Publications (111)
From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks
Changpeng Yang, Jinyang Wu, Yuchen Liu +9
Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each…
DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog
Feilong Chen, Fandong Meng, Jiaming Xu +3
Visual Dialog is a vision-language task that requires an AI agent to engage in a conversation with humans grounded in an image. It remains a challenging task since it requires the…
Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals
Jing Shi, Xuankai Chang, Pengcheng Guo +5
Neural sequence-to-sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus…
Settling the Sharp Reconstruction Thresholds of Random Graph Matching
Yihong Wu, Jiaming Xu, Sophie H. Yu
This paper studies the problem of recovering the hidden vertex correspondence between two edge-correlated random graphs. We focus on the Gaussian model where the two graphs are com…
MARCA: Mamba Accelerator with ReConfigurable Architecture
Jinhao Li, Shan Huang, Jiaming Xu +4
We propose a Mamba accelerator with reconfigurable architecture, MARCA.We propose three novel approaches in this paper. (1) Reduction alternative PE array architecture for both lin…
On the Accuracy of the Wyner Model in Cellular Networks
Jiaming Xu, Jun Zhang, Jeffery G. Andrews
The Wyner model has been widely used to model and analyze cellular networks due to its simplicity and analytical tractability. Its key aspects include fixed user locations and the…
The Power of -hops in Matching Power-Law Graphs
Liren Yu, Jiaming Xu, Xiaojun Lin
This paper studies seeded graph matching for power-law graphs. Assume that two edge-correlated graphs are independently edge-sampled from a common parent graph with a power-law deg…
Learning with Shared Representations: Statistical Rates and Efficient Algorithms
Xiaochun Niu, Lili Su, Jiaming Xu +1
Collaborative learning through latent shared feature representations enables heterogeneous clients to train personalized models with improved performance and reduced sample complex…
Consistent recovery threshold of hidden nearest neighbor graphs
Jian Ding, Yihong Wu, Jiaming Xu +1
Motivated by applications such as discovering strong ties in social networks and assembling genome subsequences in biology, we study the problem of recovering a hidden -nearest…
Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling
Peng Zhou, Zhenyu Qi, Suncong Zheng +3
Recurrent Neural Network (RNN) is one of the most popular architectures used in Natural Language Processsing (NLP) tasks because its recurrent structure is very suitable to process…
Local Algorithms for Block Models with Side Information
Elchanan Mossel, Jiaming Xu
There has been a recent interest in understanding the power of local algorithms for optimization and inference problems on sparse graphs. Gamarnik and Sudan (2014) showed that loca…
SpeContext: Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMs
Jiaming Xu, Jiayi Pan, Hanzhen Wang +4
In this paper, we point out that the objective of the retrieval algorithms is to align with the LLM, which is similar to the objective of knowledge distillation in LLMs. We analyze…
LiMuSE: Lightweight Multi-modal Speaker Extraction
Qinghua Liu, Yating Huang, Yunzhe Hao +2
Multi-modal cues, including spatial information, facial expression and voiceprint, are introduced to the speech separation and speaker extraction tasks to serve as complementary in…
Self-Taught Convolutional Neural Networks for Short Text Clustering
Jiaming Xu, Bo Xu, Peng Wang +3
Short text clustering is a challenging problem due to its sparseness of text representation. Here we propose a flexible Self-Taught Convolutional neural network framework for Short…
Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective
Jinhao Li, Jiaming Xu, Shan Huang +9
Large Language Models (LLMs) have demonstrated remarkable capabilities across various fields, from natural language understanding to text generation. Compared to non-generative LLM…
Airy line ensemble and its Laplace transform
Vadim Gorin, Jiaming Xu, Lingfu Zhang
The Airy line ensemble is a random collection of continuous curves, which should serve as a universal edge scaling limit in problems related to eigenvalues of random matrices…
Mutual Information in Rank-One Matrix Estimation
Florent Krzakala, Jiaming Xu, Lenka Zdeborová
We consider the estimation of a n-dimensional vector x from the knowledge of noisy and possibility non-linear element-wise measurements of xxT , a very generic problem that contain…
Perturbed Beta Corners Process
Leonid Petrov, Jiaming Xu
