arXiv subjects

Liang He

Publications and source records attributed to Liang He.

At least 145 records · Page 8Linked to original sources

arXiv2025

Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback

This paper introduces an interactive continual learning paradigm where AI models dynamically learn new skills from real-time human feedback while retaining prior knowledge. This paradigm distinctively addresses two major limitations of traditional continual learning: (1) dynamic model updates using streaming, real-time human-annotated data, rather than static datasets with fixed labels, and (2) the assumption of clean labels, by explicitly handling the noisy feedback common in real-world interactions. To tackle these problems, we propose RiCL, a Reinforced interactive Continual Learning framework leveraging Large Language Models (LLMs) to learn new skills effectively from dynamic feedback. RiCL incorporates three key components: a temporal consistency-aware purifier to automatically discern clean from noisy samples in data streams; an interaction-aware direct preference optimization strategy to align model behavior with human intent by reconciling AI-generated and human-provided feedback; and a noise-resistant contrastive learning module that captures robust representations by exploiting inherent data relationships, thus avoiding reliance on potentially unreliable labels. Extensive experiments on two benchmark datasets (FewRel and TACRED), contaminated with realistic noise patterns, demonstrate that our RiCL approach substantially outperforms existing combinations of state-of-the-art online continual learning and noisy-label learning methods.

cs.LG↗

arXiv2025

Task-Core Memory Management and Consolidation for Long-term Continual Learning

In this paper, we focus on a long-term continual learning (CL) task, where a model learns sequentially from a stream of vast tasks over time, acquiring new knowledge while retaining previously learned information in a manner akin to human learning. Unlike traditional CL settings, long-term CL involves handling a significantly larger number of tasks, which exacerbates the issue of catastrophic forgetting. Our work seeks to address two critical questions: 1) How do existing CL methods perform in the context of long-term CL? and 2) How can we mitigate the catastrophic forgetting that arises from prolonged sequential updates? To tackle these challenges, we propose a novel framework inspired by human memory mechanisms for long-term continual learning (Long-CL). Specifically, we introduce a task-core memory management strategy to efficiently index crucial memories and adaptively update them as learning progresses. Additionally, we develop a long-term memory consolidation mechanism that selectively retains hard and discriminative samples, ensuring robust knowledge retention. To facilitate research in this area, we construct and release two multi-modal and textual benchmarks, MMLongCL-Bench and TextLongCL-Bench, providing a valuable resource for evaluating long-term CL approaches. Experimental results show that Long-CL outperforms the previous state-of-the-art by 7.4\% and 6.5\% AP on the two benchmarks, respectively, demonstrating the effectiveness of our approach.

cs.LG↗

arXiv2025

A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law

This survey explores recent advancements in reasoning large language models (LLMs) designed to mimic "slow thinking" - a reasoning process inspired by human cognition, as described in Kahneman's Thinking, Fast and Slow. These models, like OpenAI's o1, focus on scaling computational resources dynamically during complex tasks, such as math reasoning, visual reasoning, medical diagnosis, and multi-agent debates. We present the development of reasoning LLMs and list their key technologies. By synthesizing over 100 studies, it charts a path toward LLMs that combine human-like deep thinking with scalable efficiency for reasoning. The review breaks down methods into three categories: (1) test-time scaling dynamically adjusts computation based on task complexity via search and sampling, dynamic verification; (2) reinforced learning refines decision-making through iterative improvement leveraging policy networks, reward models, and self-evolution strategies; and (3) slow-thinking frameworks (e.g., long CoT, hierarchical processes) that structure problem-solving with manageable steps. The survey highlights the challenges and further directions of this domain. Understanding and advancing the reasoning abilities of LLMs is crucial for unlocking their full potential in real-world applications, from scientific discovery to decision support systems.

cs.AI↗

arXiv2025

Barrier induced stalemate-consensus transition of self-propelled participants subject to majority rule

