Publications (139)
Evolution of relative Yamabe constant under Ricci Flow
Boris Botvinnik, Peng Lu
Let be a manifold with boundary given together with a conformal class which restricts to a conformal class on . Then the relative Yamabe constant $Y_{\bar C…
Resona: Improving Context Copying in Linear Recurrence Models with Retrieval
Xinyu Wang, Linrui Ma, Jerry Huang +5
Recent shifts in the space of large language model (LLM) research have shown an increasing focus on novel architectures to compete with prototypical Transformer-based models that h…
Global well-posedness and large-time behavior for three-dimensional magneto-micropolar equations with horizontal dissipation
Peng Lu, Yuanyuan Qiao
This paper is concerned with the stability and large-time behavior for 3D magneto-micropolar equations with horizontal dissipation. The global well-posedness of the aforementioned…
Herculean: An Agentic Benchmark for Financial Intelligence
Xueqing Peng, Zhuohan Xie, Yupeng Cao +60
As AI agents improve, the central question is no longer whether they can solve isolated well-defined financial tasks, but whether they can reliably carry out financial professional…
Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking
Ziyuan Huang, Changhong Fu, Yiming Li +2
Traditional framework of discriminative correlation filters (DCF) is often subject to undesired boundary effects. Several approaches to enlarge search regions have been already pro…
A note on uniformization of Riemann surfaces by Ricci flow
Xiuxiong Chen, Peng Lu, Gang Tian
In this note we clarify that the Rcci flow can be used to give an independent proof of the uniformization theorem of Riemann surfaces.
Generating Feasible and Diverse Synthetic Populations Using Diffusion Models
Min Tang, Peng Lu, Qing Feng
Population synthesis is a critical task that involves generating synthetic yet realistic representations of populations. It is a fundamental problem in agent-based modeling (ABM),…
Ancient Ricci Flow Solutions on Bundles
Peng Lu, Y. K. Wang
We generalize the circle bundle examples of ancient solutions of the Ricci flow discovered by Bakas, Kong, and Ni to a class of principal torus bundles over an arbitrary finite pro…
FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering
Jijun Chi, Zhenghan Tai, Hanwei Wu +21
Financial question answering over U.S. Securities and Exchange Commission (SEC) filings requires retrieving and synthesizing heterogeneous evidence dispersed across long, standardi…
InfMem: Learning System-2 Memory Control for Long-Context Agent
Xinyu Wang, Mingze Li, Peng Lu +6
Reasoning over ultra-long documents requires synthesizing sparse evidence scattered across distant segments under strict memory constraints. While streaming agents enable scalable…
ECMD: An Event-Centric Multisensory Driving Dataset for SLAM
Peiyu Chen, Weipeng Guan, Feng Huang +4
Leveraging multiple sensors enhances complex environmental perception and increases resilience to varying luminance conditions and high-speed motion patterns, achieving precise loc…
Simultaneous State and Unknown Input Estimation for Continuous-discrete Stochastic Systems
Peng Lu
This paper considers the simultaneous state and unknown input estimation for continuous-discrete stochastic systems. Two types of approaches (with and without modeling of unknown i…
A study on the -distribution motivated by Chvátal's theorem
Qianqian Zhou, Peng Lu, Zechun Hu
Let be an -random variable with parameters and and expectation . In this paper, for any we investigate the infimum value of…
In-between Motion Generation Based Multi-Style Quadruped Robot Locomotion
Yuanhao Chen, Liu Zhao, Ji Ma +1
Quadruped robots face persistent challenges in achieving versatile locomotion due to limitations in reference motion data diversity. To address these challenges, we introduce an in…
New proofs of Perelman's theorem on shrinking Breathers in Ricci flow
Peng Lu, Yu Zheng
We give two new proofs of Perelman's theorem that shrinking breathers of Ricci flow on closed manifolds are gradient Ricci solitons, using the fact that the singularity models of t…
RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose
Tao Jiang, Peng Lu, Li Zhang +5
Recent studies on 2D pose estimation have achieved excellent performance on public benchmarks, yet its application in the industrial community still suffers from heavy model parame…
The linear trace Harnack quadratic on a steady gradient Ricci soliton satisfies the heat equation
Bennett Chow, Peng Lu
We show that the linear trace Harnack quadratic on a steady gradient Ricci soliton satisfies the heat equation. Similar result holds for shrinkers. We also present an interpolation…
Ancient solutions for Andrews' hypersurface flow
