Publications (90)
AI Enlightens Wireless Communication: Analyses, Solutions and Opportunities on CSI Feedback
Han Xiao, Zhiqin Wang, Wenqiang Tian +6
In this paper, we give a systematic description of the 1st Wireless Communication Artificial Intelligence (AI) Competition (WAIC) which is hosted by IMT-2020(5G) Promotion Group 5G…
Predicting Neighbor Distribution in Heterogeneous Information Networks
Yuchi Ma, Ning Yang, Chuan Li +2
Recently, considerable attention has been devoted to the prediction problems arising from heterogeneous information networks. In this paper, we present a new prediction task, Neigh…
On decycling and forest numbers of Cartesian products of trees
Ali Ghalavand, Sandi Klavžar, Ning Yang
The decycling number of a graph is the minimum number of vertices that must be removed to eliminate all cycles in . The forest number is the maximum numbe…
AI2Pot: A scalable and unified framework for machine-learning interatomic potential development and large-scale molecular dynamic simulations
Hanyu Liu, Linggang Zhu, Xuanguang Zhang +3
Machine-learning interatomic potentials (MLIPs) bridge the accuracy of first-principles calculations and the efficiency required for large-scale molecular dynamics (MD) simulations…
Multi-objective Deep Reinforcement Learning for Mobile Edge Computing
Ning Yang, Junrui Wen, Meng Zhang +1
Mobile edge computing (MEC) is essential for next-generation mobile network applications that prioritize various performance metrics, including delays and energy consumption. Howev…
Adaptive and Robust Data Poisoning Detection and Sanitization in Wearable IoT Systems using Large Language Models
W. K. M Mithsara, Ning Yang, Ahmed Imteaj +2
The widespread integration of wearable sensing devices in Internet of Things (IoT) ecosystems, particularly in healthcare, smart homes, and industrial applications, has required ro…
Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring
Dongxu Zhang, Yiding Sun, Cheng Tan +4
While Chain-of-Thought (CoT) reasoning significantly enhances the performance of Multimodal Large Language Models (MLLMs), its autoregressive nature incurs prohibitive latency cons…
Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement
Dongxu Zhang, Hongqiang Lin, Yiding Sun +4
Scaling test-time computation enhances LLM reasoning ability but faces a uniform computation paradox. Allocating identical resources leads to over-correction on simple tasks and in…
WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation
Ning Yang, Yan Huang, Kaiwen Peng +9
Visual navigation requires generating smooth and collision-free trajectories under complex geometric and physical constraints. Existing reactive policies that directly map observat…
Token-Importance Guided Direct Preference Optimization
Ning Yang, Hai Lin, Yibo Liu +3
Aligning Large Language Models (LLMs) with human preferences is crucial for safe and effective AI interactions. While popular methods like Direct Preference Optimization (DPO) have…
Collaborative Inference of Coexisting Information Diffusions
Yanchao Sun, Cong Qian, Ning Yang +1
Recently, \textit{diffusion history inference} has become an emerging research topic due to its great benefits for various applications, whose purpose is to reconstruct the missing…
SDO: Structure-Aware Data Organization for Efficient LLM Post-Training
Jinliang Gao, Ning Yang, Hai Wang +2
The paper introduces SDO, a plug‑and‑play framework that dynamically organizes training data for large language model post‑training by using exposure‑driven feedback and K‑nearest‑…
AI Enlightens Wireless Communication: A Transformer Backbone for CSI Feedback
Han Xiao, Zhiqin Wang, Dexin Li +7
This paper is based on the background of the 2nd Wireless Communication Artificial Intelligence (AI) Competition (WAIC) which is hosted by IMT-2020(5G) Promotion Group 5G+AIWork Gr…
SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models
Ziheng He, Yixiang Chen, Ning Yang +11
Embodied world models have emerged as a promising paradigm in robotics by predicting how robot actions affect the surrounding scene. However, the rollout inference remains computat…
Mechatronics-Driven Musical Expressivity for Robotic Percussionists
Ning Yang, Richard Savery, Raghavasimhan Sankaranarayanan +2
Musical expressivity is an important aspect of musical performance for humans as well as robotic musicians. We present a novel mechatronics-driven implementation of Brushless Direc…
Large Language Model Integrated Healthcare Cyber-Physical Systems Architecture
