arXiv subjects

Zhi Zheng

Publications and source records attributed to Zhi Zheng.

At least 73 records · Page 4Linked to original sources

arXiv2025

Tailless Flapping-Wing Robot With Bio-Inspired Elastic Passive Legs for Multi-Modal Locomotion

Flapping-wing robots offer significant versatility; however, achieving efficient multi-modal locomotion remains challenging. This paper presents the design, modeling, and experimentation of a novel tailless flapping-wing robot with three independently actuated pairs of wings. Inspired by the leg morphology of juvenile water striders, the robot incorporates bio-inspired elastic passive legs that convert flapping-induced vibrations into directional ground movement, enabling locomotion without additional actuators. This vibration-driven mechanism facilitates lightweight, mechanically simplified multi-modal mobility. An SE(3)-based controller coordinates flight and mode transitions with minimal actuation. To validate the robot's feasibility, a functional prototype was developed, and experiments were conducted to evaluate its flight, ground locomotion, and mode-switching capabilities. Results show satisfactory performance under constrained actuation, highlighting the potential of multi-modal flapping-wing designs for future aerial-ground robotic applications. These findings provide a foundation for future studies on frequency-based terrestrial control and passive yaw stabilization in hybrid locomotion systems.

cs.RO↗

arXiv2025

AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models

Existing multi-objective preference alignment methods for large language models (LLMs) face limitations: (1) the inability to effectively balance various preference dimensions, and (2) reliance on auxiliary reward/reference models introduces computational complexity. To address these challenges, we propose Adaptive Multi-objective Preference Optimization (AMoPO), a novel framework that achieves dynamic balance across preference dimensions. By introducing the multi-objective optimization paradigm to use the dimension-aware generation metrics as implicit rewards, AMoPO aligns LLMs with diverse preferences without additional reward models or reference models. We introduce an adaptive weight assignment mechanism that models the generation space as a Gaussian distribution, allowing dynamic prioritization of preference dimensions. Empirical results demonstrate that AMoPO outperforms state-of-the-art baselines by 28.5%, and the experiments on 7B, 14B, and 32B models reveal the scaling ability of AMoPO. Moreover, additional analysis of multiple dimensions verifies its adaptability and effectiveness. These findings validate AMoPO's capability to achieve dimension-aware preference alignment, highlighting its superiority. Our codes and datasets are available at https://github.com/Javkonline/AMoPO.

cs.LG↗

arXiv2025

Reasoning-CV: Fine-tuning Powerful Reasoning LLMs for Knowledge-Assisted Claim Verification

Claim verification is essential in combating misinformation, and large language models (LLMs) have recently emerged in this area as powerful tools for assessing the veracity of claims using external knowledge. Existing LLM-based methods for claim verification typically adopt a Decompose-Then-Verify paradigm, which involves decomposing complex claims into several independent sub-claims and verifying each sub-claim separately. However, this paradigm often introduces errors during the claim decomposition process. To mitigate these errors, we propose to develop the Chain-of-Thought (CoT)-Verify paradigm, which leverages LLM reasoning methods to generate CoT-verification paths for the original complex claim without requiring decompositions into sub-claims and separate verification stages. The CoT-Verify paradigm allows us to propose a natural fine-tuning method called Reasoning-CV to enhance the verification capabilities in LLMs. Reasoning-CV includes a supervised fine-tuning (SFT) stage and a self-improvement direct preference optimization (DPO) stage. Utilizing only an 8B pre-trained LLM, Reasoning-CV demonstrates superior knowledge-assisted claim verification performances compared to existing Decompose-Then-Verify methods, as well as powerful black-box LLMs such as GPT-4o+CoT and o1-preview. Our code is available.