Peng Lu, Jiuru Zhou
We construct the ancient solutions of the hypersurface flows in Euclidean spaces studied by B. Andrews in 1994. As time the solutions collapse to a round point…
Nonlinear disturbance attenuation control of hydraulic robotics
Peng Lu, Timothy Sandy, Jonas Buchli
This paper presents a novel nonlinear disturbance rejection control for hydraulic robots. This method requires two third-order filters as well as inverse dynamics in order to estim…
An End-to-End Neural Network for Image Cropping by Learning Composition from Aesthetic Photos
Peng Lu, Hao Zhang, Xujun Peng +1
As one of the fundamental techniques for image editing, image cropping discards unrelevant contents and remains the pleasing portions of the image to enhance the overall compositio…
A Fast Planning Approach for 3D Short Trajectory with a Parallel Framework
Han Chen, Shengyang Chen, Peng Lu +1
For real applications of unmanned aerial vehicles, the capability of navigating with full autonomy in unknown environments is a crucial requirement. However, planning a shorter pat…
EVI-SAM: Robust, Real-time, Tightly-coupled Event-Visual-Inertial State Estimation and 3D Dense Mapping
Weipeng Guan, Peiyu Chen, Huibin Zhao +2
Event cameras are bio-inspired, motion-activated sensors that demonstrate substantial potential in handling challenging situations, such as motion blur and high-dynamic range. In t…
A black-box-model-enhanced interaction method for water-wave scattering by large group of arbitrary-shaped ice floes in Arctic route planning
Chongwei Zhang, Hongli Yang, Peng Wu +2
This study develops an enhanced interaction (EI) method for efficient prediction of the water-wave field among a large group of ice floes in Arctic route planning. A novel black-bo…
Stroke-based Cyclic Amplifier: Image Super-Resolution at Arbitrary Ultra-Large Scales
Wenhao Guo, Peng Lu, Xujun Peng +2
Prior Arbitrary-Scale Image Super-Resolution (ASISR) methods often experience a significant performance decline when the upsampling factor exceeds the range covered by the training…
Global Existence and Asymptotic Behavior of Large Strong Solutions to the 3D Full Compressible Navier-Stokes Equations with Density-dependent Viscosities
Yachun Li, Peng Lu, Zhaoyang Shang +1
The purpose of this work is to investigate the Cauchy problem of global-in-time existence of large strong solutions to the Navier-Stokes equations for compressible viscous and heat…
HEPP: Hyper-efficient Perception and Planning for High-speed Obstacle Avoidance of UAVs
Minghao Lu, Xiyu Fan, Bowen Xu +5
High-speed obstacle avoidance of uncrewed aerial vehicles (UAVs) in cluttered environments is a significant challenge. Existing UAV planning and obstacle avoidance systems can only…
Domain-Aware SE Network for Sketch-based Image Retrieval with Multiplicative Euclidean Margin Softmax
Peng Lu, Gao Huang, Hangyu Lin +3
This paper proposes a novel approach for Sketch-Based Image Retrieval (SBIR), for which the key is to bridge the gap between sketches and photos in terms of the data representation…
Lasso Gripper: A String Shooting-Retracting Mechanism for Shape-Adaptive Grasping
Qiyuan Qiao, Yu Wang, Xiyu Fan +1
Handling oversized, variable-shaped, or delicate objects in transportation, grasping tasks is extremely challenging, mainly due to the limitations of the gripper's shape and size.…
Learning Consistency Pursued Correlation Filters for Real-Time UAV Tracking
Changhong Fu, Xiaoxiao Yang, Fan Li +3
Correlation filter (CF)-based methods have demonstrated exceptional performance in visual object tracking for unmanned aerial vehicle (UAV) applications, but suffer from the undesi…
Framework for state and unknown input estimation of linear time-varying systems
Peng Lu, Erik-Jan van Kampen, Cornelis C. de Visser +1
The design of unknown-input decoupled observers and filters requires the assumption of an existence condition in the literature. This paper addresses an unknown input filtering pro…
Boundary Effect-Aware Visual Tracking for UAV with Online Enhanced Background Learning and Multi-Frame Consensus Verification
Changhong Fu, Ziyuan Huang, Yiming Li +2
Due to implicitly introduced periodic shifting of limited searching area, visual object tracking using correlation filters often has to confront undesired boundary effect. As bound…
Knowledge Gaps and Research Needs for Modeling CO2 Mineralization in the Basalt-CO2-Water System: A Review of Laboratory Experiments
Peng Lu, John Apps, Guanru Zhang +1
Carbon capture and storage in basalt is being actively investigated as a scalable climate change mitigation option. Accurate geochemical modeling prediction of the extent and rate…
Do we need Label Regularization to Fine-tune Pre-trained Language Models?
