Search Results for author:
Found 75 papers, 21 papers with code
qNBO: quasi-Newton Meets Bilevel Optimization
Bilevel optimization, addressing challenges in hierarchical learning tasks, has gained significant interest in machine learning.
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Moreover, we present effective long2short methods that use long-CoT techniques to improve short-CoT models, yielding state-of-the-art short-CoT reasoning results -- e. g., 60. 8 on AIME, 94. 6 on MATH500, 47. 3 on LiveCodeBench -- outperforming existing short-CoT models such as GPT-4o and Claude Sonnet 3. 5 by a large margin (up to +550%).
Adaptive Sampled Softmax with Inverted Multi-Index: Methods, Theory and Applications
The softmax function is a cornerstone of multi-class classification, integral to a wide range of machine learning applications, from large-scale retrieval and ranking models to advanced large language models.
CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models
Large Vision-Language Models (LVLMs) have recently demonstrated amazing success in multi-modal tasks, including advancements in Multi-modal Chain-of-Thought (MCoT) reasoning.
GAOKAO-Eval: Does high scores truly reflect strong capabilities in LLMs?
Large Language Models (LLMs) are commonly evaluated using human-crafted benchmarks, under the premise that higher scores implicitly reflect stronger human-like performance.
Multi-Aircraft Scheduling Optimization in Urban Environments
With the increasing development of intelligent transportation systems and advancements in aviation technology, the concept of Advanced Air Mobility (AAM) is gaining attention.
Learning Deep Tree-based Retriever for Efficient Recommendation: Theory and Method
Although advancements in deep learning have significantly enhanced the recommendation accuracy of deep recommendation models, these methods still suffer from low recommendation efficiency.
AcousAF: Acoustic Sensing-Based Atrial Fibrillation Detection System for Mobile Phones
In addition, we propose a well-designed framework comprised of pulse wave probing, pulse wave extraction, and AF detection to ensure accurate and reliable AF detection.
Learning Camouflaged Object Detection from Noisy Pseudo Label
Existing Camouflaged Object Detection (COD) methods rely heavily on large-scale pixel-annotated training sets, which are both time-consuming and labor-intensive.
Increasing certainty in systems biology models using Bayesian multimodel inference
Mathematical models are indispensable to the system biology toolkit for studying the structure and behavior of intracellular signaling networks.
SPABA: A Single-Loop and Probabilistic Stochastic Bilevel Algorithm Achieving Optimal Sample Complexity
While stochastic bilevel optimization methods have been extensively studied for addressing large-scale nested optimization problems in machine learning, it remains an open question whether the optimal complexity bounds for solving bilevel optimization are the same as those in single-level optimization.
M$^3$CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought
In addition, we highlight that the current VLLMs still struggle to correctly reason in M$^3$CoT and there remains a large gap between existing VLLMs and human performance in M$^3$CoT, despite their superior results on previous MCoT benchmarks.
Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-loop and Hessian-free Solution Strategy
This work focuses on addressing two major challenges in the context of large-scale nonconvex Bi-Level Optimization (BLO) problems, which are increasingly applied in machine learning due to their ability to model nested structures.
Heuristic Solution to Joint Deployment and Beamforming Design for STAR-RIS Aided Networks
This paper tackles the deployment challenges of Simultaneous Transmitting and Reflecting Reconfigurable Intelligent Surface (STAR-RIS) in communication systems.
Constrained Bi-Level Optimization: Proximal Lagrangian Value function Approach and Hessian-free Algorithm
To address this challenge, we begin by devising a smooth proximal Lagrangian value function to handle the constrained lower-level problem.
Physics-Informed Generator-Encoder Adversarial Networks with Latent Space Matching for Stochastic Differential Equations
We propose a new class of physics-informed neural networks, called Physics-Informed Generator-Encoder Adversarial Networks, to effectively address the challenges posed by forward, inverse, and mixed problems in stochastic differential equations.