Malithi Wanniarachchi Kankanamge, Syed Mhamudul Hasan, Abdur R. Shahid +1
Cyber-physical systems have become an essential part of the modern healthcare industry. The healthcare cyber-physical systems (HCPS) combine physical and cyber components to improv…
Negative Metric Learning for Graphs
Yiyang Zhao, Chengpei Wu, Lilin Zhang +1
Graph contrastive learning (GCL) often suffers from false negatives, which degrades the performance on downstream tasks. The existing methods addressing the false negative issue us…
TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement Learning
Yuxuan Li, Yicheng Gao, Ning Yang +1
Episodic tasks in Reinforcement Learning (RL) often pose challenges due to sparse reward signals and high-dimensional state spaces, which hinder efficient learning. Additionally, t…
Aharonov-Bohm phase operations on a double-barrier nanoring charge qubit
Yuquan Wang, Ning Yang, Jia-Lin Zhu
We present a scheme for charge qubit implementation in a double-barrier nanoring. The logical states of the qubit are encoded in the spatial wavefunctions of the two lowest energy…
Enhancing Efficiency and Propulsion in Bio-mimetic Robotic Fish through End-to-End Deep Reinforcement Learning
Xinyu Cui, Boai Sun, Yi Zhu +5
Aquatic organisms are known for their ability to generate efficient propulsion with low energy expenditure. While existing research has sought to leverage bio-inspired structures t…
Partitewise Entanglement
Yu Guo, Ning Yang
It is known that as a bipartite reduced state of the 3-qubit GHZ state is separable, but part and part indeed ``share tripartite entanglement'' in the GHZ state.…
Provable Unrestricted Adversarial Training without Compromise with Generalizability
Lilin Zhang, Ning Yang, Yanchao Sun +1
Adversarial training (AT) is widely considered as the most promising strategy to defend against adversarial attacks and has drawn increasing interest from researchers. However, the…
Many Field Packet Classification with Decomposition and Reinforcement Learning
Hasibul Jamil, Ning Yang, Ning Weng
Scalable packet classification is a key requirement to support scalable network applications like firewalls, intrusion detection, and differentiated services. With ever increasing…
Causal Reward World Models: Zero-shot Reward Design for Automated Skill Generation
Yang Yang, Yuchuang Tong, Zhengtao Zhang +6
Automated Reward Design (ARD) aims to replace manual reward engineering in reinforcement learning with language-driven reward function synthesis. However, existing approaches based…
EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devices
Liuchuan Yu, Erdem Murat, Beichen Wang +10
Egocentric video is increasingly used as a data source for robot learning, activity understanding, and embodied AI research, but collecting it at scale remains fragmented in practi…
CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation
Ning Yang, Chengzhi Wang, Yibo Liu +2
Prefill-only KV compression freezes a token subset at the end of prefill and decodes from it without further eviction. The retention decision is therefore irreversible, yet existin…
Cascade-KDE: Robust Time-Series Restoration under Out-of-Distribution Impulse Corruptions
Yuefeng Liu, Ning Yang, Ziyu Yang
Real-world time-series data in industrial sensing, healthcare, and energy systems is often corrupted by a mixture of Gaussian noise and occasional large-magnitude impulse outliers.…
Cooperative Edge Caching with Large Language Model in Wireless Networks
Ning Yang, Wentao Wang, Lingtao Ouyang +1
Cooperative edge caching in overlapping zones couples Base Station (BS) decisions, making content replacement sensitive to spatial topology and temporal reuse. Conventional heurist…
Deep Collaborative Embedding for information cascade prediction
Yuhui Zhao, Ning Yang, Tao Lin +1
Recently, information cascade prediction has attracted increasing interest from researchers, but it is far from being well solved partly due to the three defects of the existing wo…
Cross-wired lamplighter groups and linearity of automata groups
Ning Yang
We consider the two generalizations of lamplighter groups: automata groups generated by Cayley machine and cross-wired lamplighter groups. For a finite step two nilpotent group wit…
Weakly Supervised Contrastive Adversarial Training for Learning Robust Features from Semi-supervised Data
Lilin Zhang, Chengpei Wu, Ning Yang
Existing adversarial training (AT) methods often suffer from incomplete perturbation, meaning that not all non-robust features are perturbed when generating adversarial examples (A…