cs.AI↗

arXiv2025

Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Data

Data quality has become a key factor in enhancing model performance with the rapid development of large language models (LLMs). Model-driven data filtering has increasingly become a primary approach for acquiring high-quality data. However, it still faces two main challenges: (1) the lack of an efficient data verification strategy makes it difficult to provide timely feedback on data quality; and (2) the selection of seed data for training classifiers lacks clear criteria and relies heavily on human expertise, introducing a degree of subjectivity. To address the first challenge, we introduce an efficient verification strategy that enables rapid evaluation of the impact of data on LLM training with minimal computational cost. To tackle the second challenge, we build upon the assumption that high-quality seed data is beneficial for LLM training, and by integrating the proposed verification strategy, we optimize the selection of positive and negative samples and propose an efficient data filtering pipeline. This pipeline not only improves filtering efficiency, classifier quality, and robustness, but also significantly reduces experimental and inference costs. In addition, to efficiently filter high-quality data, we employ a lightweight classifier based on fastText, and successfully apply the filtering pipeline to two widely-used pre-training corpora, FineWeb and Chinese FineWeb datasets, resulting in the creation of the higher-quality Ultra-FineWeb dataset. Ultra-FineWeb contains approximately 1 trillion English tokens and 120 billion Chinese tokens. Empirical results demonstrate that the LLMs trained on Ultra-FineWeb exhibit significant performance improvements across multiple benchmark tasks, validating the effectiveness of our pipeline in enhancing both data quality and training efficiency.

cs.CL↗

arXiv2025

Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Planners

Recently, Large Language Models (LLMs) have witnessed remarkable performance as zero-shot task planners for robotic manipulation tasks. However, the open-loop nature of previous works makes LLM-based planning error-prone and fragile. On the other hand, failure detection approaches for closed-loop planning are often limited by task-specific heuristics or following an unrealistic assumption that the prediction is trustworthy all the time. As a general-purpose reasoning machine, LLMs or Multimodal Large Language Models (MLLMs) are promising for detecting failures. However, However, the appropriateness of the aforementioned assumption diminishes due to the notorious hullucination problem. In this work, we attempt to mitigate these issues by introducing a framework for closed-loop LLM-based planning called KnowLoop, backed by an uncertainty-based MLLMs failure detector, which is agnostic to any used MLLMs or LLMs. Specifically, we evaluate three different ways for quantifying the uncertainty of MLLMs, namely token probability, entropy, and self-explained confidence as primary metrics based on three carefully designed representative prompting strategies. With a self-collected dataset including various manipulation tasks and an LLM-based robot system, our experiments demonstrate that token probability and entropy are more reflective compared to self-explained confidence. By setting an appropriate threshold to filter out uncertain predictions and seek human help actively, the accuracy of failure detection can be significantly enhanced. This improvement boosts the effectiveness of closed-loop planning and the overall success rate of tasks.

cs.RO↗

arXiv2025

Language-Guided Object-Centric Diffusion Policy for Generalizable and Collision-Aware Robotic Manipulation

Learning from demonstrations faces challenges in generalizing beyond the training data and often lacks collision awareness. This paper introduces Lan-o3dp, a language-guided object-centric diffusion policy framework that can adapt to unseen situations such as cluttered scenes, shifting camera views, and ambiguous similar objects while offering training-free collision avoidance and achieving a high success rate with few demonstrations. We train a diffusion model conditioned on 3D point clouds of task-relevant objects to predict the robot's end-effector trajectories, enabling it to complete the tasks. During inference, we incorporate cost optimization into denoising steps to guide the generated trajectory to be collision-free. We leverage open-set segmentation to obtain the 3D point clouds of related objects. We use a large language model to identify the target objects and possible obstacles by interpreting the user's natural language instructions. To effectively guide the conditional diffusion model using a time-independent cost function, we proposed a novel guided generation mechanism based on the estimated clean trajectories. In the simulation, we showed that diffusion policy based on the object-centric 3D representation achieves a much higher success rate (68.7%) compared to baselines with simple 2D (39.3%) and 3D scene (43.6%) representations across 21 challenging RLBench tasks with only 40 demonstrations. In real-world experiments, we extensively evaluated the generalization in various unseen situations and validated the effectiveness of the proposed zero-shot cost-guided collision avoidance.