AFLOW: Developing Adversarial Examples under Extremely Noise-limited Settings
Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks.
Deep Reinforcement Learning Enabled Joint Deployment and Beamforming in STAR-RIS Assisted Networks
The paper constructs a STAR-RIS assisted multi-user multiple-input single-output (MU-MISO) mobile wireless network and jointly optimizes the dynamic deployment strategy of STAR-RIS and the hybrid beamforming strategy to maximize the long-term total communication rate of users.
Interactive Graph Convolutional Filtering
Furthermore, we employ Bayesian meta-learning methods to effectively address the cold-start problem and derive theoretical regret bounds for our proposed method, ensuring a robust performance guarantee.
IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse
Humans have the ability to reuse previously learned policies to solve new tasks quickly, and reinforcement learning (RL) agents can do the same by transferring knowledge from source policies to a related target task.
TBIN: Modeling Long Textual Behavior Data for CTR Prediction
Click-through rate (CTR) prediction plays a pivotal role in the success of recommendations.
Moreau Envelope Based Difference-of-weakly-Convex Reformulation and Algorithm for Bilevel Programs
In a recent study by Ye et al. (2023), a value function-based difference of convex algorithm was introduced to address bilevel programs.
Offline Meta Reinforcement Learning with In-Distribution Online Adaptation
We find a return-based uncertainty quantification for IDAQ that performs effectively.
HST-MRF: Heterogeneous Swin Transformer with Multi-Receptive Field for Medical Image Segmentation
In this study, we proposed a Heterogeneous Swin Transformer with Multi-Receptive Field (HST-MRF) model based on U-shaped networks for medical image segmentation.
Hierarchical Optimization-Derived Learning
In recent years, by utilizing optimization techniques to formulate the propagation of deep model, a variety of so-called Optimization-Derived Learning (ODL) approaches have been proposed to address diverse learning and vision tasks.
Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity
Gradient methods have become mainstream techniques for Bi-Level Optimization (BLO) in learning fields.
Decision-Making Context Interaction Network for Click-Through Rate Prediction
Click-through rate (CTR) prediction is crucial in recommendation and online advertising systems.
Hyperuniform disordered parametric loudspeaker array
A steerable parametric loudspeaker array is known for its directivity and narrow beam width.
The Devil is in the Crack Orientation: A New Perspective for Crack Detection
However, the vanilla adaptation of the existing oriented object detection methods to the crack detection tasks will result in limited performance, due to the boundary discontinuity issue and the ambiguities in sub-crack orientation.
Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report
In this Mobile AI challenge, the target was to develop an efficient end-to-end AI-based bokeh effect rendering approach that can run on modern smartphone GPUs using TensorFlow Lite.
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report
While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints.
Less Emphasis on Difficult Layer Regions: Curriculum Learning for Singularly Perturbed Convection-Diffusion-Reaction Problems
Although Physics-Informed Neural Networks (PINNs) have been successfully applied in a wide variety of science and engineering fields, they can fail to accurately predict the underlying solution in slightly challenging convection-diffusion-reaction problems.
CUP: Critic-Guided Policy Reuse
The ability to reuse previous policies is an important aspect of human intelligence.
KD-SCFNet: Towards More Accurate and Efficient Salient Object Detection via Knowledge Distillation
Most existing salient object detection (SOD) models are difficult to apply due to the complex and huge model structures.
Optimization-Derived Learning with Essential Convergence Analysis of Training and Hyper-training
Recently, Optimization-Derived Learning (ODL) has attracted attention from learning and vision areas, which designs learning models from the perspective of optimization.
Value Function Based Difference-of-Convex Algorithm for Bilevel Hyperparameter Selection Problems
Gradient-based optimization methods for hyperparameter tuning guarantee theoretical convergence to stationary solutions when for fixed upper-level variable values, the lower level of the bilevel program is strongly convex (LLSC) and smooth (LLS).
NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results
The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i. e. solutions can not exceed a given number of operations).