SF-AMS: Strategic Forgetting for Structured Memory in LLM Agent
Ning Yang, Siqi Li, Miaoxin Shen +4
Managing long-context dependencies remains a primary bottleneck in LLM agents, as redundant and irrelevant information can degrade multi-step reasoning. Strategic Forgetting for Ag…
Multi-Turn Reasoning LLMs for Task Offloading in Mobile Edge Computing
Ning Yang, Chuangxin Cheng, Haijun Zhang
Emerging computation-intensive applications impose stringent latency requirements on resource-constrained mobile devices. Mobile Edge Computing (MEC) addresses this challenge throu…
Computable lower bound of the parameterized entanglement monotone
Ning Yang, Yu Guo, Shuanping Du
Although numerous measures of entanglement have been proposed so far, the calculation of a given faithful entanglement measure is a hard work since it is always involved in some op…
Secure Communications in NOMA System: Subcarrier Assignment and Power Allocation
Haijun Zhang, Ning Yang, Keping Long +3
Secure communication is a promising technology for wireless networks because it ensures secure transmission of information. In this paper, we investigate the joint subcarrier (SC)…
Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression
Peijun Zhu, Ning Yang, Baoliang Tian +4
Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead. We introduce a unified framework based on…
Multi-Sparse-Domain Collaborative Recommendation via Enhanced Comprehensive Aspect Preference Learning
Xiaoyun Zhao, Ning Yang, Philip S. Yu
Cross-domain recommendation (CDR) has been attracting increasing attention of researchers for its ability to alleviate the data sparsity problem in recommender systems. However, th…
LCD: Advancing Extreme Low-Bit Clustering for Large Language Models via Knowledge Distillation
Fangxin Liu, Ning Yang, Junping Zhao +3
Large language models (LLMs) have achieved significant progress in natural language processing but face challenges in deployment due to high memory and computational requirements.…
Adaptive Fair Representation Learning for Personalized Fairness in Recommendations via Information Alignment
Xinyu Zhu, Lilin Zhang, Ning Yang
Personalized fairness in recommendations has been attracting increasing attention from researchers. The existing works often treat a fairness requirement, represented as a collecti…
Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning
Dongxu Zhang, Yujun Wu, Yiding Sun +5
While Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs), ensuring reasoning reliability remains an open challenge. Contrary to the prevailing cascading failure…
XRoboToolkit: A Cross-Platform Framework for Robot Teleoperation
Zhigen Zhao, Liuchuan Yu, Ke Jing +1
The rapid advancement of Vision-Language-Action models has created an urgent need for large-scale, high-quality robot demonstration datasets. Although teleoperation is the predomin…
Denoised Recommendation Model with Collaborative Signal Decoupling
Zefeng Li, Ning Yang
Although the collaborative filtering (CF) algorithm has achieved remarkable performance in recommendation systems, it suffers from suboptimal recommendation performance due to nois…
Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling
Ziyi Ni, Yifan Li, Ning Yang +3
Solving complex reasoning tasks is a key real-world application of agents. Thanks to the pretraining of Large Language Models (LLMs) on code data, recent approaches like CodeAct su…
Research on a Two-Layer Demand Response Framework for Electric Vehicle Users and Aggregators Based on LLMs
Zhaoyi Zhang, Chenggang Cui, Ning Yang +1
The widespread adoption of electric vehicles (EVs) has increased the importance of demand response in smart grids. This paper proposes a two-layer demand response optimization fram…
Local large temperature difference and ultra-wideband photothermoelectric response of the silver nanostructure film/carbon nanotube film heterostructure
Bocheng Lv, Weidong Wu, Yan Xie +7
Photothermoelectric materials have important applications in many fields. Here, we joined a silver nanostructure film (AgNSF) and a carbon nanotube film (CNTF) by van der Waals for…
Global-and-Local Collaborative Learning for Co-Salient Object Detection
Runmin Cong, Ning Yang, Chongyi Li +4
The goal of co-salient object detection (CoSOD) is to discover salient objects that commonly appear in a query group containing two or more relevant images. Therefore, how to effec…
Noise-Driven Exploration and Transient Freezing Select Flat Minima in Stochastic Gradient Descent