The authors define a perturbed β‑corners process by adding a deterministic diagonal matrix to Gaussian random matrices, extend the construction to all β>0, and analyze its large‑β…
DistFlow: A Fully Distributed RL Framework for Scalable and Efficient LLM Post-Training
Zhixin Wang, Jiaming Xu, Tianyi Zhou +10
Effectively scaling Reinforcement Learning (RL) is crucial for enhancing the reasoning and alignment of Large Language Models. The massive data and complex execution flows inherent…
One-pass Stochastic Gradient Descent in Overparametrized Two-layer Neural Networks
Jiaming Xu, Hanjing Zhu
There has been a recent surge of interest in understanding the convergence of gradient descent (GD) and stochastic gradient descent (SGD) in overparameterized neural networks. Most…
Learner-Private Convex Optimization
Jiaming Xu, Kuang Xu, Dana Yang
Convex optimization with feedback is a framework where a learner relies on iterative queries and feedback to arrive at the minimizer of a convex function. It has gained considerabl…
Soft edge limit of the Laguerre beta-ensemble at the lower edge
Yun Li, Benedek Valkó, Jiaming Xu
We show that the lower edge of the appropriately scaled size Laguerre beta-ensemble with parameter converges to the process as wh…
Information Limits for Recovering a Hidden Community
Bruce Hajek, Yihong Wu, Jiaming Xu
We study the problem of recovering a hidden community of cardinality from an symmetric data matrix , where for distinct indices , if …
Random Graph Matching in Geometric Models: the Case of Complete Graphs
Haoyu Wang, Yihong Wu, Jiaming Xu +1
This paper studies the problem of matching two complete graphs with edge weights correlated through latent geometries, extending a recent line of research on random graph matching…
Submatrix localization via message passing
Bruce Hajek, Yihong Wu, Jiaming Xu
The principal submatrix localization problem deals with recovering a principal submatrix of elevated mean in a large symmetric matrix subject to additi…
POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion
Wen Chen, Pipei Huang, Jiaming Xu +7
Increasing demand for fashion recommendation raises a lot of challenges for online shopping platforms and fashion communities. In particular, there exist two requirements for fashi…
Testing network correlation efficiently via counting trees
Cheng Mao, Yihong Wu, Jiaming Xu +1
We propose a new procedure for testing whether two networks are edge-correlated through some latent vertex correspondence. The test statistic is based on counting the co-occurrence…
WASE: Learning When to Attend for Speaker Extraction in Cocktail Party Environments
Yunzhe Hao, Jiaming Xu, Peng Zhang +1
In the speaker extraction problem, it is found that additional information from the target speaker contributes to the tracking and extraction of the target speaker, which includes…
SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting
Jiaming Xu, Jiayi Pan, Yongkang Zhou +5
Early exiting has recently emerged as a promising technique for accelerating large language models (LLMs) by effectively reducing the hardware computation and memory access. In thi…
Spectral Graph Matching and Regularized Quadratic Relaxations I: The Gaussian Model
Zhou Fan, Cheng Mao, Yihong Wu +1
Graph matching aims at finding the vertex correspondence between two unlabeled graphs that maximizes the total edge weight correlation. This amounts to solving a computationally in…
Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization
Jinhao Li, Jiaming Xu, Shiyao Li +4
Large language models (LLMs) have demonstrated impressive abilities in various domains while the inference cost is expensive. Many previous studies exploit quantization methods to…
Statistical Problems with Planted Structures: Information-Theoretical and Computational Limits
Yihong Wu, Jiaming Xu
Over the past few years, insights from computer science, statistical physics, and information theory have revealed phase transitions in a wide array of high-dimensional statistical…
Seeded Graph Matching via Large Neighborhood Statistics
Elchanan Mossel, Jiaming Xu
We study a well known noisy model of the graph isomorphism problem. In this model, the goal is to perfectly recover the vertex correspondence between two edge-correlated ErdÅs-Ré…
ProUIE: A Macro-to-Micro Progressive Learning Method for LLM-based Universal Information Extraction
Wenda Liu, Zhigang Song, Shuai Nie +11
LLM-based universal information extraction (UIE) methods often rely on additional information beyond the original training data, which increases training complexity yet often yield…
Airy limit for -additions through Dunkl operators
