arXiv subjects

Ziyi Wang

Publications and source records attributed to Ziyi Wang.

At least 109 records · Page 6Linked to original sources

arXiv2025

CogniPair: From LLM Chatbots to Conscious AI Agents -- GNWT-Based Multi-Agent Digital Twins for Social Pairing -- Dating & Hiring Applications

Current large language model (LLM) agents lack authentic human psychological processes necessary for genuine digital twins and social AI applications. To address this limitation, we present a computational implementation of Global Workspace Theory (GNWT) that integrates human cognitive architecture principles into LLM agents, creating specialized sub-agents for emotion, memory, social norms, planning, and goal-tracking coordinated through a global workspace mechanism. However, authentic digital twins require accurate personality initialization. We therefore develop a novel adventure-based personality test that evaluates true personality through behavioral choices within interactive scenarios, bypassing self-presentation bias found in traditional assessments. Building on these innovations, our CogniPair platform enables digital twins to engage in realistic simulated dating interactions and job interviews before real encounters, providing bidirectional cultural fit assessment for both romantic compatibility and workplace matching. Validation using 551 GNWT-Agents and Columbia University Speed Dating dataset demonstrates 72% correlation with human attraction patterns, 77.8% match prediction accuracy, and 74% agreement in human validation studies. This work advances psychological authenticity in LLM agents and establishes a foundation for intelligent dating platforms and HR technology solutions.

cs.AI↗

arXiv2025

Mitigating Hallucinations in Large Language Models via Causal Reasoning

Large language models (LLMs) exhibit logically inconsistent hallucinations that appear coherent yet violate reasoning principles, with recent research suggesting an inverse relationship between causal reasoning capabilities and such hallucinations. However, existing reasoning approaches in LLMs, such as Chain-of-Thought (CoT) and its graph-based variants, operate at the linguistic token level rather than modeling the underlying causal relationships between variables, lacking the ability to represent conditional independencies or satisfy causal identification assumptions. To bridge this gap, we introduce causal-DAG construction and reasoning (CDCR-SFT), a supervised fine-tuning framework that trains LLMs to explicitly construct variable-level directed acyclic graph (DAG) and then perform reasoning over it. Moreover, we present a dataset comprising 25,368 samples (CausalDR), where each sample includes an input question, explicit causal DAG, graph-based reasoning trace, and validated answer. Experiments on four LLMs across eight tasks show that CDCR-SFT improves the causal reasoning capability with the state-of-the-art 95.33% accuracy on CLADDER (surpassing human performance of 94.8% for the first time) and reduces the hallucination on HaluEval with 10% improvements. It demonstrates that explicit causal structure modeling in LLMs can effectively mitigate logical inconsistencies in LLM outputs. Code is available at https://github.com/MrLYG/CDCR-SFT.

cs.CL↗

arXiv2025

Low-Field Ferroelectricity in 10 nm AlBScN Thin Films

Ferroelectric aluminum scandium nitride (Al1-xScxN, AlScN) offers CMOS-compatible integration but suffers from high coercive fields and leakage currents that hinder thickness scaling. Further reduction in thickness is essential for low-voltage embedded nonvolatile memory applications. Boron incorporation into AlScN (AlBScN) suppresses leakage current in films down to 40 nm, yet its ferroelectric characteristics in ultrathin films remains unexplored. This letter demonstrates robust ferroelectric switching in 10 nm sputtered AlBScN capacitors with a low coercive field and approximately two orders of magnitude lower leakage than AlScN. Notably, ferroelectric switching was observed at 2.2 MV/cm in capacitance-voltage measurements, and symmetric polarization reversal occurred near 4.6 MV/cm in positive-up-negative-down (PUND) measurements using 2 μs pulses. Moreover, Weibull analysis revealed a breakdown-to-coercive-field ratio (EBD/Ec) of ~2.2. These findings demonstrated AlBScN as a promising candidate for CMOS back-end-of-line (BEOL) compatible ferroelectric applications with improved energy consumption and reduced leakage current.