Ning Yang, Yikuan Zhang, Qi Ouyang +2
Stochastic gradient descent (SGD) is central to deep learning, yet the dynamical origin of its preference for flatter, more generalizable solutions remains unclear. Here, by analyz…
CrossCheck-Bench: Diagnosing Compositional Failures in Multimodal Conflict Resolution
Baoliang Tian, Yuxuan Si, Jilong Wang +13
Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largel…
Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction
Tencent WorkBuddy Bench Team, Siqi Cai, Shaopeng Chen +35
We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model lea…
MLANE: Meta-Learning Based Adaptive Network Embedding
Chen Cui, Ning Yang, Philip S. Yu
Most existing random walk based network embedding methods often follow only one of two principles, homophily or structural equivalence. In real world networks, however, nodes exhib…
Realization of ultrabroadband THz/IR photoresponse in a bias-tunable ratchet photodetector
Peng Bai, Xiaohong Li, Ning Yang +14
High performance Terahertz (THz) photodetector has drawn wide attention and got great improvement due to its significant application in biomedical, astrophysics, nondestructive ins…
Cross-Domain Causal Preference Learning for Out-of-Distribution Recommendation
Zhuhang Li, Ning Yang
Recommender systems use users' historical interactions to learn their preferences and deliver personalized recommendations from a vast array of candidate items. Current recommender…
One-step synthesis of van der Waals heterostructures of graphene and 2D superconducting a-Mo2C
Jia-Bin Qiao, Yue Gong, Wei-Jie Zuo +8
Assembling different two-dimensional (2D) crystals, covering a very broad range of properties, into van der Waals (vdW) heterostructures enables the unprecedented possibilities for…
Inverse orbital Hall effect induced terahertz emission enabled by a ferromagnet with quenched orbital moment in Fe/Pt/W trilayers
Chao Zhou, Lei Hao, Shaohua Zhang +10
The inverse orbital Hall effect (IOHE) has recently attracted considerable attention as an emerging mechanism for terahertz (THz) emission based on ultrafast angular-momentum-to-ch…
Minimizing Age of Information for Mobile Edge Computing Systems: A Nested Index Approach
Shuo Chen, Ning Yang, Meng Zhang +1
Exploiting the computational heterogeneity of mobile devices and edge nodes, mobile edge computation (MEC) provides an efficient approach to achieving real-time applications that a…
Time Lag Aware Sequential Recommendation
Lihua Chen, Ning Yang, Philip S Yu
Although a variety of methods have been proposed for sequential recommendation, it is still far from being well solved partly due to two challenges. First, the existing methods oft…
AI-Native 6G Physical Layer with Cross-Module Optimization and Cooperative Control Agents
Xufei Zheng, Han Xiao, Shi Jin +8
In this article, a framework of AI-native cross-module optimized physical layer with cooperative control agents is proposed, which involves optimization across global AI/ML modules…
Mean Field Correlated Imitation Learning
Zhiyu Zhao, Qirui Mi, Ning Yang +4
We investigate multi-agent imitation learning (IL) within the framework of mean field games (MFGs), considering the presence of time-varying correlated signals. Existing MFG IL alg…
Graph Attention Reinforcement Learning for Multicast Routing and Age-Optimal Scheduling
Yanning Zhang, Guocheng Liao, Shengbin Cao +3
Multicast routing is essential for real-time group applications, such as video streaming, virtual reality, and metaverse platforms, where the Age of Information (AoI) acts as a cru…
Stochastic gradient descent introduces an effective landscape-dependent regularization favoring flat solutions
Ning Yang, Chao Tang, Yuhai Tu
Generalization is one of the most important problems in deep learning (DL). In the overparameterized regime in neural networks, there exist many low-loss solutions that fit the tra…
Bound States in Nanoscale Graphene Quantum Dots in a Continuous Graphene Sheet
Jia-Bin Qiao, Hua Jiang, Haiwen Liu +4
Considerable efforts have been made to trap massless Dirac fermions in graphene monolayer, but only quasi-bound states are realized in continuous graphene sheets up to now. Here, w…
Vortex structures in few-electron quantum dots with spin degree of freedom
Ning Yang, Jia-Lin Zhu, Zhensheng Dai +1
The vortex structures and formations of the few-electron states in quantum dots without the Zeeman splitting are investigated. With spin degree of freedom, it is noticed that both…