Ivan Kobyzev, Aref Jafari, Mehdi Rezagholizadeh +5
Knowledge Distillation (KD) is a prominent neural model compression technique that heavily relies on teacher network predictions to guide the training of a student model. Consideri…
Global well-posedness and exponential decay of strong solution for the three-dimensional inhomogeneous incompressible micropolar equations with density-dependent transport coefficients and large initial data
Peng Lu, Yuanyuan Qiao
In this paper, we consider the Dirichlet problem of three-dimensional inhomogeneous incompressible micropolar equations with density-dependent viscosity. Under the assumption that…
Towards Robust Visual Tracking for Unmanned Aerial Vehicle with Tri-Attentional Correlation Filters
Yujie He, Changhong Fu, Fuling Lin +2
Object tracking has been broadly applied in unmanned aerial vehicle (UAV) tasks in recent years. However, existing algorithms still face difficulties such as partial occlusion, clu…
DEIO: Deep Event Inertial Odometry
Weipeng Guan, Fuling Lin, Peiyu Chen +1
Event cameras show great potential for visual odometry (VO) in handling challenging situations, such as fast motion and high dynamic range. Despite this promise, the sparse and mot…
SEGAN: semi-supervised learning approach for missing data imputation
Xiaohua Pan, Weifeng Wu, Peiran Liu +6
In many practical real-world applications, data missing is a very common phenomenon, making the development of data-driven artificial intelligence theory and technology increasingl…
EventOD: Event-Aware OD Flow Generation via LLM-Guided Semantic Modulation
Jie Zhao, Jie Feng, Can Rong +3
Estimating origin-destination (OD) flows under disruptive events is important for disaster response and urban resilience. Existing deep OD models trained on routine mobility often…
HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models
Xinyu Wang, Mingze Li, Sicheng Lyu +6
Vision-Language-Action (VLA) models unify perception, reasoning, and control in a single policy, but their multi-billion-parameter backbones and diffusion-based action heads make o…
Convergence of fundamental solutions of linear parabolic equations under Cheeger-Gromov convergence
Peng Lu
In this note we show the convergence of the fundamental solutions of the parabolic equations assuming the Cheeger-Gromov convergence of the underlying manifolds and the uniform $L^…
Improved Genetic Algorithm Based on Greedy and Simulated Annealing Ideas for Vascular Robot Ordering Strategy
Zixi Wang, Yubo Huang, Yukai Zhang +3
This study presents a comprehensive approach for optimizing the acquisition, utilization, and maintenance of ABLVR vascular robots in healthcare settings. Medical robotics, particu…
Computationally Efficient Obstacle Avoidance Trajectory Planner for UAVs Based on Heuristic Angular Search Method
Han Chen, Peng Lu
For accomplishing a variety of missions in challenging environments, the capability of navigating with full autonomy while avoiding unexpected obstacles is the most crucial require…
The infimum values of the probability functions for some infinitely divisible distributions motivated by Chvátal's theorem
Ze-Chun Hu, Peng Lu, Qian-Qian Zhou +1
Let denote a binomial random variable with parameters and . Chvátal's theorem says that for any fixed , as ranges over , the probabili…
OJBKQ: Objective-Joint Babai-Klein Quantization
Xinyu Wang, Ziyu Zhao, Peng Lu +2
Post-training quantization (PTQ) is widely used to compress large language models without retraining. However, many existing weight-only methods rely on heuristic objectives and gr…
Like Playing a Video Game: Spatial-Temporal Optimization of Foot Trajectories for Controlled Football Kicking in Bipedal Robots
Wanyue Li, Ji Ma, Minghao Lu +1
Humanoid robot soccer presents several challenges, particularly in maintaining system stability during aggressive kicking motions while achieving precise ball trajectory control. C…