David Keating, Jiaming Xu
It is well known that the edge limit of Gaussian/Laguerre Beta-ensembles, as well as a large class of -ensembles is given by the point process. We extend th…
Testing correlation of unlabeled random graphs
Yihong Wu, Jiaming Xu, Sophie H. Yu
We study the problem of detecting the edge correlation between two random graphs with unlabeled nodes. This is formalized as a hypothesis testing problem, where under the null…
Information-theoretic bounds and phase transitions in clustering, sparse PCA, and submatrix localization
Jess Banks, Cristopher Moore, Nicolas Verzelen +2
We study the problem of detecting a structured, low-rank signal matrix corrupted with additive Gaussian noise. This includes clustering in a Gaussian mixture model, sparse PCA, and…
Speaker and Direction Inferred Dual-channel Speech Separation
Chenxing Li, Jiaming Xu, Nima Mesgarani +1
Most speech separation methods, trying to separate all channel sources simultaneously, are still far from having enough general- ization capabilities for real scenarios where the n…
Law of Large Numbers for continuous -particle ensembles at fixed temperature
Cesar Cuenca, Jiaming Xu
In this paper, we find necessary and sufficient conditions for the Law of Large Numbers of averaged empirical measures of -particle ensembles, in terms of the asymptotics of the…
Finding Planted Cycles in a Random Graph
Julia Gaudio, Colin Sandon, Jiaming Xu +1
In this paper, we study the problem of finding a collection of planted cycles in an \ER random graph , in analogy to the famous Planted Clique Problem.…
A Survey on Efficient Inference for Large Language Models
Zixuan Zhou, Xuefei Ning, Ke Hong +12
Large Language Models (LLMs) have attracted extensive attention due to their remarkable performance across various tasks. However, the substantial computational and memory requirem…
Hidden Hamiltonian Cycle Recovery via Linear Programming
Vivek Bagaria, Jian Ding, David Tse +2
We introduce the problem of hidden Hamiltonian cycle recovery, where there is an unknown Hamiltonian cycle in an -vertex complete graph that needs to be inferred from noisy edge…
Rectangular Matrix Additions in Low and High Temperatures
Jiaming Xu
We study the addition of two independent random rectangular matrices with invariant distributions in two limiting regimes, where the parameter (inverse temperature…
Short Text Hashing Improved by Integrating Multi-Granularity Topics and Tags
Jiaming Xu, Bo Xu, Guanhua Tian +3
Due to computational and storage efficiencies of compact binary codes, hashing has been widely used for large-scale similarity search. Unfortunately, many existing hashing methods…
Convex Relaxation Methods for Community Detection
Xiaodong Li, Yudong Chen, Jiaming Xu
This paper surveys recent theoretical advances in convex optimization approaches for community detection. We introduce some important theoretical techniques and results for establi…
FAST-LIVGO: A Degeneracy-Robust LiDAR-Inertial-Visual-GNSS Fusion Odometry
Zhiyu Chen, Chunran Zheng, Jiayu Wen +4
Robust state estimation and mapping in long-term, large-scale, and highly dynamic environments remains a key challenge in robotics. Existing LiDAR-Inertial-Visual Odometry (LIVO) s…
Optimality of Random Regular Graphs in Sparse Network Designs
Weijia Li, Xiaochun Niu, Yehua Wei +1
The problems of designing sparse networks arise frequently in resource allocation and operations research. In production systems, for example, sparse process flexibility designs ar…
Computational Lower Bounds for Community Detection on Random Graphs
Bruce Hajek, Yihong Wu, Jiaming Xu
This paper studies the problem of detecting the presence of a small dense community planted in a large ErdÅs-Rényi random graph , where the edge probability wit…
The Supermarket Game
Jiaming Xu, Bruce Hajek
A supermarket game is considered with FCFS queues with unit exponential service rate and global Poisson arrival rate . Upon arrival each customer chooses a number of queu…
FlashDecoding++: Faster Large Language Model Inference on GPUs
Ke Hong, Guohao Dai, Jiaming Xu +6
As the Large Language Model (LLM) becomes increasingly important in various domains. However, the following challenges still remain unsolved in accelerating LLM inference: (1) Sync…
HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices
HyperAI Team, Yuchen Liu, Kaiyang Han +26
Current multimodal large lanauge models possess strong perceptual and reasoning capabilities, however high computational and memory requirements make them difficult to deploy direc…
Securing Distributed Gradient Descent in High Dimensional Statistical Learning