Natural or artificial barriers, such as the Himalayas, the Berlin Wall, or the Korean Demilitarized Zone, can significantly impede human migration. As a consequence, they may also hinder the dissemination of opinions within society, thereby contributing to divergent geopolitical landscapes and cultural developments. This raises a fundamental question: how do such barriers influence the opinion dynamics of mobile agents, such as human beings? In particular, can a barrier induce transitions in collective opinion states among spatially segregated groups? Here, we investigate the opinion dynamics governed by majority rule in a minimal model comprising self-propelled agents with binary opinions performing random walks within a closed space divided by a barrier. We focus on the conditions under which initially segregated clusters of agents with opposing opinions can reach consensus. Our results reveal the existence of a critical barrier size that marks a transition between stalemate and consensus states. Near this critical point, the relaxation time to reach consensus from an initial stalemate exhibits a power-law divergence. This barrier-induced stalemate-consensus transition in a simple agent-based model offers new insights into the role of physical or social barriers in shaping opinion dynamics and social structures.

physics.soc-ph↗

arXiv2025

SOPTX: A High-Performance Multi-Backend Framework for Topology Optimization

In recent years, topology optimization (TO) has gained widespread attention as a powerful structural design method. However, its application remains challenging due to the deep expertise and extensive development effort required. Traditional TO methods, tightly coupled with computational mechanics like finite element method (FEM), result in intrusive algorithms demanding a comprehensive system understanding. This paper presents SOPTX, a TO package based on FEALPy, which implements a modular architecture that decouples analysis from optimization, supports multiple computational backends (NumPy, PyTorch, JAX), and achieves a non-intrusive design paradigm. Core innovations include: (1) cross-platform design that supports multiple computational backends, enabling efficient algorithm execution on central processing units (CPUs) and flexible acceleration using graphics processing units (GPUs), while leveraging automatic differentiation (AD) technology for efficient sensitivity computation of objective and constraint functions; (2) fast matrix assembly techniques that overcome the performance bottlenecks of traditional numerical integration methods, significantly accelerating finite element computations and enhancing overall efficiency; (3) a modular framework supporting TO problems for arbitrary dimensions and meshes, allowing flexible configuration and extensibility of optimization workflows through a rich library of composable components. Using the density-based method for the classic compliance minimization problem with volume constraints as an example, numerical experiments demonstrate SOPTX's high efficiency in computational speed and memory usage, while showcasing its strong potential for research and engineering applications.

math.AP↗

arXiv2025

Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis

Multimodal aspect-based sentiment classification (MASC) is an emerging task due to an increase in user-generated multimodal content on social platforms, aimed at predicting sentiment polarity toward specific aspect targets (i.e., entities or attributes explicitly mentioned in text-image pairs). Despite extensive efforts and significant achievements in existing MASC, substantial gaps remain in understanding fine-grained visual content and the cognitive rationales derived from semantic content and impressions (cognitive interpretations of emotions evoked by image content). In this study, we present Chimera: a cognitive and aesthetic sentiment causality understanding framework to derive fine-grained holistic features of aspects and infer the fundamental drivers of sentiment expression from both semantic perspectives and affective-cognitive resonance (the synergistic effect between emotional responses and cognitive interpretations). Specifically, this framework first incorporates visual patch features for patch-word alignment. Meanwhile, it extracts coarse-grained visual features (e.g., overall image representation) and fine-grained visual regions (e.g., aspect-related regions) and translates them into corresponding textual descriptions (e.g., facial, aesthetic). Finally, we leverage the sentimental causes and impressions generated by a large language model (LLM) to enhance the model's awareness of sentimental cues evoked by semantic content and affective-cognitive resonance. Experimental results on standard MASC datasets demonstrate the effectiveness of the proposed model, which also exhibits greater flexibility to MASC compared to LLMs such as GPT-4o. We have publicly released the complete implementation and dataset at https://github.com/Xillv/Chimera

