arXiv subjects

Ruirui Zhang

Publications and source records attributed to Ruirui Zhang.

8 recordsLinked to original sources

arXiv2026

Dense Process Supervision for Search Agents via Fact Utility Estimation

Reinforcement learning (RL) for search agents typically relies on outcome rewards. However, it often fails to achieve effective credit assignment, due to the unclear value of intermediate steps. It is hard to separate their contributions from the final result. In this paper, we propose a dense process supervision method based on fact utility estimation, which models the reasoning process as the accumulation of discrete evidence facts. We first extract structured facts from raw observations and organize them into an explicit fact store. To support credit assignment, we then cluster semantically equivalent facts and infer the posterior utility of each fact cluster using Bayesian estimation over group rollouts. Finally, we convert the estimated fact utilities into dense step-level rewards to guide RL training. Experiments on seven single-hop and multi-hop QA benchmarks show that our method consistently outperforms existing baselines. Ablation studies validate clear relative improvements on multi-hop QA compared to outcome reward-only training.

cs.CL↗

arXiv2026

MultiCompose: Multi-Concept Personalized Composition with Per-Subject Attribute Binding

Text-to-image diffusion models enable personalization of specific visual concepts from a small number of reference images. However, generating a single image that contains multiple personalized subjects, each bound to user-specified attributes such as clothing, accessories, and held objects, remains largely unaddressed. Without explicit spatial constraints, concurrently activated concept checkpoints produce overlapping cross-attention responses, causing per-subject identity degradation and attribute misalignment. Moreover, no established benchmark jointly evaluates these two failure modes in the personalized multi-subject setting. We present MultiCompose, a composition framework that decouples per-concept personalization from multi-subject inference. A semantic preservation regularization maintains attribute binding capacity during fine-tuning, while a two-phase inference procedure automatically establishes subject layout and composes per-concept predictions through spatially exclusive masks. We further introduce MSP-Bench, a benchmark that jointly evaluates identity fidelity (ID), attribute binding accuracy (BIND), and attribute misalignment (MIS) through a dual-pathway protocol. Experiments show that MultiCompose outperforms existing methods on both conventional metrics and MSP-Bench, confirming the benchmark's ability to reveal failure modes that conventional metrics overlook. Code is available at https://github.com/I2-Multimedia-Lab/MultiCompose

cs.CV↗

arXiv2025

Towards Human-level Intelligence via Human-like Whole-Body Manipulation

Building general-purpose intelligent robots has long been a fundamental goal of robotics. A promising approach is to mirror the evolutionary trajectory of humans: learning through continuous interaction with the environment, with early progress driven by the imitation of human behaviors. Achieving this goal presents three core challenges: (1) designing safe robotic hardware with human-level physical capabilities; (2) developing an intuitive and scalable whole-body teleoperation interface for data collection; and (3) creating algorithms capable of learning whole-body visuomotor policies from human demonstrations. To address these challenges in a unified framework, we propose Astribot Suite, a robot learning suite for whole-body manipulation aimed at general daily tasks across diverse environments. We demonstrate the effectiveness of our system on a wide range of activities that require whole-body coordination, extensive reachability, human-level dexterity, and agility. Our results show that Astribot's cohesive integration of embodiment, teleoperation interface, and learning pipeline marks a significant step towards real-world, general-purpose whole-body robotic manipulation, laying the groundwork for the next generation of intelligent robots.

cs.RO↗

arXiv2025

Agent WARPP: Workflow Adherence via Runtime Parallel Personalization

Large language models (LLMs) are increasingly applied in task-oriented dialogue (TOD) systems but often struggle with long, conditional workflows that involve external tool calls and depend on user-specific information. We present Workflow Adherence via Runtime Parallel Personalization, or WARPP, a training-free, modular framework that combines multi-agent orchestration with runtime personalization to improve workflow adherence in LLM-based systems. By dynamically pruning conditional branches based on user attributes, the framework reduces reasoning overhead and narrows tool selection at runtime. WARPP deploys a parallelized architecture where a dedicated Personalizer agent operates alongside modular, domain-specific agents to dynamically tailor execution paths in real time. The framework is evaluated across five representative user intents of varying complexity within three domains: banking, flights, and healthcare. Our evaluation leverages synthetic datasets and LLM-powered simulated users to test scenarios with conditional dependencies. Our results demonstrate that WARPP outperforms both the non-personalized method and the ReAct baseline, achieving increasingly larger gains in parameter fidelity and tool accuracy as intent complexity grows, while also reducing average token usage, without any additional training.

cs.AI↗

arXiv2025

OptiCorNet: Optimizing Sequence-Based Context Correlation for Visual Place Recognition

