges in E-commerce search scenarios, including the complexity of generating detailed item titles from brief queries, the presence of noise in item titles with weak language order, issues with long-tail queries, and the interpretability of results. To address these challenges, we have developed an innovative framework for E-commerce search, called generative retrieval with preference optimization. This framework is designed to effectively learn and align an autoregressive model with target data, subsequently generating the final item through constraint-based beam search. By employing multi-span identifiers to represent raw item titles and transforming the task of generating titles from queries into the task of generating multi-span identifiers from queries, we aim to simplify the generation process. The framework further aligns with human preferences using click data and employs a constrained search method to identify key spans for retrieving the final item, thereby enhancing result interpretability. Our extensive experiments show that this framework achieves competitive performance on a real-world dataset, and online A/B tests demonstrate the superiority and effectiveness in improving conversion gains.