Towards Extremely Fast Bilevel Optimization with Self-governed Convergence Guarantees
Gradient methods have become mainstream techniques for Bi-Level Optimization (BLO) in learning and vision fields.
Efficient Progressive High Dynamic Range Image Restoration via Attention and Alignment Network
In this paper, we propose a lightweight neural network called Efficient Attention-and-alignment-guided Progressive Network (EAPNet) for the challenge NTIRE 2022 HDR Track 1 and Track 2.
DSRRTracker: Dynamic Search Region Refinement for Attention-based Siamese Multi-Object Tracking
Many multi-object tracking (MOT) methods follow the framework of "tracking by detection", which associates the target objects-of-interest based on the detection results.
$Radar^2$: Passive Spy Radar Detection and Localization using COTS mmWave Radar
Specifically, we propose a novel \textit{Frequency Component Detection} method to detect the existence of mmWave signals, distinguish between mmWave radar and WiGig signals using a waveform classifier based on a convolutional neural network (CNN), and localize spy radars using triangulation based on the detector's observations at multiple anchor points.
Adversarial Attack via Dual-Stage Network Erosion
Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations.
Geometry-Aware Guided Loss for Deep Crack Recognition
Despite the substantial progress of deep models for crack recognition, due to the inconsistent cracks in varying sizes, shapes, and noisy background textures, there still lacks the discriminative power of the deeply learned features when supervised by the cross-entropy loss.
Distributed Optimal Output Consensus of Uncertain Nonlinear Multi-Agent Systems over Unbalanced Directed Networks via Output Feedback
In this note, a novel observer-based output feedback control approach is proposed to address the distributed optimal output consensus problem of uncertain nonlinear multi-agent systems in the normal form over unbalanced directed graphs.
ViDA-MAN: Visual Dialog with Digital Humans
We demonstrate ViDA-MAN, a digital-human agent for multi-modal interaction, which offers realtime audio-visual responses to instant speech inquiries.
Robust Multi-view Registration of Point Sets with Laplacian Mixture Model
The proposed method assumes each data point is generated by a Laplacian Mixture Model (LMM), where its centers are determined by the corresponding points in other point sets.
Value-Function-based Sequential Minimization for Bi-level Optimization
We also extend BVFSM to address BLO with additional functional constraints.
Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond
In particular, by introducing an auxiliary as initialization to guide the optimization dynamics and designing a pessimistic trajectory truncation operation, we construct a reliable approximate version of the original BLO in the absence of LLC hypothesis.
Hybrid Beamforming for RIS-Aided Communications: Fitness Landscape Analysis and Niching Genetic Algorithm
To investigate the number and distribution of local optima, we conduct a fitness landscape analysis on the sum rate maximization problems.
Learning Coated Adversarial Camouflages for Object Detectors
An adversary can fool deep neural network object detectors by generating adversarial noises.
Serial-EMD: Fast Empirical Mode Decomposition Method for Multi-dimensional Signals Based on Serialization
Empirical mode decomposition (EMD) has developed into a prominent tool for adaptive, scale-based signal analysis in various fields like robotics, security and biomedical engineering.
A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization
Bi-level optimization model is able to capture a wide range of complex learning tasks with practical interest.
Multiobjective Bilevel Evolutionary Approach for Off-Grid Direction-of-Arrival Estimation
We formulate a multiobjective off-grid DOA estimation model to realize this idea, by which the source number can be automatically identified together with DOA estimation.
Gridless Evolutionary Approach for Line Spectral Estimation with Unknown Model Order
To overcome the above shortcomings of relaxation, we propose a novel idea of simultaneously estimating the frequencies and model order by means of the atomic $l_0$ norm.
Active Hierarchical Exploration with Stable Subgoal Representation Learning
Although GCHRL possesses superior exploration ability by decomposing tasks via subgoals, existing GCHRL methods struggle in temporally extended tasks with sparse external rewards, since the high-level policy learning relies on external rewards.