Lili Su, Jiaming Xu
We consider unreliable distributed learning systems wherein the training data is kept confidential by external workers, and the learner has to interact closely with those workers t…
MIMO Self-attentive RNN Beamformer for Multi-speaker Speech Separation
Xiyun Li, Yong Xu, Meng Yu +4
Recently, our proposed recurrent neural network (RNN) based all deep learning minimum variance distortionless response (ADL-MVDR) beamformer method yielded superior performance ove…
SeedGNN: Graph Neural Networks for Supervised Seeded Graph Matching
Liren Yu, Jiaming Xu, Xiaojun Lin
There is a growing interest in designing Graph Neural Networks (GNNs) for seeded graph matching, which aims to match two unlabeled graphs using only topological information and a s…
Spectral Graph Matching and Regularized Quadratic Relaxations II: ErdÅs-Rényi Graphs and Universality
Zhou Fan, Cheng Mao, Yihong Wu +1
We analyze a new spectral graph matching algorithm, GRAph Matching by Pairwise eigen-Alignments (GRAMPA), for recovering the latent vertex correspondence between two unlabeled, edg…
High-Dimensional Procrustes Matching via Tree Counts
Xiaochun Niu, Tselil Schramm, Jiaming Xu
Suppose we observe two sets of Gaussian vectors in , with the promise that, after applying a permutation of and a rotation of , the two sets a…
Optimal query complexity for private sequential learning against eavesdropping
Jiaming Xu, Kuang Xu, Dana Yang
We study the query complexity of a learner-private sequential learning problem, motivated by the privacy and security concerns due to eavesdropping that arise in practical applicat…
Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents
Zhijie Ding, Weinan Hong, Zicheng Zhu +6
Multimodal large language models (MLLMs) have substantially advanced mobile agents, yet proactive mobile assistance remains challenging because agents must decide \emph{when} to in…
Audio-visual Speech Separation with Adversarially Disentangled Visual Representation
Peng Zhang, Jiaming Xu, Jing shi +2
Speech separation aims to separate individual voice from an audio mixture of multiple simultaneous talkers. Although audio-only approaches achieve satisfactory performance, they bu…
A Proof of The Changepoint Detection Threshold Conjecture in Preferential Attachment Models
Hang Du, Shuyang Gong, Jiaming Xu
We investigate the problem of detecting and estimating a changepoint in the attachment function of a network evolving according to a preferential attachment model on vertices,…
Edge Label Inference in Generalized Stochastic Block Models: from Spectral Theory to Impossibility Results
Jiaming Xu, Laurent Massoulié, Marc Lelarge
The classical setting of community detection consists of networks exhibiting a clustered structure. To more accurately model real systems we consider a class of networks (i) whose…
Multi-Modal Manipulation via Multi-Modal Policy Consensus
Haonan Chen, Jiaming Xu, Hongyu Chen +7
Effectively integrating diverse sensory modalities is crucial for robotic manipulation. However, the typical approach of feature concatenation is often suboptimal: dominant modalit…
Convexified Modularity Maximization for Degree-corrected Stochastic Block Models
Yudong Chen, Xiaodong Li, Jiaming Xu
The stochastic block model (SBM) is a popular framework for studying community detection in networks. This model is limited by the assumption that all nodes in the same community a…
SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization
Jinyang Wu, Changpeng Yang, Yuhao Shen +9
Reinforcement learning with verifiable rewards has emerged as a powerful paradigm for training intelligent agents. However, existing methods typically employ binary rewards that fa…
Speaker-Conditional Chain Model for Speech Separation and Extraction
Jing Shi, Jiaming Xu, Yusuke Fujita +2
Speech separation has been extensively explored to tackle the cocktail party problem. However, these studies are still far from having enough generalization capabilities for real s…
LIT-GS: LiDAR-Inertial-Thermal Gaussian Splatting for Illumination-Robust Mapping
Shikuan Shi, Chunran Zheng, Jiaming Xu +3
Gaussian Splatting has enabled real-time neural rendering, yet existing LiDAR-inertial-visual (LIV) Gaussian mapping pipelines remain fragile under illumination changes and texture…
Rates of Convergence of Spectral Methods for Graphon Estimation
Jiaming Xu
This paper studies the problem of estimating the grahpon model - the underlying generating mechanism of a network. Graphon estimation arises in many applications such as predicting…