cond-mat.mtrl-sci↗

arXiv2025

Janus: Leveraging Incremental Computation for Efficient DNS Verification

Existing DNS configuration verification tools face significant issues (e.g., inefficient and lacking support for incremental verification). Inspired by the advancements in recent work of distributed data plane verification and the resemblance be- tween the data plane and DNS configuration, we tackle the challenge of DNS misconfiguration by introducing Janus, a DNS verification tool. Our key insight is that the process of a nameserver handling queries can be transformed into a matching process on a match-action table. With this insight, Janus consists of (1) an efficient data structure for partition query space based on the behaviors, (2) a symbolic execution algorithm that specifies how a single nameserver can efficiently cover all possible queries and ensure the accuracy of verification, (3) a mechanism to support incremental verification with less computational effort. Extensive experiments on real-world datasets (with over 6 million resource records) show that Janus achieves significant speedups, with peak improvements of up to 255.7x and a maximum 6046x reduction in the number of LECs.

cs.NI↗

arXiv2025

Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials

Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi-Head Self-Attention (MHSA) layer still performs a quadratic query-key interaction for every token pair, spending the bulk of computation on visually weak or redundant correlations. We introduce Visual-Contrast Attention (VCA), a drop-in replacement for MHSA that injects an explicit notion of discrimination while reducing the theoretical complexity from O(N N C) to O(N n C) with n << N. VCA first distils each head's dense query field into a handful of spatially pooled visual-contrast tokens, then splits them into a learnable positive and negative stream whose differential interaction highlights what truly separates one region from another. The module adds fewer than 0.3M parameters to a DeiT-Tiny backbone, requires no extra FLOPs, and is wholly architecture-agnostic. Empirically, VCA lifts DeiT-Tiny top-1 accuracy on ImageNet-1K from 72.2% to 75.6% (+3.4) and improves three strong hierarchical ViTs by up to 3.1%, while in class-conditional ImageNet generation it lowers FID-50K by 2.1 to 5.2 points across both diffusion (DiT) and flow (SiT) models. Extensive ablations confirm that (i) spatial pooling supplies low-variance global cues, (ii) dual positional embeddings are indispensable for contrastive reasoning, and (iii) combining the two in both stages yields the strongest synergy. VCA therefore offers a simple path towards faster and sharper Vision Transformers. The source code is available at https://github.com/LeapLabTHU/LinearDiff.

cs.CV↗

arXiv2025

Multi-Agent Reinforcement Learning for Market Making: Competition without Collusion

Algorithmic collusion has emerged as a central question in AI: Will the interaction between different AI agents deployed in markets lead to collusion? More generally, understanding how emergent behavior, be it a cartel or market dominance from more advanced bots, affects the market overall is an important research question. We propose a hierarchical multi-agent reinforcement learning framework to study algorithmic collusion in market making. The framework includes a self-interested market maker (Agent~A), which is trained in an uncertain environment shaped by an adversary, and three bottom-layer competitors: the self-interested Agent~B1 (whose objective is to maximize its own PnL), the competitive Agent~B2 (whose objective is to minimize the PnL of its opponent), and the hybrid Agent~B$^\star$, which can modulate between the behavior of the other two. To analyze how these agents shape the behavior of each other and affect market outcomes, we propose interaction-level metrics that quantify behavioral asymmetry and system-level dynamics, while providing signals potentially indicative of emergent interaction patterns. Experimental results show that Agent~B2 secures dominant performance in a zero-sum setting against B1, aggressively capturing order flow while tightening average spreads, thus improving market execution efficiency. In contrast, Agent~B$^\star$ exhibits a self-interested inclination when co-existing with other profit-seeking agents, securing dominant market share through adaptive quoting, yet exerting a milder adverse impact on the rewards of Agents~A and B1 compared to B2. These findings suggest that adaptive incentive control supports more sustainable strategic co-existence in heterogeneous agent environments and offers a structured lens for evaluating behavioral design in algorithmic trading systems.

cs.MA↗

arXiv2025

Interior Hessian estimates for sum Hessian quotient equation

This paper is devoted to the interior $C^2$ estimates for a class of sum Hessian quotient equations. For $0\leq l<k<n$, we establish the interior estimates and the Pogorelov type estimates. In the case $k=n$, we obtain a weaker Pogorelov type estimate for $0\leq l<n-1$.