Flying Through a Narrow Gap Using End-to-end Deep Reinforcement Learning Augmented with Curriculum Learning and Sim2Real
Chenxi Xiao, Peng Lu, Qizhi He
Traversing through a tilted narrow gap is previously an intractable task for reinforcement learning mainly due to two challenges. First, searching feasible trajectories is not triv…
Evolution of Yamabe constant under Ricci flow
Shu-Cheng Chang, Peng Lu
In this note under a crucial technical assumption we derive a differential equality of the Yamabe constant where is a solution of the Ricci flow on a…
Identification and Avoidance of Static and Dynamic Obstacles on Point Cloud for UAVs Navigation
Han Chen, Peng Lu
Avoiding hybrid obstacles in unknown scenarios with an efficient flight strategy is a key challenge for unmanned aerial vehicle applications. In this paper, we introduce a techniqu…
NeurIDA: Dynamic Modeling for Effective In-Database Analytics
Lingze Zeng, Naili Xing, Shaofeng Cai +4
Relational Database Management Systems (RDBMS) manage complex, interrelated data and support a broad spectrum of analytical tasks. With the growing demand for predictive analytics,…
On the asymptotic scalar curvature ratio of complete Type I-like ancient solutions to the Ricci flow on non-compact 3-manifolds
Bennett Chow, Peng Lu
The main result of this paper is: Given any constant C, there is such that if a complete, orientable, noncompact odd-dimensional manifold with bounded positive sectional…
SDFP: Speculative Decoding with FIT-Pruned Models for Training-Free and Plug-and-Play LLM Acceleration
Hanyu Wei, Zunhai Su, Peng Lu +4
Large language models (LLMs) underpin interactive multimedia applications such as captioning, retrieval, recommendation, and creative content generation, yet their autoregressive d…
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application
Xueqing Peng, Lingfei Qian, Yan Wang +44
Real-world financial analysis involves information across multiple languages and modalities, from reports and news to scanned filings and meeting recordings. Yet most existing eval…
MARG: MAstering Risky Gap Terrains for Legged Robots with Elevation Mapping
Yinzhao Dong, Ji Ma, Liu Zhao +2
Deep Reinforcement Learning (DRL) controllers for quadrupedal locomotion have demonstrated impressive performance on challenging terrains, allowing robots to execute complex skills…
RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning
Yichao Zhong, Yidan Lu, Yuhang Lu +9
Elite humanoid soccer shooting requires whole-body stability, high-impulse whole-body interactions, and accuracy to targets. Motion tracking-driven reinforcement learning (RL) prov…
: A Route-to-Rerank Post-Training Framework for Multi-Domain Decoder-Only Rerankers
Xinyu Wang, Hanwei Wu, Qingchen Hu +13
Decoder-only rerankers are central to Retrieval-Augmented Generation (RAG). However, generalist models miss domain-specific nuances in high-stakes fields like finance and law, and…
Ricci flow on locally homogeneous closed 4-manifolds
James Isenberg, Martin Jackson, Peng Lu
We discuss the Ricci flow on homogeneous 4-manifolds. After classifying these manifolds, we note that there are families of initial metrics such that we can diagonalize them and th…
Training-Set Distillation for Real-Time UAV Object Tracking
Fan Li, Changhong Fu, Fuling Lin +2
Correlation filter (CF) has recently exhibited promising performance in visual object tracking for unmanned aerial vehicle (UAV). Such online learning method heavily depends on the…
Metric transformations under collapsing of Riemannian manifolds
Bennett Chow, David Glickenstein, Peng Lu
Let (M,g) be a Riemannian manifold with an isometric action of the Lie group G. Let g_G be a left invariant metric on G. Consider the diagonal G action on the product …
Self-supervised Photographic Image Layout Representation Learning
Zhaoran Zhao, Peng Lu, Xujun Peng +1
In the domain of image layout representation learning, the critical process of translating image layouts into succinct vector forms is increasingly significant across diverse appli…