Unified Multimodal and Multilingual Retrieval via Multi-Task Learning with NLU Integration
Xinyuan Zhang, Lina Zhang, Lisung Chen +6
Multimodal retrieval systems typically employ Vision Language Models (VLMs) that encode images and text independently into vectors within a shared embedding space. Despite incorpor…
SB-RF: Schrödinger Bridge Rectified Flow for One-Step Robust Speech Enhancement
Caixia Lu, Xueyang Lv, Penglong Hu +1
Generative models have shown promising results for speech enhancement (SE), but they often rely on multi-step inference, limiting low-latency deployment. We propose SB-RF, a one-st…
The broken sample problem revisited: Proof of a conjecture by Bai-Hsing and high-dimensional extensions
Simiao Jiao, Yihong Wu, Jiaming Xu
We revisit the classical broken sample problem: Two samples of i.i.d.\ data points and are observed w…
All-or-Nothing Phenomena: From Single-Letter to High Dimensions
Galen Reeves, Jiaming Xu, Ilias Zadik
We consider the linear regression problem of estimating a -dimensional vector from observations , where for a real…
Sharp Information-Theoretic Thresholds for Shuffled Linear Regression
Leon Lufkin, Yihong Wu, Jiaming Xu
This paper studies the problem of shuffled linear regression, where the correspondence between predictors and responses in a linear model is obfuscated by a latent permutation. Spe…
Resolution of the Detection Threshold Conjecture for Random Geometric Graphs in the Regime
Hang Du, Cheng Mao, Nike Sun +2
A random geometric graph (RGG) is generated by first sampling latent points independently and uniformly from the unit sphere in , and then connecting…
The planted matching problem: Sharp threshold and infinite-order phase transition
Jian Ding, Yihong Wu, Jiaming Xu +1
We study the problem of reconstructing a perfect matching hidden in a randomly weighted bipartite graph. The edge set includes every node pair in and each o…
Learning from Comparisons and Choices
Sahand Negahban, Sewoong Oh, Kiran K. Thekumparampil +1
When tracking user-specific online activities, each user's preference is revealed in the form of choices and comparisons. For example, a user's purchase history is a record of her…
ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices
Dezhi Kong, Zhengzhao Feng, Qiliang Liang +12
Multimodal large language models (MLLMs) have made significant progress in mobile agent development, yet their capabilities are predominantly confined to a reactive paradigm, where…
Global Convergence of Federated Learning for Mixed Regression
Lili Su, Jiaming Xu, Pengkun Yang
This paper studies the problem of model training under Federated Learning when clients exhibit cluster structure. We contextualize this problem in mixed regression, where each clie…
Efficient random graph matching via degree profiles
Jian Ding, Zongming Ma, Yihong Wu +1
Random graph matching refers to recovering the underlying vertex correspondence between two random graphs with correlated edges; a prominent example is when the two random graphs a…
Jointly Clustering Rows and Columns of Binary Matrices: Algorithms and Trade-offs
Jiaming Xu, Rui Wu, Kai Zhu +3
In standard clustering problems, data points are represented by vectors, and by stacking them together, one forms a data matrix with row or column cluster structure. In this paper,…
Recovering a Hidden Community Beyond the Kesten-Stigum Threshold in Time
Bruce Hajek, Yihong Wu, Jiaming Xu
Community detection is considered for a stochastic block model graph of n vertices, with K vertices in the planted community, edge probability p for pairs of vertices both in the c…
Statistical-Computational Tradeoffs in Planted Problems and Submatrix Localization with a Growing Number of Clusters and Submatrices
Yudong Chen, Jiaming Xu
We consider two closely related problems: planted clustering and submatrix localization. The planted clustering problem assumes that a random graph is generated based on some under…
Learning Coordinated Bimanual Manipulation Policies using State Diffusion and Inverse Dynamics Models
Haonan Chen, Jiaming Xu, Lily Sheng +4
When performing tasks like laundry, humans naturally coordinate both hands to manipulate objects and anticipate how their actions will change the state of the clothes. However, ach…
Graph Matching with Partially-Correct Seeds
Liren Yu, Jiaming Xu, Xiaojun Lin
Graph matching aims to find the latent vertex correspondence between two edge-correlated graphs and has found numerous applications across different fields. In this paper, we study…
Semidefinite Programs for Exact Recovery of a Hidden Community
Bruce Hajek, Yihong Wu, Jiaming Xu
