menu
techminis

A naukri.com initiative

google-web-stories
Home

>

ML News

ML News

source image

Arxiv

2d

read

179

img
dot

Image Credit: Arxiv

A Comparison of Parametric Dynamic Mode Decomposition Algorithms for Thermal-Hydraulics Applications

  • This work compares different parametric Dynamic Mode Decomposition (DMD) algorithms for thermal-hydraulics applications.
  • DMD is an equation-free technique used to learn linear models from time series datasets.
  • The standard DMD formulation cannot handle parametric time series, requiring different linear models for each parameter realization.
  • The study explores three different thermal-hydraulics problems to assess the advantages and shortcomings of the deployed algorithms.

Read Full Article

like

10 Likes

source image

Arxiv

2d

read

316

img
dot

Image Credit: Arxiv

MB-ORES: A Multi-Branch Object Reasoner for Visual Grounding in Remote Sensing

  • A unified framework, MB-ORES, has been proposed to integrate object detection (OD) and visual grounding (VG) for remote sensing (RS) imagery.
  • MB-ORES fine-tunes an open-set object detector, using referring expression data, to support OD and establish a prior for VG task in remote sensing.
  • The model has a multi-branch network that generates task-aware proposals by integrating spatial, visual, and categorical features, and an object reasoning network that assigns probabilities to proposals for final referring object localization.
  • MB-ORES demonstrates superior performance on OPT-RSVG and DIOR-RSVG datasets, outperforming existing methods while maintaining classical OD capabilities.

Read Full Article

like

19 Likes

source image

Arxiv

2d

read

132

img
dot

Image Credit: Arxiv

GPU-centric Communication Schemes for HPC and ML Applications

  • Compute nodes on modern heterogeneous supercomputing systems consist of CPUs, GPUs, and high-speed network interconnects.
  • Parallelization is a technique used for scalable simulation and deep learning workloads on these systems.
  • Communication bottlenecks from distributed execution of parallel workloads can impact performance.
  • This survey explores GPU-centric communication schemes that move control path from CPU to GPU.

Read Full Article

like

7 Likes

source image

Arxiv

2d

read

230

img
dot

Image Credit: Arxiv

Enhancing Image Resolution of Solar Magnetograms: A Latent Diffusion Model Approach

  • The study focuses on enhancing the resolution of solar magnetograms taken by the Michelson Doppler Imager (MDI).
  • A novel diffusion model approach called Latent Diffusion Model (LDM) is used to super-resolve the MDI magnetograms.
  • The resolution of MDI observations is enhanced from 2"/pixel to 0.5"/pixel to match the higher-resolution capabilities of the Helioseismic and Magnetic Imager (HMI).
  • Reconstructed images are evaluated using classical metrics and physical properties are examined to ensure preservation.

Read Full Article

like

13 Likes

source image

Arxiv

2d

read

234

img
dot

Image Credit: Arxiv

Learning Velocity and Acceleration: Self-Supervised Motion Consistency for Pedestrian Trajectory Prediction

  • Understanding human motion is crucial for accurate pedestrian trajectory prediction.
  • This work proposes a self-supervised pedestrian trajectory prediction framework that explicitly models position, velocity, and acceleration.
  • The model leverages velocity and acceleration information to enhance position prediction through feature injection and a self-supervised motion consistency mechanism.
  • Experiments on the ETH-UCY and Stanford Drone datasets show that the proposed method achieves state-of-the-art performance.

Read Full Article

like

14 Likes

source image

Arxiv

2d

read

101

img
dot

Image Credit: Arxiv

Fair Dynamic Spectrum Access via Fully Decentralized Multi-Agent Reinforcement Learning

  • Decentralized wireless network with several source-destination pairs sharing limited frequency bands.
  • Sources adapt band selection strategy without information sharing.
  • Proposed Fair Share RL (FSRL) solution achieves fairness without coordination.
  • FSRL can be up to 89.0% fairer compared to baseline RL algorithm.

Read Full Article

like

6 Likes

source image

Arxiv

2d

read

7

img
dot

Image Credit: Arxiv

Solving the Best Subset Selection Problem via Suboptimal Algorithms

  • Best subset selection in linear regression is a nonconvex problem that is challenging to solve.
  • Finding the global optimal solution via an exact optimization method may be impractical for high-dimensional problems.
  • This study introduces a new suboptimal procedure for best subset selection in linear regression.
  • Comparative experiments with synthetic and real data show the competitive performance of the new algorithm.

