menu
techminis

A naukri.com initiative

google-web-stories
Home

>

ML News

ML News

source image

Arxiv

22h

read

298

img
dot

Image Credit: Arxiv

Barrier Certificates for Unknown Systems with Latent States and Polynomial Dynamics using Bayesian Inference

  • Certifying safety in dynamical systems is crucial, but barrier certificates typically require explicit system models.
  • A novel approach is proposed for synthesizing barrier certificates for unknown systems with latent states and polynomial dynamics.
  • A Bayesian framework is employed, updating a prior in state-space representation using input-output data via a targeted marginal Metropolis-Hastings sampler.
  • The resulting samples are used to construct a candidate barrier certificate through a sum-of-squares program, providing probabilistic guarantees for the unknown system.

Read Full Article

like

17 Likes

source image

Arxiv

22h

read

264

img
dot

Image Credit: Arxiv

Autonomous optical navigation for DESTINY+: Enhancing misalignment robustness in flyby observations with a rotating telescope

  • The upcoming JAXA Epsilon medium-class mission, DESTINY+, aims to flyby multiple asteroids including Phaethon.
  • The mission's flyby observation instrument, TCAP, is a telescope capable of single-axis rotation.
  • TCAP is also used as a navigation camera for autonomous optical navigation during the closest-approach phase.
  • A proposed algorithm utilizing the unscented Kalman filter can mitigate misalignment-induced degradation of the optical navigation accuracy.

Read Full Article

like

15 Likes

source image

Arxiv

22h

read

279

img
dot

Image Credit: Arxiv

A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning

  • A novel framework is proposed for heterogeneous federated learning (FL) to address client heterogeneity and improve model performance.
  • The framework captures local and global training processes through a bilevel formulation.
  • It includes personalized learning, pre-training on the server's side, nonstandard aggregation, nonidentical local steps, and clients' local constraints.
  • The proposed method, ZO-HFL, achieves nonasymptotic and asymptotic convergence guarantees without relying on standard assumptions in heterogeneous FL.

Read Full Article

like

16 Likes

source image

Arxiv

22h

read

22

img
dot

Image Credit: Arxiv

An Approach to Technical AGI Safety and Security

  • Artificial General Intelligence (AGI) presents transformative benefits and risks.
  • The approach focuses on addressing two areas of risk: misuse and misalignment.
  • To prevent misuse, the strategy includes identifying dangerous capabilities and implementing security measures.
  • To address misalignment, model-level mitigations and system-level security measures are proposed.

Read Full Article

like

1 Like

source image

Arxiv

22h

read

223

img
dot

Image Credit: Arxiv

Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments

  • Robotic grasping is a critical capability for robots to interact with their environment.
  • Researchers propose a method for effective grasping in cluttered bin-picking environments.
  • They utilize a multi-functional gripper combining suction and finger grasping.
  • The proposed method prevents collisions and successfully grasps objects in cluttered scenarios.

Read Full Article

like

13 Likes

source image

Arxiv

22h

read

89

img
dot

Image Credit: Arxiv

CoRAG: Collaborative Retrieval-Augmented Generation

  • CoRAG is a framework that extends Retrieval-Augmented Generation (RAG) models to collaborative settings.
  • CoRAG allows clients to jointly train a shared model using a collaborative passage store.
  • CoRAG outperforms parametric collaborative learning methods and locally trained RAG models in low-resource scenarios.
  • The trade-off between leveraging a collectively enriched knowledge base and the potential risk of incorporating detrimental passages is a key consideration in collaborative RAG.

Read Full Article

like

5 Likes

source image

Arxiv

22h

read

134

img
dot

Image Credit: Arxiv

Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights

  • Detecting abusive language in social media conversations is challenging due to the contextual nature of abusiveness.
  • Traditional Abusive Language Detection (ALD) models often overlook the conversational context, leading to unreliable performance metrics.
  • A novel approach is proposed in this paper using graph neural networks (GNNs) to model social media conversations as graphs, capturing comment relationships.
  • The GNN model outperforms context-agnostic baselines and linear context-aware methods, achieving significant improvements in F1 scores.

Read Full Article

like

8 Likes

source image

Arxiv

22h

read

253

img
dot

Image Credit: Arxiv

Representing Flow Fields with Divergence-Free Kernels for Reconstruction

  • Accurately reconstructing continuous flow fields from sparse or indirect measurements remains an open challenge.
  • A novel flow field reconstruction framework based on divergence-free kernels (DFKs) is introduced.
  • DFKs-Wen4 (matrix-valued radial basis functions derived from Wendland's C^4 polynomial) are identified as the optimal form of analytically divergence-free approximation for velocity fields.
  • Experiments demonstrate that DFKs-Wen4 outperform other divergence-free representations in reconstruction accuracy and computational efficiency.