math.AP↗

arXiv2025

Hierarchical Dual-Head Model for Suicide Risk Assessment via MentalRoBERTa

Social media platforms have become important sources for identifying suicide risk, but automated detection systems face multiple challenges including severe class imbalance, temporal complexity in posting patterns, and the dual nature of risk levels as both ordinal and categorical. This paper proposes a hierarchical dual-head neural network based on MentalRoBERTa for suicide risk classification into four levels: indicator, ideation, behavior, and attempt. The model employs two complementary prediction heads operating on a shared sequence representation: a CORAL (Consistent Rank Logits) head that preserves ordinal relationships between risk levels, and a standard classification head that enables flexible categorical distinctions. A 3-layer Transformer encoder with 8-head multi-head attention models temporal dependencies across post sequences, while explicit time interval embeddings capture posting behavior dynamics. The model is trained with a combined loss function (0.5 CORAL + 0.3 Cross-Entropy + 0.2 Focal Loss) that simultaneously addresses ordinal structure preservation, overconfidence reduction, and class imbalance. To improve computational efficiency, we freeze the first 6 layers (50%) of MentalRoBERTa and employ mixed-precision training. The model is evaluated using 5-fold stratified cross-validation with macro F1 score as the primary metric.

cs.LG↗

arXiv2025

See, Think, Act: Online Shopper Behavior Simulation with VLM Agents

LLMs have recently demonstrated strong potential in simulating online shopper behavior. Prior work has improved action prediction by applying SFT on action traces with LLM-generated rationales, and by leveraging RL to further enhance reasoning capabilities. Despite these advances, current approaches rely on text-based inputs and overlook the essential role of visual perception in shaping human decision-making during web GUI interactions. In this paper, we investigate the integration of visual information, specifically webpage screenshots, into behavior simulation via VLMs, leveraging OPeRA dataset. By grounding agent decision-making in both textual and visual modalities, we aim to narrow the gap between synthetic agents and real-world users, thereby enabling more cognitively aligned simulations of online shopping behavior. Specifically, we employ SFT for joint action prediction and rationale generation, conditioning on the full interaction context, which comprises action history, past HTML observations, and the current webpage screenshot. To further enhance reasoning capabilities, we integrate RL with a hierarchical reward structure, scaled by a difficulty-aware factor that prioritizes challenging decision points. Empirically, our studies show that incorporating visual grounding yields substantial gains: the combination of text and image inputs improves exact match accuracy by more than 6% over text-only inputs. These results indicate that multi-modal grounding not only boosts predictive accuracy but also enhances simulation fidelity in visually complex environments, which captures nuances of human attention and decision-making that text-only agents often miss. Finally, we revisit the design space of behavior simulation frameworks, identify key methodological limitations, and propose future research directions toward building efficient and effective human behavior simulators.

cs.CY↗

arXiv2025

LLM Safety Alignment is Divergence Estimation in Disguise

We present a theoretical framework showing that popular LLM alignment methods, including RLHF and its variants, can be understood as divergence estimators between aligned (safe or preferred) and unaligned (harmful or less preferred) distributions. This perspective explains the emergence of separation in the latent space between safe and harmful prompts after alignment. As an application of our general divergence framework, we propose KLDO, a novel KL divergence-based alignment method, and empirically validate its effectiveness. We further show that using compliance-refusal datasets, rather than standard preference-based datasets, leads to stronger separation and improved safety alignment. Finally, to quantify the separation effect, we propose a distance-based metric in the prompt representation space, which also acts as a statistically significant indicator for model safety.

cs.LG↗

arXiv2025

Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shopping

Simulating step-wise human behavior with Large Language Models (LLMs) has become an emerging research direction, enabling applications in various practical domains. While prior methods, including prompting, supervised fine-tuning (SFT), and reinforcement learning (RL), have shown promise in modeling step-wise behavior, they primarily learn a population-level policy without conditioning on a user's persona, yielding generic rather than personalized simulations. In this work, we pose a critical question: how can LLM agents better simulate personalized user behavior? We introduce Customer-R1, an RL-based method for personalized, step-wise user behavior simulation in online shopping environments. Our policy is conditioned on an explicit persona, and we optimize next-step rationale and action generation via action correctness reward signals. Experiments on the OPeRA dataset emonstrate that Customer-R1 not only significantly outperforms prompting and SFT-based baselines in next-action prediction tasks, but also better matches users' action distribution, indicating higher fidelity in personalized behavior simulation.