Read Full Article

like

Like

source image

Arxiv

2d

read

281

img
dot

Image Credit: Arxiv

Contextual Preference Collaborative Measure Framework Based on Belief System

  • This article introduces a preference collaborative measure framework based on an updated belief system.
  • The framework aims to reduce human intervention and improve the accuracy and efficiency of preference measures.
  • It proposes algorithms to discover common preferences, update the belief system, and classify preference rules.
  • Experimental results show that the proposed algorithms outperform state-of-the-art algorithms in most aspects.

Read Full Article

like

16 Likes

source image

Arxiv

2d

read

348

img
dot

Image Credit: Arxiv

Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation

  • Large real-world robot datasets hold potential to train generalist robot models.
  • Co-training policy on a mixture of simulation and real-world datasets improves performance.
  • Simulation data can enhance real-world task performance by an average of 38%.
  • Research presents a simple recipe for utilizing simulation data for vision-based robotic manipulation.

Read Full Article

like

20 Likes

source image

Arxiv

2d

read

78

img
dot

Image Credit: Arxiv

Policy Gradient for LQR with Domain Randomization

  • Domain randomization (DR) enables sim-to-real transfer by training controllers on a distribution of simulated environments.
  • Simple policy gradient (PG) methods are often used to solve DR, but the theoretical guarantees are limited.
  • A convergence analysis of PG methods for domain-randomized linear quadratic regulation (LQR) is provided in this study.
  • The study shows that PG converges globally under suitable bounds on the heterogeneity of sampled systems, and proposes a discount-factor annealing algorithm.

Read Full Article

like

4 Likes

source image

Arxiv

2d

read

97

img
dot

Image Credit: Arxiv

Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1

  • Recent advancements in Chain of Thought (COT) generation have improved the reasoning capabilities of Large Language Models (LLMs).
  • SEED-Bench-R1 is a benchmark designed to evaluate post-training methods for Multimodal Large Language Models (MLLMs) in video understanding.
  • Reinforcement Learning (RL) shows data efficiency and superior performance on both in-distribution and out-of-distribution tasks compared to supervised fine-tuning (SFT).
  • However, RL often produces less logically coherent reasoning chains and has limitations such as inconsistent reasoning and overlooked visual cues.

Read Full Article

like

5 Likes

source image

Arxiv

2d

read

226

img
dot

Image Credit: Arxiv

RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy

  • RIG (Reasoning and Imagination in Generalist Policy) is a new approach that combines reasoning and imagination in an end-to-end agent.
  • RIG utilizes a data pipeline to integrate and enrich the content of imagination and reasoning in agent trajectories.
  • The joint learning of reasoning and next image generation in RIG leads to significant sample efficiency improvements and generalization.
  • The synergy of reasoning and imagination in RIG enhances the robustness, generalization, interoperability, and overall performance of the agent.

Read Full Article

like

13 Likes

source image

Arxiv

2d

read

62

img
dot

Image Credit: Arxiv

I Know Therefore I Score: Label-Free Crafting of Scoring Functions using Constraints Based on Domain Expertise

  • Researchers propose a label-free approach to crafting scoring functions using domain expertise constraints.
  • The approach incorporates insights and business rules from domain experts as easily observable and specifiable constraints.
  • The constraints are used as weak supervision by a machine learning model to learn the scoring function.
  • The approach is tested on synthetic and real-life datasets, comparing it to supervised learning models.

Read Full Article

like

3 Likes

source image

Arxiv

2d

read

43

img
dot

Image Credit: Arxiv

Reachable Polyhedral Marching (RPM): An Exact Analysis Tool for Deep-Learned Control Systems

  • Neural networks used in robotics require analysis of learned behaviors and their impact on closed-loop performance.
  • Researchers have developed the Reachable Polyhedral Marching (RPM) algorithm for analyzing neural networks that implement piecewise-affine functions.
  • The algorithm enables the computation of control invariant sets and regions of attraction (ROAs) for feedforward neural networks with ReLU activation.
  • The approach showcases the ability to find non-convex control invariant sets and ROAs, as demonstrated in examples with learned oscillator and pendulum models.

Read Full Article

like

2 Likes

source image

Arxiv

2d

read

152

img
dot

Image Credit: Arxiv

Dark patterns in e-commerce: a dataset and its baseline evaluations

  • Dark patterns are user interface designs in online services that induce users to take unintended actions.
  • A dataset for dark pattern detection has been constructed, consisting of 1,818 dark pattern texts from shopping sites.
  • State-of-the-art machine learning methods like BERT, RoBERTa, ALBERT, and XLNet have been applied to demonstrate automatic detection accuracy as baselines.
  • RoBERTa achieved the highest accuracy of 0.975 in the 5-fold cross-validation.

Read Full Article

like

9 Likes

For uninterrupted reading, download the app