cs.CL↗

arXiv2025

Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection

Large Language Models (LLMs) are prone to hallucination with non-factual or unfaithful statements, which undermines the applications in real-world scenarios. Recent researches focus on uncertainty-based hallucination detection, which utilizes the output probability of LLMs for uncertainty calculation and does not rely on external knowledge or frequent sampling from LLMs. Whereas, most approaches merely consider the uncertainty of each independent token, while the intricate semantic relations among tokens and sentences are not well studied, which limits the detection of hallucination that spans over multiple tokens and sentences in the passage. In this paper, we propose a method to enhance uncertainty modeling with semantic graph for hallucination detection. Specifically, we first construct a semantic graph that well captures the relations among entity tokens and sentences. Then, we incorporate the relations between two entities for uncertainty propagation to enhance sentence-level hallucination detection. Given that hallucination occurs due to the conflict between sentences, we further present a graph-based uncertainty calibration method that integrates the contradiction probability of the sentence with its neighbors in the semantic graph for uncertainty calculation. Extensive experiments on two datasets show the great advantages of our proposed approach. In particular, we obtain substantial improvements with 19.78% in passage-level hallucination detection.

cs.CL↗

arXiv2025

Emergent non-Hermitian conservation laws at exceptional points

Non-Hermitian systems can manifest rich static and dynamical properties at their exceptional points (EPs). Here, we identify yet another class of distinct phenomena that is hinged on EPs, namely, the emergence of a series of non-Hermitian conservation laws. We demonstrate these distinct phenomena concretely in the non-Hermitian Heisenberg chain and formulate a general theory for identifying these emergent non-Hermitian conservation laws at EPs. By establishing a one-to-one correspondence between the constant of motions at EPs and those in corresponding auxiliary Hermitian systems, we trace their physical origin back to the presence of emergent symmetries in the auxiliary systems. Concrete simulations on quantum circuits show that these emergent conserved dynamics can be readily observed in current digital quantum computing systems.

quant-ph↗

arXiv2025

Rethinking Technological Solutions for Community-Based Older Adult Care: Insights from 'Older Partners' in China

Aging in place refers to the enabling of individuals to age comfortably and securely within their own homes and communities. Aging in place relies on robust infrastructure, prompting the development and implementation of both human-led care services and information and communication technologies to provide support. Through a long-term ethnographic study that includes semi-structured interviews with 24 stakeholders, we consider these human- and technology-driven care infrastructures for aging in place, examining their origins, deployment, interactions with older adults, and challenges. In doing so, we reconsider the value of these different forms of older adult care, highlighting the various issues associated with using, for instance, health monitoring technology or appointment scheduling systems to care for older adults aging in place. We suggest that technology should take a supportive, not substitutive role in older adult care infrastructure. Furthermore, we note that designing for aging in place should move beyond a narrow focus on independence in one's home to instead encompass the broader community and its dynamics.

cs.HC↗

arXiv2025

Characterizing LLM-Empowered Personalized Story-Reading and Interaction for Children: Insights from Multi-Stakeholder Perspectives

Personalized interaction is highly valued by parents in their story-reading activities with children. While AI-empowered story-reading tools have been increasingly used, their abilities to support personalized interaction with children are still limited. Recent advances in large language models (LLMs) show promise in facilitating personalized interactions, but little is known about how to effectively and appropriately use LLMs to enhance children's personalized story-reading experiences. This work explores this question through a design-based study. Drawing on a formative study, we designed and developed StoryMate, an LLM-empowered personalized interactive story-reading tool for children, following an empirical study with children, parents, and education experts. Our participants valued the personalized features in StoryMate, and also highlighted the need to support personalized content, guiding mechanisms, reading context variations, and interactive interfaces. Based on these findings, we propose a series of design recommendations for better using LLMs to empower children's personalized story reading and interaction.

cs.HC↗

arXiv2025

Teaching LLMs for Step-Level Automatic Math Correction via Reinforcement Learning

Automatic math correction aims to check students' solutions to mathematical problems via artificial intelligence technologies. Most existing studies focus on judging the final answer at the problem level, while they ignore detailed feedback on each step in a math problem-solving process, which requires abilities of semantic understanding and reasoning. In this paper, we propose a reinforcement learning (RL)-based method to boost large language model (LLM) for step-level automatic math correction, named StepAMC. Particularly, we convert the step-level automatic math correction within the text classification task into an RL problem to enhance the reasoning capabilities of LLMs. Then, we design a space-constrained policy network to improve the stability of RL. Then, we introduce a fine-grained reward network to convert the binary human feedback into a continuous value. We conduct extensive experiments over two benchmark datasets and the results show that our model outperforms the eleven strong baselines.