cs.CL↗

arXiv2025

TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning

Process Reward Models (PRMs) have recently emerged as a powerful framework for enhancing the reasoning capabilities of large reasoning models (LRMs), particularly in the context of test-time scaling (TTS). However, their potential for supervising LRMs on tabular reasoning domains remains underexplored. Through detailed empirical analyses, we identify that existing PRMs, though widely adopted for supervising text-only reasoning steps, struggle with table-specific operations such as sub-table retrieval and schema interaction, leading to critical performance bottlenecks. To address this limitation, we propose TaTToo, a novel table-grounded PRM framework that (i) reasons explicitly over tabular reasoning steps and (ii) integrates tool-based verification to provide precise reward supervision. Concretely, we first design a scalable data curation pipeline that constructs over 60k high-quality step-level annotations by integrating table verification rationales with tool-based executions. Building on the collected data, we train TaTToo with a dual-stage paradigm: cold-start supervised fine-tuning to capture tool-use reasoning patterns, followed by reinforcement learning with tool-grounded reward shaping to align our model with table-based verification. We provide a comprehensive evaluation of the policy improvement induced by our newly designed PRM. Across 5 challenging tabular reasoning benchmarks covering numerical reasoning, fact-checking, and data analysis, TaTToo improves downstream policy LRMs by 30.9% at inference, surpasses strong PRM baselines such as Qwen-2.5-Math-PRM-72B with only 8B parameters, and demonstrates strong generalizability across diverse TTS strategies.

cs.AI↗

arXiv2025

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs

Chain-of-Thought (CoT) prompting has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing implementations, such as in-context learning and fine-tuning, remain costly and inefficient. To improve CoT reasoning at a lower cost, and inspired by the task vector paradigm, we introduce CoT Vectors, compact representations that encode task-general, multi-step reasoning knowledge. Through experiments with Extracted CoT Vectors, we observe pronounced layer-wise instability, manifesting as a U-shaped performance curve that reflects a systematic three-stage reasoning process in LLMs. To address this limitation, we propose Learnable CoT Vectors, optimized under a teacher-student framework to provide more stable and robust guidance. Extensive evaluations across diverse benchmarks and models demonstrate that CoT Vectors not only outperform existing baselines but also achieve performance comparable to parameter-efficient fine-tuning methods, while requiring fewer trainable parameters. Moreover, by treating CoT Vectors as a probe, we uncover how their effectiveness varies due to latent space structure, information density, acquisition mechanisms, and pre-training differences, offering new insights into the functional organization of multi-step reasoning in LLMs. The source code will be released.

cs.CL↗

arXiv2025

PhysicsMinions: Winning Gold Medals in the Latest Physics Olympiads with a Coevolutionary Multimodal Multi-Agent System

Physics is central to understanding and shaping the real world, and the ability to solve physics problems is a key indicator of real-world physical intelligence. Physics Olympiads, renowned as the crown of competitive physics, provide a rigorous testbed requiring complex reasoning and deep multimodal understanding, yet they remain largely underexplored in AI research. Existing approaches are predominantly single-model based, and open-source MLLMs rarely reach gold-medal-level performance. To address this gap, we propose PhysicsMinions, a coevolutionary multi-agent system for Physics Olympiad. Its architecture features three synergistic studios: a Visual Studio to interpret diagrams, a Logic Studio to formulate solutions, and a Review Studio to perform dual-stage verification. The system coevolves through an iterative refinement loop where feedback from the Review Studio continuously guides the Logic Studio, enabling the system to self-correct and converge towards the ground truth. Evaluated on the HiPhO benchmark spanning 7 latest physics Olympiads, PhysicsMinions delivers three major breakthroughs: (i) Strong generalization: it consistently improves both open-source and closed-source models of different sizes, delivering clear benefits over their single-model baselines; (ii) Historic breakthroughs: it elevates open-source models from only 1-2 to 6 gold medals across 7 Olympiads, achieving the first-ever open-source gold medal in the latest International Physics Olympiad (IPhO) under the average-score metric; and (iii) Scaling to human expert: it further advances the open-source Pass@32 score to 26.8/30 points on the latest IPhO, ranking 4th of 406 contestants and far surpassing the top single-model score of 22.7 (ranked 22nd). Generally, PhysicsMinions offers a generalizable framework for Olympiad-level problem solving, with the potential to extend across disciplines.

cs.AI↗

arXiv2025

Neural Integrated Sensing and Communication for the MIMO-OFDM Downlink

The ongoing convergence of spectrum and hardware requirements for wireless sensing and communication applications has fueled the integrated sensing and communication (ISAC) paradigm in next-generation networks. Neural-network-based ISAC leverages data-driven learning techniques to add sensing capabilities to existing communication infrastructure. This paper presents a novel signal-processing framework for such neural ISAC systems based on the multiple-input multiple-output (MIMO) and orthogonal frequency-division multiplexing (OFDM) downlink. Our approach enables generalized sensing functionality without modifying the MIMO-OFDM communication link. Specifically, our neural ISAC pipeline measures the backscattered communication signals to generate discrete map representations of spatial occupancy, formulated as multiclass or multilabel classification problems, which can then be utilized by specialized downstream tasks. To improve sensing performance in closed or cluttered environments, our neural ISAC pipeline relies on features specifically designed to mitigate strong reflective paths. Extensive simulations using ray-tracing models demonstrate that our neural ISAC framework reliably reconstructs scene maps without altering the MIMO-OFDM communication pipeline or reducing data rates.