ESVIO: Event-based Stereo Visual Inertial Odometry
Peiyu Chen, Weipeng Guan, Peng Lu
Event cameras that asynchronously output low-latency event streams provide great opportunities for state estimation under challenging situations. Despite event-based visual odometr…
PAMPC: Perception-Aware Model Predictive Control for Quadrotors
Davide Falanga, Philipp Foehn, Peng Lu +1
We present the first perception-aware model predictive control framework for quadrotors that unifies control and planning with respect to action and perception objectives. Our fram…
Enhancing Table Reasoning with Deterministic Table-State Rewards
Tung Sum Thomas Kwok, Xinyu Wang, Hengzhi He +9
Large Language Models (LLMs) struggle with multi-step reasoning over structured tables. The primary reason is the lack of explicit supervision for intermediate reasoning states. Ex…
Monotonicity of functionals along conformal Ricci flow
Fengjiang Li, Peng Lu, Jianhong Wang +1
The main purpose of this note is to construct two functionals of the positive solutions to the conjugate heat equation associated to the metrics evolving by the conformal Ricci flo…
Resonance RoPE: Improving Context Length Generalization of Large Language Models
Suyuchen Wang, Ivan Kobyzev, Peng Lu +2
This paper addresses the challenge of train-short-test-long (TSTL) scenarios in Large Language Models (LLMs) equipped with Rotary Position Embedding (RoPE), where models pre-traine…
ReGLA: Refining Gated Linear Attention
Peng Lu, Ivan Kobyzev, Mehdi Rezagholizadeh +2
Recent advancements in Large Language Models (LLMs) have set themselves apart with their exceptional performance in complex language modelling tasks. However, these models are also…
Global Strong Solutions to the Cauchy Problem of Three-dimensional Isentropic Magnetohydrodynamics Equations with Large Initial Data
Yachun Li, Peng Lu, Zhaoyang Shang
We consider the Cauchy problem to the three-dimensional isentropic compressible Magnetohydrodynamics (MHD) system with density-dependent viscosities. When the initial density is li…
Hyperparameter Optimization for Large Language Model Instruction-Tuning
Christophe Tribes, Sacha Benarroch-Lelong, Peng Lu +1
The fine-tuning of Large Language Models (LLMs) has enabled them to recently achieve milestones in natural language processing applications. The emergence of ever larger LLMs has p…
Calibrated Language Models and How to Find Them with Label Smoothing
Jerry Huang, Peng Lu, Qiuhao Zeng
Recent advances in natural language processing (NLP) have opened up greater opportunities to enable fine-tuned large language models (LLMs) to behave as more powerful interactive a…
Global Existence of Ideal Invicid Compressible and Heat Conductive Fluids with Radial Symmetry
Peng Lu, Yi Zhou
In this paper, we study the global existence of classical solutions to the three dimensional ideal invicid compressible and heat conductive fluids with radial symmetrical data in $…
Local existence of classical solutions to the 3D isentropic compressible Navier-Stokes-Poisson equations with degenerate viscosities and vacuum
Peng Lu, Shaojun Yu
We consider the isentropic compressible Navier-Stokes-Poisson equations with degenerate viscousities and vacuum in a three-dimensional torus. The local well-posedness of classical…
pTNAS: Progressive Neural Architecture Search for Tabular Data
Naili Xing, Shaofeng Cai, Lingze Zeng +4
Recent advances have shifted the paradigm of tabular learning toward tabular foundation models, yet their accuracy relies on a heavy inference cost that scales poorly with context…
LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization
Peng Lu, Ahmad Rashid, Ivan Kobyzev +2
Regularization techniques are crucial to improving the generalization performance and training efficiency of deep neural networks. Many deep learning algorithms rely on weight deca…
Flow-Aided Flight Through Dynamic Clutters From Point To Motion