cs.CL↗

arXiv2025

Code-Driven Inductive Synthesis: Enhancing Reasoning Abilities of Large Language Models with Sequences

Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive reasoning, is not well studied. We attribute the reason to the fact that obtaining high-quality process supervision data is challenging for inductive reasoning. Towards this end, we novelly employ number sequences as the source of inductive reasoning data. We package sequences into algorithmic problems to find the general term of each sequence through a code solution. In this way, we can verify whether the code solution holds for any term in the current sequence, and inject case-based supervision signals by using code unit tests. We build a sequence synthetic data pipeline and form a training dataset CodeSeq. Experimental results show that the models tuned with CodeSeq improve on both code and comprehensive reasoning benchmarks.

cs.CL↗

arXiv2025

Human Simulacra: Benchmarking the Personification of Large Language Models

Large language models (LLMs) are recognized as systems that closely mimic aspects of human intelligence. This capability has attracted attention from the social science community, who see the potential in leveraging LLMs to replace human participants in experiments, thereby reducing research costs and complexity. In this paper, we introduce a framework for large language models personification, including a strategy for constructing virtual characters' life stories from the ground up, a Multi-Agent Cognitive Mechanism capable of simulating human cognitive processes, and a psychology-guided evaluation method to assess human simulations from both self and observational perspectives. Experimental results demonstrate that our constructed simulacra can produce personified responses that align with their target characters. Our work is a preliminary exploration which offers great potential in practical applications. All the code and datasets will be released, with the hope of inspiring further investigations. Our code and dataset are available at: https://github.com/hasakiXie123/Human-Simulacra.

cs.CY↗

arXiv2025

CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering

Multimodal large language models (MLLMs) have garnered widespread attention from researchers due to their remarkable understanding and generation capabilities in visual language tasks (e.g., visual question answering). However, the rapid pace of knowledge updates in the real world makes offline training of MLLMs costly, and when faced with non-stationary data streams, MLLMs suffer from catastrophic forgetting during learning. In this paper, we propose an MLLMs-based dual momentum Mixture-of-Experts (CL-MoE) framework for continual visual question answering (VQA). We integrate MLLMs with continual learning to utilize the rich commonsense knowledge in LLMs. We introduce a Dual-Router MoE (RMoE) strategy to select the global and local experts using task-level and instance-level routers, to robustly assign weights to the experts most appropriate for the task. Then, we design a dynamic Momentum MoE (MMoE) to update the parameters of experts dynamically based on the relationships between the experts and tasks/instances, so that the model can absorb new knowledge while maintaining existing knowledge. The extensive experimental results indicate that our method achieves state-of-the-art performance on 10 VQA tasks, proving the effectiveness of our approach.

cs.CV↗

arXiv2025

Stretchable Capacitive and Resistive Strain Sensors: Accessible Manufacturing Using Direct Ink Writing

As robotics advances toward integrating soft structures, anthropomorphic shapes, and complex tasks, soft and highly stretchable mechanotransducers are becoming essential. To reliably measure tactile and proprioceptive data while ensuring shape conformability, stretchability, and adaptability, researchers have explored diverse transduction principles alongside scalable and versatile manufacturing techniques. Nonetheless, many current methods for stretchable sensors are designed to produce a single sensor configuration, thereby limiting design flexibility. Here, we present an accessible, flexible, printing-based fabrication approach for customizable, stretchable sensors. Our method employs a custom-built printhead integrated with a commercial 3D printer to enable direct ink writing (DIW) of conductive ink onto cured silicone substrates. A layer-wise fabrication process, facilitated by stackable trays, allows for the deposition of multiple liquid conductive ink layers within a silicone matrix. To demonstrate the method's capacity for high design flexibility, we fabricate and evaluate both capacitive and resistive strain sensor morphologies. Experimental characterization showed that the capacitive strain sensor possesses high linearity (R^2 = 0.99), high sensitivity near the 1.0 theoretical limit (GF = 0.95), minimal hysteresis (DH = 1.36%), and large stretchability (550%), comparable to state-of-the-art stretchable strain sensors reported in the literature.