eess.SP↗

arXiv2025

SymBridge: A Human-in-the-Loop Cyber-Physical Interactive System for Adaptive Human-Robot Symbiosis

The development of intelligent robots seeks to seamlessly integrate them into the human world, providing assistance and companionship in daily life and work, with the ultimate goal of achieving human-robot symbiosis. This requires robots with intelligent interaction abilities to work naturally and effectively with humans. However, current robotic simulators fail to support real human participation, limiting their ability to provide authentic interaction experiences and gather valuable human feedback essential for enhancing robotic capabilities. In this paper, we introduce SymBridge, the first human-in-the-loop cyber-physical interactive system designed to enable the safe and efficient development, evaluation, and optimization of human-robot interaction methods. Specifically, we employ augmented reality technology to enable real humans to interact with virtual robots in physical environments, creating an authentic interactive experience. Building on this, we propose a novel robotic interaction model that generates responsive, precise robot actions in real time through continuous human behavior observation. The model incorporates multi-resolution human motion features and environmental affordances, ensuring contextually adaptive robotic responses. Additionally, SymBridge enables continuous robot learning by collecting human feedback and dynamically adapting the robotic interaction model. By leveraging a carefully designed system architecture and modules, SymBridge builds a bridge between humans and robots, as well as between cyber and physical spaces, providing a natural and realistic online interaction experience while facilitating the continuous evolution of robotic intelligence. Extensive experiments, user studies, and real robot testing demonstrate the promising performance of the system and highlight its potential to significantly advance research on human-robot symbiosis.

cs.RO↗

arXiv2025

UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling

Point cloud videos capture dynamic 3D motion while reducing the effects of lighting and viewpoint variations, making them highly effective for recognizing subtle and continuous human actions. Although Selective State Space Models (SSMs) have shown good performance in sequence modeling with linear complexity, the spatio-temporal disorder of point cloud videos hinders their unidirectional modeling when directly unfolding the point cloud video into a 1D sequence through temporally sequential scanning. To address this challenge, we propose the Unified Spatio-Temporal State Space Model (UST-SSM), which extends the latest advancements in SSMs to point cloud videos. Specifically, we introduce Spatial-Temporal Selection Scanning (STSS), which reorganizes unordered points into semantic-aware sequences through prompt-guided clustering, thereby enabling the effective utilization of points that are spatially and temporally distant yet similar within the sequence. For missing 4D geometric and motion details, Spatio-Temporal Structure Aggregation (STSA) aggregates spatio-temporal features and compensates. To improve temporal interaction within the sampled sequence, Temporal Interaction Sampling (TIS) enhances fine-grained temporal dependencies through non-anchor frame utilization and expanded receptive fields. Experimental results on the MSR-Action3D, NTU RGB+D, and Synthia 4D datasets validate the effectiveness of our method. Our code is available at https://github.com/wangzy01/UST-SSM.

cs.CV↗

arXiv2025

Jahn-Teller-like Distortion in a One-dimensional π-Conjugated Polymer

Structurally distorting low-dimensional π-conjugated systems can profoundly influence their electronic properties, but controlling such behavior in extended-width systems remains challenging. Here we demonstrate that a one-dimensional conjugated polymer, poly-(difluorenoheptalene-ethynylene) (PDFHE), undergoes a pronounced out-of-plane backbone distortion, equivalent to a spontaneous symmetry breaking (SSB) of its mirror symmetry. We synthesized PDFHE on noble metal surfaces and characterized its structure and electronic states using low-temperature scanning tunneling microscopy. Rather than adopting a planar, high-symmetry conformation, PDFHE relaxes into non-planar isomers stabilized by a Jahn-Teller-like mechanism that relieves an electronic instability relative to the gapped planar structure. Density functional theory calculations corroborate these findings, revealing that distortion lowers the total polymer energy and enlarges the bandgap, providing a microscopic explanation for the SSB. Our results show that even in mechanically robust extended π-systems, subtle electron-lattice coupling can spontaneously drive significant structural rearrangements.

cond-mat.mes-hall↗