arXiv subjects

Yuansheng Gao

Publications and source records attributed to Yuansheng Gao.

8 recordsLinked to original sources

arXiv2026

Random Walk on Bézier Curves for Global Optimization

Balancing exploration and exploitation remains a central challenge in metaheuristic optimization. To address this issue, this paper proposes Bézier Walk Evolution (BWE), a geometry-driven optimization framework that reformulates evolutionary search as adaptive trajectory construction in the decision space. BWE integrates Bézier curve modeling with a distance-aware random walk mechanism to generate topology-guided search trajectories. By adaptively varying the curve order during evolution, the proposed method enables a smooth transition from diversified global exploration to refined local exploitation. Higher-order Bézier curves leverage multiple population-derived control points to enhance search diversity, while lower-order curves generate near-linear trajectories to improve convergence efficiency. This adaptive geometric search mechanism provides an interpretable alternative to conventional nature-inspired designs. Extensive experiments on 41 benchmark functions from the CEC2017 and CEC2022 suites, spanning dimensions from 10 to 100, show that BWE achieves strong overall performance and favorable scalability compared with 7 classical and 6 state-of-the-art optimizers, including L-SHADE and CMA-ES. Additional evaluations on five constrained engineering design problems further demonstrate the practical applicability and robustness of BWE.

cs.NE↗

arXiv2026

MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models

Video Large Multimodal Models have achieved remarkable progress in video understanding, yet they remain prone to hallucinations, where generated responses are not faithfully supported by the input video. In this paper, we propose MultiToP, a multimodal-context-aware visual token patching framework that mitigates hallucinations by refining unreliable visual tokens before language generation. MultiToP introduces a lightweight Visual Token Patcher to predict token-level replacement distributions and selectively substitute unreliable visual tokens with a dynamic global patch token. To train the patcher effectively, we further propose information-guided rank calibration, which uses answer-conditioned frame-level information cues derived from the backbone to guide token replacement. Combined with ground-truth answer supervision and sparsity regularization, MultiToP enables localized visual evidence refinement without modifying the original model. Extensive experiments demonstrate that MultiToP effectively reduces hallucinations on Vript-HAL with negligible inference overhead, improving the F1 scores of Qwen3-VL-4B-Instruct by 50.60% over the vanilla model. Meanwhile, MultiToP preserves general video understanding ability, yielding an 18.58% relative accuracy gain on ActivityNet-QA for Video-LLaVA-7B.

cs.CV↗

arXiv2026

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models

Although Video Large Multimodal Models have achieved strong performance in video understanding, they still suffer from hallucination. Existing inference-time intervention methods usually modify videos under the contrastive decoding framework, but their heuristic designs bring limited improvements and increase inference latency. To address these issues, we propose ViSSRes, an inference-time intervention method that enhances video representations through a lightweight MLP-style network. Specifically, we use a contrastive random walk approach to characterize the spatiotemporal consistency of video representations, and introduce conditional mutual information to associate video representations with the model's semantic understanding. With the model backbone kept frozen, ViSSRes learns residuals for video representations and optimizes them from both spatiotemporal and semantic consistency perspectives. During inference, ViSSRes requires only a single forward pass and introduces no substantial additional inference cost. Experiments show that ViSSRes reduces the hallucination rate of LLaVA-NeXT-Video on EventHallusion by 40.69% and improves video understanding on MMVU by 18.36% under the CoT setting, demonstrating its effectiveness in mitigating hallucinations.

cs.CV↗

arXiv2026

Dogfight Search: A Swarm-Based Optimization Algorithm for Complex Engineering Optimization and Mountainous Terrain Path Planning

Dogfight is a tactical behavior of cooperation between fighters. Inspired by this, this paper proposes a novel metaphor-free metaheuristic algorithm called Dogfight Search (DoS). Unlike traditional algorithms, DoS draws algorithmic framework from the inspiration, but its search mechanism is constructed based on the displacement integration equations in kinematics. Through experimental validation on CEC2017 and CEC2022 benchmark test functions, 10 real-world constrained optimization problems and mountainous terrain path planning tasks, DoS significantly outperforms 7 advanced competitors in overall performance and ranks first in the Friedman ranking. Furthermore, this paper compares the performance of DoS with 3 SOTA algorithms on the CEC2017 and CEC2022 benchmark test functions. The results show that DoS continues to maintain its lead, demonstrating strong competitiveness. The source code of DoS is available at https://ww2.mathworks.cn/matlabcentral/fileexchange/183519-dogfight-search.