cs.RO↗

arXiv2025

Unleashing the Power of Large Language Model for Denoising Recommendation

Recommender systems are crucial for personalizing user experiences but often depend on implicit feedback data, which can be noisy and misleading. Existing denoising studies involve incorporating auxiliary information or learning strategies from interaction data. However, they struggle with the inherent limitations of external knowledge and interaction data, as well as the non-universality of certain predefined assumptions, hindering accurate noise identification. Recently, large language models (LLMs) have gained attention for their extensive world knowledge and reasoning abilities, yet their potential in enhancing denoising in recommendations remains underexplored. In this paper, we introduce LLaRD, a framework leveraging LLMs to improve denoising in recommender systems, thereby boosting overall recommendation performance. Specifically, LLaRD generates denoising-related knowledge by first enriching semantic insights from observational data via LLMs and inferring user-item preference knowledge. It then employs a novel Chain-of-Thought (CoT) technique over user-item interaction graphs to reveal relation knowledge for denoising. Finally, it applies the Information Bottleneck (IB) principle to align LLM-generated denoising knowledge with recommendation targets, filtering out noise and irrelevant LLM knowledge. Empirical results demonstrate LLaRD's effectiveness in enhancing denoising and recommendation accuracy.

cs.IR↗

arXiv2025

Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design

Handcrafting heuristics for solving complex optimization tasks (e.g., route planning and task allocation) is a common practice but requires extensive domain knowledge. Recently, Large Language Model (LLM)-based automatic heuristic design (AHD) methods have shown promise in generating high-quality heuristics without manual interventions. Existing LLM-based AHD methods employ a population to maintain a fixed number of top-performing LLM-generated heuristics and introduce evolutionary computation (EC) to iteratively enhance the population. However, these population-based procedures cannot fully develop the potential of each heuristic and are prone to converge into local optima. To more comprehensively explore the space of heuristics, this paper proposes to use Monte Carlo Tree Search (MCTS) for LLM-based heuristic evolution. The proposed MCTS-AHD method organizes all LLM-generated heuristics in a tree structure and can better develop the potential of temporarily underperforming heuristics. In experiments, MCTS-AHD delivers significantly higher-quality heuristics on various complex tasks. Our code is available.

cs.AI↗

arXiv2025

UDC: A Unified Neural Divide-and-Conquer Framework for Large-Scale Combinatorial Optimization Problems

Single-stage neural combinatorial optimization solvers have achieved near-optimal results on various small-scale combinatorial optimization (CO) problems without requiring expert knowledge. However, these solvers exhibit significant performance degradation when applied to large-scale CO problems. Recently, two-stage neural methods motivated by divide-and-conquer strategies have shown efficiency in addressing large-scale CO problems. Nevertheless, the performance of these methods highly relies on problem-specific heuristics in either the dividing or the conquering procedure, which limits their applicability to general CO problems. Moreover, these methods employ separate training schemes and ignore the interdependencies between the dividing and conquering strategies, often leading to sub-optimal solutions. To tackle these drawbacks, this article develops a unified neural divide-and-conquer framework (i.e., UDC) for solving general large-scale CO problems. UDC offers a Divide-Conquer-Reunion (DCR) training method to eliminate the negative impact of a sub-optimal dividing policy. Employing a high-efficiency Graph Neural Network (GNN) for global instance dividing and a fixed-length sub-path solver for conquering divided sub-problems, the proposed UDC framework demonstrates extensive applicability, achieving superior performance in 10 representative large-scale CO problems. The code is available at https://github.com/CIAM-Group/NCO_code/tree/main/single_objective/UDC-Large-scale-CO-master.