cs.RO↗

arXiv2025

LLM-KT: Aligning Large Language Models with Knowledge Tracing using a Plug-and-Play Instruction

The knowledge tracing (KT) problem is an extremely important topic in personalized education, which aims to predict whether students can correctly answer the next question based on their past question-answer records. Prior work on this task mainly focused on learning the sequence of behaviors based on the IDs or textual information. However, these studies usually fail to capture students' sufficient behavioral patterns without reasoning with rich world knowledge about questions. In this paper, we propose a large language models (LLMs)-based framework for KT, named \texttt{\textbf{LLM-KT}}, to integrate the strengths of LLMs and traditional sequence interaction models. For task-level alignment, we design Plug-and-Play instruction to align LLMs with KT, leveraging LLMs' rich knowledge and powerful reasoning capacity. For modality-level alignment, we design the plug-in context and sequence to integrate multiple modalities learned by traditional methods. To capture the long context of history records, we present a plug-in context to flexibly insert the compressed context embedding into LLMs using question-specific and concept-specific tokens. Furthermore, we introduce a plug-in sequence to enhance LLMs with sequence interaction behavior representation learned by traditional sequence models using a sequence adapter. Extensive experiments show that \texttt{\textbf{LLM-KT}} obtains state-of-the-art performance on four typical datasets by comparing it with approximately 20 strong baselines.

cs.CL↗

arXiv2025

Designing Kresling Origami for Personalised Wrist Orthosis

The wrist plays a pivotal role in facilitating motion dexterity and hand functions. Wrist orthoses, from passive braces to active exoskeletons, provide an effective solution for the assistance and rehabilitation of motor abilities. However, the type of motions facilitated by currently available orthoses is limited, with little emphasis on personalised design. To address these gaps, this paper proposes a novel wrist orthosis design inspired by the Kresling origami. The design can be adapted to accommodate various individual shape parameters, which benefits from the topological variations and intrinsic compliance of origami. Heat-sealable fabrics are used to replicate the non-rigid nature of the Kresling origami. The orthosis is capable of six distinct motion modes with a detachable tendon-based actuation system. Experimental characterisation of the workspace has been conducted by activating tendons individually. The maximum bending angle in each direction ranges from 18.81° to 32.63°. When tendons are pulled in combination, the maximum bending angles in the dorsal, palmar, radial, and ulnar directions are 31.66°, 30.38°, 27.14°, and 14.92°, respectively. The capability to generate complex motions such as the dart-throwing motion and circumduction has also been experimentally validated. The work presents a promising foundation for the development of personalised wrist orthoses for training and rehabilitation.

cs.RO↗

arXiv2025

Disentangled Modeling of Preferences and Social Influence for Group Recommendation

The group recommendation (GR) aims to suggest items for a group of users in social networks. Existing work typically considers individual preferences as the sole factor in aggregating group preferences. Actually, social influence is also an important factor in modeling users' contributions to the final group decision. However, existing methods either neglect the social influence of individual members or bundle preferences and social influence together as a unified representation. As a result, these models emphasize the preferences of the majority within the group rather than the actual interaction items, which we refer to as the preference bias issue in GR. Moreover, the self-supervised learning (SSL) strategies they designed to address the issue of group data sparsity fail to account for users' contextual social weights when regulating group representations, leading to suboptimal results. To tackle these issues, we propose a novel model based on Disentangled Modeling of Preferences and Social Influence for Group Recommendation (DisRec). Concretely, we first design a user-level disentangling network to disentangle the preferences and social influence of group members with separate embedding propagation schemes based on (hyper)graph convolution networks. We then introduce a socialbased contrastive learning strategy, selectively excluding user nodes based on their social importance to enhance group representations and alleviate the group-level data sparsity issue. The experimental results demonstrate that our model significantly outperforms state-of-the-art methods on two realworld datasets.

cs.IR↗