Learn to Swim: Data-Driven LSTM Hydrodynamic Model for Quadruped Robot Gait Optimization
Fei Han, Pengming Guo, Hao Chen +5
This paper presents a Long Short-Term Memory network-based Fluid Experiment Data-Driven model (FED-LSTM) for predicting unsteady, nonlinear hydrodynamic forces on the underwater qu…
Boundary Guided Semantic Learning for Real-time COVID-19 Lung Infection Segmentation System
Runmin Cong, Yumo Zhang, Ning Yang +6
The coronavirus disease 2019 (COVID-19) continues to have a negative impact on healthcare systems around the world, though the vaccines have been developed and national vaccination…
Proactive Constrained Policy Optimization with Preemptive Penalty
Ning Yang, Pengyu Wang, Guoqing Liu +3
Safe Reinforcement Learning (RL) often faces significant issues such as constraint violations and instability, necessitating the use of constrained policy optimization, which seeks…
When and Where: Predicting Human Movements Based on Social Spatial-Temporal Events
Ning Yang, Xiangnan Kong, Fengjiao Wang +1
Predicting both the time and the location of human movements is valuable but challenging for a variety of applications. To address this problem, we propose an approach considering…
Offline Policy Optimization with Posterior Sampling
Hongqiang Lin, Dongxu Zhang, Yiding Sun +3
A fundamental challenge in model-based offline reinforcement learning (RL) lies in the trade-off between generalization and robustness against exploitation errors in out-of-distrib…
Minimizing AoI in Mobile Edge Computing: Nested Index Policy with Preemptive and Non-preemptive Structure
Ning Yang, Yibo Liu, Shuo Chen +2
Mobile Edge Computing (MEC) leverages computational heterogeneity between mobile devices and edge nodes to enable real-time applications requiring high information freshness. The A…
Generalizable Pareto-Optimal Offloading with Reinforcement Learning in Mobile Edge Computing
Ning Yang, Junrui Wen, Meng Zhang +1
Mobile edge computing (MEC) is essential for next-generation mobile network applications that prioritize various performance metrics, including delays and energy efficiency. Howeve…
LLM-Driven Large-Scale Spectrum Access
Ning Yang, Jinliang Gao, Haijun Zhang
Efficient spectrum management in massive-scale wireless networks is increasingly challenged by explosive action spaces and the computational intractability of traditional optimizat…
Beyond the Edge: An Advanced Exploration of Reinforcement Learning for Mobile Edge Computing, its Applications, and Future Research Trajectories
Ning Yang, Shuo Chen, Haijun Zhang +1
Mobile Edge Computing (MEC) broadens the scope of computation and storage beyond the central network, incorporating edge nodes close to end devices. This expansion facilitates the…
Vision-LLMs for Spatiotemporal Traffic Forecasting
Ning Yang, Hengyu Zhong, Haijun Zhang +1
Accurate spatiotemporal traffic forecasting is a critical prerequisite for proactive resource management in dense urban mobile networks. While large language models have shown prom…
DASH: Input-Aware Dynamic Layer Skipping for Efficient LLM Inference with Markov Decision Policies
Ning Yang, Fangxin Liu, Junjie Wang +4
Large language models (LLMs) have achieved remarkable performance across a wide range of NLP tasks. However, their substantial inference cost poses a major barrier to real-world de…
Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization
Yongcheng Zeng, Xinyu Cui, Xuanfa Jin +11
Self-Refinement refers to a model's ability to revise its own responses to produce improved outputs. This capability can also serve as a fundamental mechanism for Self-Improvement,…
Band Together: Untargeted Adversarial Training with Multimodal Coordination against Evasion-based Promotion Attacks
Guanmeng Xian, Ning Yang, Philip S. Yu
Multimodal recommender systems exploit visual and textual signals to alleviate data sparsity, but this also makes them more vulnerable to evasion-based promotion attacks. Existing…
Dual Adversarial Variational Embedding for Robust Recommendation
Qiaomin Yi, Ning Yang, Philip S. Yu
Robust recommendation aims at capturing true preference of users from noisy data, for which there are two lines of methods have been proposed. One is based on noise injection, and…
Automata groups generated by Cayley machines of groups of nilpotency class two
Ning Yang
We show presentations of automata groups generated by Cayley machines of finite groups of nilpotency class two and these automata groups are all cross-wired lamplighters.