cs.AI↗

arXiv2025

Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation

Recent advances in Large Language Models (LLMs) have demonstrated significant potential in the field of Recommendation Systems (RSs). Most existing studies have focused on converting user behavior logs into textual prompts and leveraging techniques such as prompt tuning to enable LLMs for recommendation tasks. Meanwhile, research interest has recently grown in multimodal recommendation systems that integrate data from images, text, and other sources using modality fusion techniques. This introduces new challenges to the existing LLM-based recommendation paradigm which relies solely on text modality information. Moreover, although Multimodal Large Language Models (MLLMs) capable of processing multi-modal inputs have emerged, how to equip MLLMs with multi-modal recommendation capabilities remains largely unexplored. To this end, in this paper, we propose the Multimodal Large Language Model-enhanced Multimodaln Sequential Recommendation (MLLM-MSR) model. To capture the dynamic user preference, we design a two-stage user preference summarization method. Specifically, we first utilize an MLLM-based item-summarizer to extract image feature given an item and convert the image into text. Then, we employ a recurrent user preference summarization generation paradigm to capture the dynamic changes in user preferences based on an LLM-based user-summarizer. Finally, to enable the MLLM for multi-modal recommendation task, we propose to fine-tune a MLLM-based recommender using Supervised Fine-Tuning (SFT) techniques. Extensive evaluations across various datasets validate the effectiveness of MLLM-MSR, showcasing its superior ability to capture and adapt to the evolving dynamics of user preferences.

cs.IR↗

arXiv2025

Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation

Large Language Models (LLMs) demonstrate remarkable capabilities, yet struggle with hallucination and outdated knowledge when tasked with complex knowledge reasoning, resulting in factually incorrect outputs. Previous studies have attempted to mitigate it by retrieving factual knowledge from large-scale knowledge graphs (KGs) to assist LLMs in logical reasoning and prediction of answers. However, this kind of approach often introduces noise and irrelevant data, especially in situations with extensive context from multiple knowledge aspects. In this way, LLM attention can be potentially mislead from question and relevant information. In our study, we introduce an Adaptive Multi-Aspect Retrieval-augmented over KGs (Amar) framework. This method retrieves knowledge including entities, relations, and subgraphs, and converts each piece of retrieved text into prompt embeddings. The Amar framework comprises two key sub-components: 1) a self-alignment module that aligns commonalities among entities, relations, and subgraphs to enhance retrieved text, thereby reducing noise interference; 2) a relevance gating module that employs a soft gate to learn the relevance score between question and multi-aspect retrieved data, to determine which information should be used to enhance LLMs' output, or even filtered altogether. Our method has achieved state-of-the-art performance on two common datasets, WebQSP and CWQ, showing a 1.9\% improvement in accuracy over its best competitor and a 6.6\% improvement in logical form generation over a method that directly uses retrieved text as context prompts. These results demonstrate the effectiveness of Amar in improving the reasoning of LLMs.

cs.CL↗

arXiv2024

CapsuleBot: A Novel Hybrid Aerial-Ground Bi-Copter Robot With Two Actuated-Wheel-Rotors

This paper presents the design, modeling, and experimental validation of CapsuleBot, a novel hybrid aerial-ground bi-copter robot designed for long-endurance and low-noise operations. CapsuleBot combines the maneuverability of a bi-copter in the air with the low power consumption and low noise of a two-wheel self-balancing robot on the ground. To achieve this, we design an innovative mechanical structure named the actuated-wheel-rotor, which uses a servo motor and a brushless motor to function as both a tilting rotor in the air and an actuated wheel on the ground. CapsuleBot is equipped with two actuated-wheel-rotors, enabling it to achieve hybrid aerial-ground propulsion using only four motors, with no additional motors required compared to a bi-copter. Additionally, we develop comprehensive dynamics and control systems for both air and wheel mode, based on the bi-copter model and the two-wheel self-balancing robot model. A prototype of CapsuleBot is constructed, and its performance in terms of low power consumption and low noise is validated through experiments. Challenging tasks demonstrate CapsuleBot's capability to climb steep, fly over cliffs, and traverse rough terrains.