cs.AI↗

arXiv2026

STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification

Multi-modal object Re-Identification (ReID) aims to exploit complementary information from different modalities to retrieve specific objects. However, existing methods often rely on hard token filtering or simple fusion strategies, which can lead to the loss of discriminative cues and increased background interference. To address these challenges, we propose STMI, a novel multi-modal learning framework consisting of three key components: (1) Segmentation-Guided Feature Modulation (SFM) module leverages SAM-generated masks to enhance foreground representations and suppress background noise through learnable attention modulation; (2) Semantic Token Reallocation (STR) module employs learnable query tokens and an adaptive reallocation mechanism to extract compact and informative representations without discarding any tokens; (3) Cross-Modal Hypergraph Interaction (CHI) module constructs a unified hypergraph across modalities to capture high-order semantic relationships. Extensive experiments on public benchmarks (i.e., RGBNT201, RGBNT100, and MSVR310) demonstrate the effectiveness and robustness of our proposed STMI framework in multi-modal ReID scenarios.

cs.CV↗

arXiv2026

Full-Covariance Chemical Langevin Predator--Prey Diffusion with Absorbing Boundaries

Many stochastic Rosenzweig--MacArthur predator--prey models inject ad hoc independent (diagonal) noise and therefore cannot encode the event-level coupling created by predation and biomass conversion. We derive an absorbed, fully mechanistic diffusion approximation and its extinction structure from a continuous-time Markov chain on $\mathbb N_0^2$ with four reaction channels: prey birth, prey competition death, predator death, and a coupled predation--conversion event. Absorbing coordinate axes are imposed to represent the irreversibility of demographic extinction. Under Kurtz density-dependent scaling, the law-of-large-numbers limit recovers the classical RM ODE, while central-limit scaling yields a chemical-Langevin diffusion with explicit drift and full state-dependent covariance. A distinctive signature is the strictly negative cross-covariance $Σ_{12}(N,P)=-mNP/(1+N)$ induced solely by the predation--conversion increment $(-1,1)$. We define the absorbed Itô SDE by freezing trajectories at the first boundary hit and prove strong well-posedness, non-explosion, and moment bounds up to absorption. Extinction has positive probability from every interior state, and predator extinction is almost sure when $m\le c$.

math.PR↗

arXiv2026

Boosting Large Language Models for Mental Manipulation Detection via Data Augmentation and Distillation

Mental manipulation on social media poses a covert yet serious threat to individuals' psychological well-being and the integrity of online interactions. Detecting such behavior is challenging due to the difficult-to-annotate training data, its highly covert and multi-turn nature, and the lack of real-world datasets. To address these challenges, we propose MentalMAD, a framework that enhances large language models for mental manipulation detection. Our approach consists of three key components: EvoSA, an annotation-free data augmentation method that combines evolutionary operations with speech-act-aware prompting; teacher-model-generated complementary-task supervision; and Complementary-Convergent Distillation, a phase-wise strategy for transferring manipulation-specific knowledge to student models. We then constructed the ReaMent dataset, comprising 5,000 real-world-sourced dialogues. Extensive experiments show that MentalMAD improves accuracy by 14.0%, macro-F1 by 27.3%, and weighted F1 by 15.1% over the strongest baseline. The code and the dataset are publicly available at https://github.com/Yuansheng-Gao/MentalMAD.

cs.CL↗

arXiv2025

Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learning

As web platforms evolve towards greater personalization and emotional complexity, conversational agents must transcend superficial empathy to demonstrate identity-aware emotional reasoning. However, existing systems face two limitations: (1) reliance on situation-centric datasets lacking persistent user identity, which hampers the capture of personalized affective nuances; and (2) dependence on opaque, coarse reward signals that hinder development of verifiable empathetic reasoning. To address these gaps, we introduce KardiaBench, a large-scale user-grounded benchmark comprising 178,080 QA pairs across 22,080 multi-turn conversations anchored to 671 real-world profiles. The dataset is constructed via a model-in-the-loop pipeline with iterative rubric-guided refinement to ensure psychological plausibility and persona consistency. This progressive empathy pipeline that integrates user comprehension, contextual reasoning, and emotion perception into conversations, followed by iterative critique and rubric-based refinement to ensure psychological plausibility, emotional fidelity, and persona consistency. Building on this, we propose Kardia-R1, a framework that trains models for interpretable, stepwise empathetic cognition. Kardia-R1 leverages Rubric-as-Judge Empathetic Reinforcement Learning (Rubric-ERL), a GRPO-based method that uses explainable, human-aligned rubric rewards to tightly couple user understanding, emotional inference, and supportive response generation. Extensive experiments across four LLM backbones demonstrate that Kardia-R1 consistently outperforms othet methods in emotion accuracy, empathy, relevance, persona consistency, and safety. Our dataset and model will be released at https://github.com/JhCircle/Kardia-R1.

cs.CL↗