Learning from Atypical Behavior: Temporary Interest Aware Recommendation Based on Reinforcement Learning
Ziwen Du, Ning Yang, Zhonghua Yu +1
Traditional robust recommendation methods view atypical user-item interactions as noise and aim to reduce their impact with some kind of noise filtering technique, which often suff…
On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature
Yikuan Zhang, Ning Yang, Yuhai Tu
Stochastic Gradient Descent (SGD) introduces anisotropic noise that is correlated with the local curvature of the loss landscape, thereby biasing optimization toward flat minima. P…
Token-level Direct Preference Optimization
Yongcheng Zeng, Guoqing Liu, Weiyu Ma +3
Fine-tuning pre-trained Large Language Models (LLMs) is essential to align them with human values and intentions. This process often utilizes methods like pairwise comparisons and…
Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignment
Guanmeng Xian, Ning Yang, Philip S. Yu
Adversarial training is effective on balanced datasets, but its robustness degrades under longtailed class distributions, where tail classes suffer high robust error and unstable d…
Hybrid Deep Embedding for Recommendations with Dynamic Aspect-Level Explanations
Huanrui Luo, Ning Yang, Philip S. Yu
Explainable recommendation is far from being well solved partly due to three challenges. The first is the personalization of preference learning, which requires that different item…
Joint Caching and Transmission in the Mobile Edge Network: A Multi-Agent Learning Approach
Qirui Mi, Ning Yang, Haifeng Zhang +2
Joint caching and transmission optimization problem is challenging due to the deep coupling between decisions. This paper proposes an iterative distributed multi-agent learning app…
Long-Range Gesture Recognition Using Millimeter Wave Radar
Yu Liu, Yuheng Wang, Haipeng Liu +3
Millimeter wave (mmWave) based gesture recognition technology provides a good human computer interaction (HCI) experience. Prior works focus on the close-range gesture recognition,…
Contrastive Collaborative Filtering for Cold-Start Item Recommendation
Zhihui Zhou, Lilin Zhang, Ning Yang
The cold-start problem is a long-standing challenge in recommender systems. As a promising solution, content-based generative models usually project a cold-start item's content ont…
HiMemVLN: Enhancing Reliability of Open-Source Zero-Shot Vision-and-Language Navigation with Hierarchical Memory System
Kailin Lyu, Kangyi Wu, Pengna Li +9
LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) tasks. However, most zero-shot methods primarily rely on closed-source LLMs…
LinearARD: Linear-Memory Attention Distillation for RoPE Restoration
Ning Yang, Hengyu Zhong, Wentao Wang +3
The extension of context windows in Large Language Models is typically facilitated by scaling positional encodings followed by lightweight Continual Pre-Training (CPT). While effec…
PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoning
Dongxu Zhang, Yiding Sun, Pengcheng Li +12
While Multimodal Large Language Models (MLLMs) demonstrate proficiency in 2D scenes, extending their perceptual intelligence to 3D point cloud understanding remains a significant c…
Correlations and entanglements in a few-electron quantum dot without Zeeman splitting
Ning Yang, Jia-Lin Zhu, Zhengsheng Dai +1
We explore the correlations and entanglements of exact-diagonalized few-electron wave functions in a quantum dot in magnetic fields without the Zeeman splitting. With the increase…
Spin-dependent Rotating Wigner Molecules in Quantum dots
Zhensheng Dai, Jia-Lin Zhu, Ning Yang +1
The spin-dependent trial wave functions with rotational symmetry are introduced to describe rotating Wigner molecular states with spin degree of freedom in four- and five-electron…