Bowen Xu, Zexuan Yan, Minghao Lu +7
Challenges in traversing dynamic clutters lie mainly in the efficient perception of the environmental dynamics and the generation of evasive behaviors considering obstacle movement…
Listen, Look, Drive: Coupling Audio Instructions for User-aware VLA-based Autonomous Driving
Ziang Guo, Feng Yang, Xuefeng Zhang +6
Vision Language Action (VLA) models promise an open-vocabulary interface that can translate perceptual ambiguity into semantically grounded driving decisions, yet they still treat…
Special Lagrangian Tori on a Borcea-Voisin Threefold
Peng Lu
We show the existence of special Lagrangian tori on one family of Borcea-Voisin threefolds. We also construct a family of special Lagrangian submanifolds on the total space of the…
RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation
Peng Lu, Tao Jiang, Yining Li +3
Real-time multi-person pose estimation presents significant challenges in balancing speed and precision. While two-stage top-down methods slow down as the number of people in the i…
Flying in Highly Dynamic Environments with End-to-end Learning Approach
Xiyu Fan, Minghao Lu, Bowen Xu +1
Obstacle avoidance for unmanned aerial vehicles like quadrotors is a popular research topic. Most existing research focuses only on static environments, and obstacle avoidance in e…
PoTPTQ: A Two-step Power-of-Two Post-training for LLMs
Xinyu Wang, Vahid Partovi Nia, Peng Lu +4
Large Language Models (LLMs) have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, their deployment is challenging due to the su…
Investigating the Multilingual Calibration Effects of Language Model Instruction-Tuning
Jerry Huang, Peng Lu, Qiuhao Zeng +5
Ensuring that deep learning models are well-calibrated in terms of their predictive uncertainty is essential in maintaining their trustworthiness and reliability, yet despite incre…
Rigidity of complete entire self-shrinking solutions to Kahler-Ricci flow
Gregory Drugan, Peng Lu, Yu Yuan
We show that every complete entire self-shrinking solution on complex Euclidean space to the Kahler-Ricci flow must be generated from a quadratic potential.
On kappa-noncollapsed complete noncompact shrinking gradient Ricci solitons which split at infinity
Bennett Chow, Peng Lu
We discuss some geometric conditions under which a complete noncompact shrinking gradient Ricci soliton will split at infinity.
Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity
Michael R. Metel, Peng Lu, Boxing Chen +2
We present a simple on the fly method for faster inference of large language models. Unlike other (self-)speculative decoding techniques, our method does not require fine-tuning or…
AeCoM: An Aerial Continuum Manipulator with Precise Kinematic Modeling for Variable Loading and Tendon-slacking Prevention
Rui Peng, Zehao Wang, Peng Lu
Aerial robotic systems have raised emerging interests in recent years. In this article, we propose a novel aerial manipulator system that is significantly different from convention…
LVI-GS: Tightly-coupled LiDAR-Visual-Inertial SLAM using 3D Gaussian Splatting
Huibin Zhao, Weipeng Guan, Peng Lu
3D Gaussian Splatting (3DGS) has shown its ability in rapid rendering and high-fidelity mapping. In this paper, we introduce LVI-GS, a tightly-coupled LiDAR-Visual-Inertial mapping…
Collapsing sequences of solutions to the Ricci flow on 3-manifolds with almost nonnegative curvature
Bennett Chow, David Glickenstein, Peng Lu
We study sequences of 3-dimensional solutions to the Ricci flow with almost nonnegative sectional curvatures and diameters tending to infinity. Such sequences may arise from the li…
Learning Human-Like Badminton Skills for Humanoid Robots
Yeke Chen, Shihao Dong, Xiaoyu Ji +10
Realizing versatile and human-like performance in high-demand sports like badminton remains a formidable challenge for humanoid robotics. Unlike standard locomotion or static manip…
FR-Net: Learning Robust Quadrupedal Fall Recovery on Challenging Terrains through Mass-Contact Prediction