cs.RO↗

arXiv2024

Densing Law of LLMs

Large Language Models (LLMs) have emerged as a milestone in artificial intelligence, and their performance can improve as the model size increases. However, this scaling brings great challenges to training and inference efficiency, particularly for deploying LLMs in resource-constrained environments, and the scaling trend is becoming increasingly unsustainable. This paper introduces the concept of ``\textit{capacity density}'' as a new metric to evaluate the quality of the LLMs across different scales and describes the trend of LLMs in terms of both effectiveness and efficiency. To calculate the capacity density of a given target LLM, we first introduce a set of reference models and develop a scaling law to predict the downstream performance of these reference models based on their parameter sizes. We then define the \textit{effective parameter size} of the target LLM as the parameter size required by a reference model to achieve equivalent performance, and formalize the capacity density as the ratio of the effective parameter size to the actual parameter size of the target LLM. Capacity density provides a unified framework for assessing both model effectiveness and efficiency. Our further analysis of recent open-source base LLMs reveals an empirical law (the densing law)that the capacity density of LLMs grows exponentially over time. More specifically, using some widely used benchmarks for evaluation, the capacity density of LLMs doubles approximately every three months. The law provides new perspectives to guide future LLM development, emphasizing the importance of improving capacity density to achieve optimal results with minimal computational overhead.

cs.AI↗

arXiv2024

CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention

Vehicle Routing Problems (VRPs) are significant Combinatorial Optimization (CO) problems holding substantial practical importance. Recently, Neural Combinatorial Optimization (NCO), which involves training deep learning models on extensive data to learn vehicle routing heuristics, has emerged as a promising approach due to its efficiency and the reduced need for manual algorithm design. However, applying NCO across diverse real-world scenarios with various constraints necessitates cross-problem capabilities. Current NCO methods typically employ a unified model lacking a constraint-specific structure, thereby restricting their cross-problem performance. Current multi-task methods for VRPs typically employ a constraint-unaware model, limiting their cross-problem performance. Furthermore, they rely solely on global connectivity, which fails to focus on key nodes and leads to inefficient representation learning. This paper introduces a Constraint-Aware Dual-Attention Model (CaDA), designed to address these limitations. CaDA incorporates a constraint prompt that efficiently represents different problem variants. Additionally, it features a dual-attention mechanism with a global branch for capturing broader graph-wide information and a sparse branch that selectively focuses on the most relevant nodes. We comprehensively evaluate our model on 16 different VRPs and compare its performance against existing cross-problem VRP solvers. CaDA achieves state-of-the-art results across all the VRPs. Our ablation study further confirms that each component of CaDA contributes positively to its cross-problem learning performance.

cs.AI↗

arXiv2024

Make Large Language Model a Better Ranker

Large Language Models (LLMs) demonstrate robust capabilities across various fields, leading to a paradigm shift in LLM-enhanced Recommender System (RS). Research to date focuses on point-wise and pair-wise recommendation paradigms, which are inefficient for LLM-based recommenders due to high computational costs. However, existing list-wise approaches also fall short in ranking tasks due to misalignment between ranking objectives and next-token prediction. Moreover, these LLM-based methods struggle to effectively address the order relation among candidates, particularly given the scale of ratings. To address these challenges, this paper introduces the large language model framework with Aligned Listwise Ranking Objectives (ALRO). ALRO is designed to bridge the gap between the capabilities of LLMs and the nuanced requirements of ranking tasks. Specifically, ALRO employs explicit feedback in a listwise manner by introducing soft lambda loss, a customized adaptation of lambda loss designed for optimizing order relations. This mechanism provides more accurate optimization goals, enhancing the ranking process. Additionally, ALRO incorporates a permutation-sensitive learning mechanism that addresses position bias, a prevalent issue in generative models, without imposing additional computational burdens during inference. Our evaluative studies reveal that ALRO outperforms both existing embedding-based recommendation methods and LLM-based recommendation baselines.