We study a semidefinite programming (SDP) relaxation of the maximum likelihood estimation for exactly recovering a hidden community of cardinality from an symmetri…
BalanceGS: Algorithm-System Co-design for Efficient 3D Gaussian Splatting Training on GPU
Junyi Wu, Jiaming Xu, Jinhao Li +4
3D Gaussian Splatting (3DGS) has emerged as a promising 3D reconstruction technique. The traditional 3DGS training pipeline follows three sequential steps: Gaussian densification,…
Federated Learning in the Presence of Adversarial Client Unavailability
Lili Su, Ming Xiang, Jiaming Xu +1
Federated learning is a decentralized machine learning framework that enables collaborative model training without revealing raw data. Due to the diverse hardware and software limi…
Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks
Jing Shi, Jiaming Xu, Yiqun Yao +1
Deep neural networks have shown superior performance in many regimes to remember familiar patterns with large amounts of data. However, the standard supervised deep learning paradi…
Random graph matching at Otter's threshold via counting chandeliers
Cheng Mao, Yihong Wu, Jiaming Xu +1
We propose an efficient algorithm for graph matching based on similarity scores constructed from counting a certain family of weighted trees rooted at each vertex. For two ErdÅs-R…
Hierarchical Memory Networks for Answer Selection on Unknown Words
Jiaming Xu, Jing Shi, Yiqun Yao +2
Recently, end-to-end memory networks have shown promising results on Question Answering task, which encode the past facts into an explicit memory and perform reasoning ability by m…
Clustering and Inference From Pairwise Comparisons
Rui Wu, Jiaming Xu, R. Srikant +3
Given a set of pairwise comparisons, the classical ranking problem computes a single ranking that best represents the preferences of all users. In this paper, we study the problem…
GUI-CEval: A Hierarchical and Comprehensive Chinese Benchmark for Mobile GUI Agents
Yang Li, Yuchen Liu, Haoyu Lu +8
Recent progress in Multimodal Large Language Models (MLLMs) has enabled mobile GUI agents capable of visual perception, cross-modal reasoning, and interactive control. However, exi…
Broadcast Channels with Delayed Finite-Rate Feedback: Predict or Observe?
Jiaming Xu, Jeffrey G. Andrews, Syed A. Jafar
Most multiuser precoding techniques require accurate transmitter channel state information (CSIT) to maintain orthogonality between the users. Such techniques have proven quite fra…
Improved queue-size scaling for input-queued switches via graph factorization
Jiaming Xu, Yuan Zhong
This paper studies the scaling of the expected total queue size in an input-queued switch, as a function of both the load and the system scale . We provide a ne…
Random geometric graphs with smooth kernels: sharp detection threshold and a spectral conjecture
Cheng Mao, Yihong Wu, Jiaming Xu
A random geometric graph (RGG) with kernel is constructed by first sampling latent points independently and uniformly from the -dimensional unit sphere, the…
Phase Transitions in Planted k-Factor Recovery
Julia Gaudio, Colin Sandon, Jiaming Xu +1
This paper studies the problem of inferring a -factor, specifically a spanning -regular graph, planted within an Erdos-Renyi random graph . We show that as the ave…
Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent
Yudong Chen, Lili Su, Jiaming Xu
We consider the problem of distributed statistical machine learning in adversarial settings, where some unknown and time-varying subset of working machines may be compromised and b…
SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
Hanzhen Wang, Jiaming Xu, Yushun Xiang +4
Pruning is a typical acceleration technique for compute-bound models by removing computation on unimportant values. Recently, it has been applied to accelerate Vision-Language-Acti…
SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation
Jiayi Pan, Jiaming Xu, Yongkang Zhou +1
Feature caching has recently emerged as a promising method for diffusion model acceleration. It effectively alleviates the inefficiency problem caused by high computational require…
The Planted Spanning Tree Problem
Mehrdad Moharrami, Cristopher Moore, Jiaming Xu
We study the problem of detecting and recovering a planted spanning tree hidden within a complete, randomly weighted graph . Specifically, each edge has a non-nega…
A Non-parametric View of FedAvg and FedProx: Beyond Stationary Points
Lili Su, Jiaming Xu, Pengkun Yang
Federated Learning (FL) is a promising decentralized learning framework and has great potentials in privacy preservation and in lowering the computation load at the cloud. Recent w…