Read Full Article

like

15 Likes

source image

Arxiv

22h

read

0

img
dot

Image Credit: Arxiv

Gen-C: Populating Virtual Worlds with Generative Crowds

  • Researchers introduce Gen-C, a generative model for authoring high-level crowd behaviors in virtual environments.
  • Gen-C leverages a large language model to generate crowd scenarios which are expanded and generalized through simulations.
  • The method employs Variational Graph Auto-Encoders to learn graph structures and node features, enabling flexible generation of dynamic crowd interactions.
  • Gen-C showcases its potential for populating diverse virtual environments with agents exhibiting varied and dynamic behaviors.

Read Full Article

like

Like

source image

Arxiv

22h

read

14

img
dot

Image Credit: Arxiv

Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure

  • Despite their impressive capabilities, LLMs exhibit a basic generalization failure known as the Reversal Curse.
  • The Reversal Curse in LLMs is attributed to the long-standing binding problem in cognitive science, neuroscience, and AI.
  • Transformers' limitations in conceptual binding cause the inconsistency and entanglements of concept representations, leading to the Reversal Curse.
  • A model design based on JEPA (Joint-Embedding Predictive Architecture) breaks the Reversal Curse and improves generalization by incorporating memory layers supporting disentangled concept representations.

Read Full Article

like

Like

source image

Arxiv

22h

read

111

img
dot

Image Credit: Arxiv

Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions

  • Deep neural networks are not resilient to parameter corruptions: even a single-bitwise error in their parameters in memory can cause an accuracy drop of over 10%.
  • Hessian-aware training is proposed as an approach to improve resilience to bitwise corruptions in neural network parameters.
  • The approach promotes models with flatter loss surfaces and shows a reduction in the number of bits leading to a significant accuracy drop.
  • This method can work synergistically with existing hardware and system-level defenses.

Read Full Article

like

6 Likes

source image

Arxiv

22h

read

343

img
dot

Image Credit: Arxiv

Deep Representation Learning for Unsupervised Clustering of Myocardial Fiber Trajectories in Cardiac Diffusion Tensor Imaging

  • Researchers have developed a deep learning framework for unsupervised clustering of myocardial fibers in cardiac diffusion tensor imaging (DTI) data.
  • The framework combines a Bidirectional Long Short-Term Memory (LSTM) network to capture local sequential information along fibers, with a Transformer autoencoder to learn global shape features and incorporate anatomical context.
  • By clustering the learned representations using a density-based algorithm, the framework successfully identifies 33 to 62 robust clusters, capturing subtle differences in fiber trajectories.
  • This approach has the potential to improve surgical planning, characterize disease-related remodeling, and advance personalized cardiac care.

Read Full Article

like

20 Likes

source image

Arxiv

22h

read

22

img
dot

Image Credit: Arxiv

Toward Interpretable Sleep Stage Classification Using Cross-Modal Transformers

  • Accurate sleep stage classification is significant for sleep health assessment.
  • A new cross-modal transformer-based method for sleep stage classification is proposed.
  • The method outperforms the state-of-the-art methods and eliminates the black-box behavior of deep-learning models.
  • Considerable reductions in the number of parameters and training time are achieved compared to the state-of-the-art methods.

Read Full Article

like

1 Like

source image

Arxiv

22h

read

179

img
dot

Image Credit: Arxiv

Latent Covariate Shift: Unlocking Partial Identifiability for Multi-Source Domain Adaptation

  • Multi-source domain adaptation (MSDA) aims to learn a label prediction function for an unlabeled target domain by leveraging labeled data from multiple source domains and unlabeled data from the target domain.
  • Conventional MSDA approaches rely on covariate shift or conditional shift paradigms, assuming a consistent label distribution across domains. However, this limits their applicability in real-world scenarios where label distributions vary across domains.
  • To address this limitation, a new paradigm called latent covariate shift (LCS) is proposed, introducing greater variability and adaptability across domains. It allows for recovering the latent cause of the label variable, referred to as the latent content variable.
  • The proposed MSDA method based on LCS achieves exceptional performance on both simulated and real-world datasets by learning the label distribution conditioned on the identifiable latent content variable, accommodating substantial distribution shifts.

Read Full Article

like

10 Likes

source image

Arxiv

22h

read

358

img
dot

Image Credit: Arxiv

Epistemic Monte Carlo Tree Search

  • The AlphaZero/MuZero (A/MZ) family of algorithms utilizes Monte Carlo Tree Search (MCTS) and learned models for remarkable success in various domains.
  • Epistemic MCTS (EMCTS) is introduced to address the uncertainty caused by learned models and enhance exploration in sparse reward environments.
  • When applied to the task of writing code in the Assembly language subleq, AZ with EMCTS achieves higher sample efficiency compared to the baseline AZ.
  • Search with EMCTS significantly outperforms equivalent methods without search for uncertainty estimation in solving hard-exploration benchmark Deep Sea, showcasing the benefits of search for epistemic uncertainty estimation.

Read Full Article

like

21 Likes

For uninterrupted reading, download the app