cs.IR↗

arXiv2024

MiniCPM-V: A GPT-4V Level MLLM on Your Phone

The recent surge of Multimodal Large Language Models (MLLMs) has fundamentally reshaped the landscape of AI research and industry, shedding light on a promising path toward the next AI milestone. However, significant challenges remain preventing MLLMs from being practical in real-world applications. The most notable challenge comes from the huge cost of running an MLLM with a massive number of parameters and extensive computation. As a result, most MLLMs need to be deployed on high-performing cloud servers, which greatly limits their application scopes such as mobile, offline, energy-sensitive, and privacy-protective scenarios. In this work, we present MiniCPM-V, a series of efficient MLLMs deployable on end-side devices. By integrating the latest MLLM techniques in architecture, pretraining and alignment, the latest MiniCPM-Llama3-V 2.5 has several notable features: (1) Strong performance, outperforming GPT-4V-1106, Gemini Pro and Claude 3 on OpenCompass, a comprehensive evaluation over 11 popular benchmarks, (2) strong OCR capability and 1.8M pixel high-resolution image perception at any aspect ratio, (3) trustworthy behavior with low hallucination rates, (4) multilingual support for 30+ languages, and (5) efficient deployment on mobile phones. More importantly, MiniCPM-V can be viewed as a representative example of a promising trend: The model sizes for achieving usable (e.g., GPT-4V) level performance are rapidly decreasing, along with the fast growth of end-side computation capacity. This jointly shows that GPT-4V level MLLMs deployed on end devices are becoming increasingly possible, unlocking a wider spectrum of real-world AI applications in the near future.

cs.CV↗

arXiv2024

Intention-Aware Planner for Robust and Safe Aerial Tracking

Autonomous target tracking with quadrotors has wide applications in many scenarios, such as cinematographic follow-up shooting or suspect chasing. Target motion prediction is necessary when designing the tracking planner. However, the widely used constant velocity or constant rotation assumption can not fully capture the dynamics of the target. The tracker may fail when the target happens to move aggressively, such as sudden turn or deceleration. In this paper, we propose an intention-aware planner by additionally considering the intention of the target to enhance safety and robustness in aerial tracking applications. Firstly, a designated intention prediction method is proposed, which combines a user-defined potential assessment function and a state observation function. A reachable region is generated to specifically evaluate the turning intentions. Then we design an intention-driven hybrid A* method to predict the future possible positions for the target. Finally, an intention-aware optimization approach is designed to generate a spatial-temporal optimal trajectory, allowing the tracker to perceive unexpected situations from the target. Benchmark comparisons and real-world experiments are conducted to validate the performance of our method.

cs.RO↗

arXiv2024

An Adaptive System for Wearable Devices to Detect Stress Using Physiological Signals

Timely stress detection is crucial for protecting vulnerable groups from long-term detrimental effects by enabling early intervention. Wearable devices, by collecting real-time physiological signals, offer a solution for accurate stress detection accommodating individual differences. This position paper introduces an adaptive framework for personalized stress detection using PPG and EDA signals. Unlike traditional methods that rely on a generalized model, which may suffer performance drops when applied to new users due to domain shifts, this framework aims to provide each user with a personalized model for higher stress detection accuracy. The framework involves three stages: developing a generalized model offline with an initial dataset, adapting the model to the user's unlabeled data, and fine-tuning it with a small set of labeled data obtained through user interaction. This approach not only offers a foundation for mobile applications that provide personalized stress detection and intervention but also has the potential to address a wider range of mental health issues beyond stress detection using physiological signals.

cs.CV↗