Parallel Scale-wise Attention Network for Effective Scene Text Recognition
To address these issues, we propose a new multi-scale and encoder-based attention network for text recognition that performs the multi-scale FE and VA in parallel.
Temporal Consistency Two-Stream CNN for Human Motion Prediction
In this paper, we propose a novel temporal fusion (TF) module to fuse the two-stream joints' information to predict human motion, including a temporal concatenation and a reinforcement trajectory spatial-temporal (TST) block, specifically designed to keep prediction temporal consistency.
A General Descent Aggregation Framework for Gradient-based Bi-level Optimization
In this work, we formulate BLOs from an optimistic bi-level viewpoint and establish a new gradient-based algorithmic framework, named Bi-level Descent Aggregation (BDA), to partially address the above issues.
Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond
Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community.
Intrinsically Guided Exploration in Meta Reinforcement Learning
Deep reinforcement learning algorithms generally require large amounts of data to solve a single task.
Engineering Three Dimensional Moiré Flat Bands
For many two dimensional van der Waals materials, twisting two adjacent layers with respect to each other leads to flat electronic bands in the two corresponding spatial directions -- a notion sometimes referred to as twistronics as it enables a wealth of physical phenomena.
Materials Science Statistical Mechanics Strongly Correlated Electrons Superconductivity
MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
Meta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks.
A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton
In recent years, a variety of gradient-based first-order methods have been developed to solve bi-level optimization problems for learning applications.
Multi-modal Datasets for Super-resolution
However, due to the variety of image degradation types in the real world, models trained on single-modal simulation datasets do not always have good robustness and generalization ability in different degradation scenarios.
Research on a New Convolutional Neural Network Model Combined with Random Edges Adding
Based on the idea of small world network, a random edge adding algorithm is proposed to improve the performance of convolutional neural network model.
A Fast deflation Method for Sparse Principal Component Analysis via Subspace Projections
The implementation of conventional sparse principal component analysis (SPCA) on high-dimensional data sets has become a time consuming work.
Testing and verification of neural-network-based safety-critical control software: A systematic literature review
Objective: With the increase in studies on the T&V of NN-based control software in safety-critical domains, it is important to systematically review the state-of-the-art T&V methodologies, to classify approaches and tools that are invented, and to identify challenges and gaps for future studies.
A TWO-STAGE FRAMEWORK FOR MATHEMATICAL EXPRESSION RECOGNITION
In the first stage, this method locates and recognizes the math symbols of input image by object detection algorithm.
Investigating Customization Strategies and Convergence Behaviors of Task-specific ADMM
Alternating Direction Method of Multiplier (ADMM) has been a popular algorithmic framework for separable optimization problems with linear constraints.
Task-Oriented Convex Bilevel Optimization with Latent Feasibility
This paper firstly proposes a convex bilevel optimization paradigm to formulate and optimize popular learning and vision problems in real-world scenarios.
USE-Net: incorporating Squeeze-and-Excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets
The following mixed scheme is used for training/testing: (i) training on either each individual dataset or multiple prostate MRI datasets and (ii) testing on all three datasets with all possible training/testing combinations.
CNN-based Prostate Zonal Segmentation on T2-weighted MR Images: A Cross-dataset Study
Prostate cancer is the most common cancer among US men.
Fast Botnet Detection From Streaming Logs Using Online Lanczos Method
Botnet, a group of coordinated bots, is becoming the main platform of malicious Internet activities like DDOS, click fraud, web scraping, spam/rumor distribution, etc.
Improving Medical Short Text Classification with Semantic Expansion Using Word-Cluster Embedding
However, in electronic medical records (EMR), the texts containing sentences are shorter than that in general domain, which leads to the lack of semantic features and the ambiguity of semantic.
Preference Completion: Large-scale Collaborative Ranking from Pairwise Comparisons
In this paper we consider the collaborative ranking setting: a pool of users each provides a small number of pairwise preferences between $d$ possible items; from these we need to predict preferences of the users for items they have not yet seen.