Visual Place Recognition (VPR) in dynamic and perceptually aliased environments remains a fundamental challenge for long-term localization. Existing deep learning-based solutions predominantly focus on single-frame embeddings, neglecting the temporal coherence present in image sequences. This paper presents OptiCorNet, a novel sequence modeling framework that unifies spatial feature extraction and temporal differencing into a differentiable, end-to-end trainable module. Central to our approach is a lightweight 1D convolutional encoder combined with a learnable differential temporal operator, termed Differentiable Sequence Delta (DSD), which jointly captures short-term spatial context and long-range temporal transitions. The DSD module models directional differences across sequences via a fixed-weight differencing kernel, followed by an LSTM-based refinement and optional residual projection, yielding compact, discriminative descriptors robust to viewpoint and appearance shifts. To further enhance inter-class separability, we incorporate a quadruplet loss that optimizes both positive alignment and multi-negative divergence within each batch. Unlike prior VPR methods that treat temporal aggregation as post-processing, OptiCorNet learns sequence-level embeddings directly, enabling more effective end-to-end place recognition. Comprehensive evaluations on multiple public benchmarks demonstrate that our approach outperforms state-of-the-art baselines under challenging seasonal and viewpoint variations.

cs.CV↗

arXiv2024

A Resource-Adaptive Approach for Federated Learning under Resource-Constrained Environments

The paper studies a fundamental federated learning (FL) problem involving multiple clients with heterogeneous constrained resources. Compared with the numerous training parameters, the computing and communication resources of clients are insufficient for fast local training and real-time knowledge sharing. Besides, training on clients with heterogeneous resources may result in the straggler problem. To address these issues, we propose Fed-RAA: a Resource-Adaptive Asynchronous Federated learning algorithm. Different from vanilla FL methods, where all parameters are trained by each participating client regardless of resource diversity, Fed-RAA adaptively allocates fragments of the global model to clients based on their computing and communication capabilities. Each client then individually trains its assigned model fragment and asynchronously uploads the updated result. Theoretical analysis confirms the convergence of our approach. Additionally, we design an online greedy-based algorithm for fragment allocation in Fed-RAA, achieving fairness comparable to an offline strategy. We present numerical results on MNIST, CIFAR-10, and CIFAR-100, along with necessary comparisons and ablation studies, demonstrating the advantages of our work. To the best of our knowledge, this paper represents the first resource-adaptive asynchronous method for fragment-based FL with guaranteed theoretical convergence.

cs.LG↗

arXiv2022

Large-Scale Integrated Flexible Tactile Sensor Array for Sensitive Smart Robotic Touch

In the long pursuit of smart robotics, it has been envisioned to empower robots with human-like senses, especially vision and touch. While tremendous progress has been made in image sensors and computer vision over the past decades, the tactile sense abilities are lagging behind due to the lack of large-scale flexible tactile sensor array with high sensitivity, high spatial resolution, and fast response. In this work, we have demonstrated a 64x64 flexible tactile sensor array with a record-high spatial resolution of 0.9 mm (equivalently 28.2 pixels per inch), by integrating a high-performance piezoresistive film (PRF) with a large-area active matrix of carbon nanotube thin-film transistors. PRF with self-formed microstructures exhibited high pressure-sensitivity of ~385 kPa-1 for MWCNTs concentration of 6%, while the 14% one exhibited fast response time of ~3 ms, good linearity, broad detection range beyond 1400 kPa, and excellent cyclability over 3000 cycles. Using this fully integrated tactile sensor array, the footprint maps of an artificial honeybee were clearly identified. Furthermore, we hardware-implemented a smart tactile system by integrating the PRF-based sensor array with a memristor-based computing-in-memory chip to record and recognize handwritten digits and Chinese calligraphy, achieving high classification accuracies of 98.8% and 97.3% in hardware, respectively. The integration of sensor networks with deep learning hardware may enable edge or near-sensor computing with significantly reduced power consumption and latency. Our work could pave the road to building large-scale intelligent sensor networks for next-generation smart robotics.

cond-mat.mtrl-sci↗

arXiv2020

An inertial Tseng's extragradient method for solving multi-valued variational inequalities with one projection

In this paper, we introduce an inertial Tseng's extragradient method for solving multi-valued variational inequalits, in which only one projection is needed at each iterate. We also obtain the strong convergence results of the proposed algorithm, provided that the multi-valued mapping is continuous and pseudomonotone with nonempty compact convex values. Moreover, numerical simulation results illustrate the efficiency of our method when compared to existing methods.

math.OC↗