Yidan Lu, Yinzhao Dong, Jiahui Zhang +2
Fall recovery for legged robots remains challenging, particularly on complex terrains where traditional controllers fail due to incomplete terrain perception and uncertain interact…
Beyond Hard Writes and Rigid Preservation: Soft Recursive Least-Squares for Lifelong LLM Editing
Xinyu Wang, Sicheng Lyu, Yu Gu +4
Model editing updates a pre-trained LLM with new facts or rules without retraining while preserving unrelated behavior. In real deployment, edits arrive as long streams, creating a…
Learning Agile Flights through Narrow Gaps with Varying Angles using Onboard Sensing
Yuhan Xie, Minghao Lu, Rui Peng +1
This paper addresses the problem of traversing through unknown, tilted, and narrow gaps for quadrotors using Deep Reinforcement Learning (DRL). Previous learning-based methods reli…
Uniqueness of asymptotic cones of complete noncompact shrinking gradient Ricci solitons with Ricci curvature decay
Bennett Chow, Peng Lu
We discuss an elementary consequence of the works of (1) Brett Kotschwar and Lu Wang and (2) Ovidiu Munteanu and Jiaping Wang.
Weak Ricci curvature bounds for Ricci shrinkers
Bennett Chow, Peng Lu, Bo Yang
We show that for a complete Ricci shrinker there exists a sequence of points tending to infinity whose norms of the Ricci tensor grow at most linearly.
A Note on Conformal Ricci Flow
Peng Lu, Jie Qing, Yu Zheng
In this note we study conformal Ricci flow introduced by Arthur Fischer. We use DeTurck's trick to rewrite conformal Ricci flow as a strong parabolic-elliptic partial differential…
Balanced Alignment for Face Recognition: A Joint Learning Approach
Huawei Wei, Peng Lu, Yichen Wei
Face alignment is crucial for face recognition and has been widely adopted. However, current practice is too simple and under-explored. There lacks an understanding of how importan…
Global well-posedness and asymptotic behavior of large strong solutions to the 3D full compressible Navier-Stokes equations with temperature-dependent coefficients
Yachun Li, Peng Lu, Zhaoyang Shang
It is well known that the global well-posedness of the Navier-Stokes equations with temperature-dependent coefficients is a challenging problem, especially in multi-dimensional spa…
Mamba Modulation: On the Length Generalization of Mamba
Peng Lu, Jerry Huang, Qiuhao Zeng +4
The quadratic complexity of the attention mechanism in Transformer models has motivated the development of alternative architectures with sub-quadratic scaling, such as state-space…
VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering
Zhenghan Tai, Hanwei Wu, Qingchen Hu +24
Retrieval-Augmented Generation (RAG) is becoming increasingly essential for Question Answering (QA) in the financial sector, where accurate and contextually grounded insights from…
VinT-6D: A Large-Scale Object-in-hand Dataset from Vision, Touch and Proprioception
Zhaoliang Wan, Yonggen Ling, Senlin Yi +9
This paper addresses the scarcity of large-scale datasets for accurate object-in-hand pose estimation, which is crucial for robotic in-hand manipulation within the ``Perception-Pla…
A necessary and sufficient condition for Ricci shrinkers to have positive AVR
Bennett Chow, Peng Lu, Bo Yang
In this short note we observe that a recent result of C.-W. Chen meshes well with earlier work of H.-D. Cao and D.-T. Zhou, O. Munteanu, J. Carrillo and L. Ni, and S.-J. Zhang to g…
NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions
Shizheng Hou, Wenqi Pei, Nuo Chen +3
Natural Language to SQL (NL2SQL) technology empowers non-expert users to query relational databases without requiring SQL expertise. While large language models (LLMs) have greatly…
Mild Ricci curvature restrictions for steady gradient Ricci solitons
Bennett Chow, Peng Lu
We show for a complete noncompact steady Ricci soliton that there exists a sequence {x_i} of points tending to infinity such that |Rc|(x_i) limits to zero.