Home Knowledge Base MTL

MTL

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations

arXiv:2606.02221v1 Announce Type: new Abstract: Multi-task learning (MTL) aims to construct a joint model for multiple tasks by sharing a common representation across domains. To achieve this goal, existing optimization-centric methods either balance task gradients or modify the shared architecture.

arXiv CS 8d ago

Revisiting the expressiveness of metric temporal logic : A tale of "Je t'aime, moi non plus."

Announce Type: replace Abstract: The expressiveness of Metric Temporal Logic (MTL) has been extensively studied throughout the last two decades. In particular, it has been shown that the \emph{interval-based} semantics of MTL is strictly more expressive than the \emph{pointwise} one. These results may suggest that enabling the evaluation of formulae at arbitrary time points \emph{instead of} positions of timed events increases the expressive power of MTL.

arXiv CS 9d ago

Multi-task Learning is Not Enough: Representational Entanglement in Dual-output Second Language Speech Recognition

arXiv:2606.06065v2 Announce Type: replace Abstract: Second-language (L2) speech recognition often requires transcriptions of pronunciations and intended meanings. Multi-task learning (MTL) is a natural approach because it assumes that shared representations benefit both outputs. However, this paper shows that this assumption does not hold across Korean and English.

arXiv CS 2d ago

Multi-task Learning is Not Enough: Representational Entanglement in Dual-output Second Language Speech Recognition

Announce Type: new Abstract: Second-language (L2) speech recognition often requires transcriptions of pronunciations and intended meanings. Multi-task learning (MTL) is a natural approach because it assumes that shared representations benefit both outputs. However, this paper shows that this assumption does not hold across Korean and English.

arXiv CS 5d ago

AttnRegDeepLab: A Two-Stage Decoupled Framework for Interpretable Embryo Fragmentation Grading

arXiv:2511.18454v4 Announce Type: replace Abstract: Assessing embryo fragmentation is crucial for predicting IVF success, yet manual grading is prone to subjectivity, and existing AI models struggle with clinical interpretability and segmentation errors. We propose AttnRegDeepLab, a Multi-Task Learning (MTL) framework designed to solve these challenges. The model enhances a DeepLabV3+ decoder with Attention Gates to filter out cytoplasmic noise and retain sharp contour details.

arXiv CS 1d ago

A Survey on Deep Multi-Task Learning in Connected Autonomous Vehicles

Announce Type: replace Abstract: Connected autonomous vehicles (CAVs) must simultaneously perform multiple tasks, such as perception, prediction, planning, and control, to ensure safe and reliable navigation in complex environments. Moreover, through vehicle-to-everything (V2X) communication, cooperative perception and driving among CAVs can be enabled, thereby mitigating the limitations of individual vehicles, while it also introduces stringent latency, reliability, and bandwidth...

arXiv CS 1d ago

AttnRegDeepLab: A Two-Stage Decoupled Framework for Interpretable Embryo Fragmentation Grading

arXiv:2511.18454v3 Announce Type: replace Abstract: Embryo fragmentation is a morphological indicator critical for evaluating developmental potential in In Vitro Fertilization (IVF). However, manual grading is subjective and inefficient, while existing deep learning solutions often lack clinical explainability or suffer from accumulated errors in segmentation area estimation. To address these issues, this study proposes AttnRegDeepLab (Attention-Guided Regression DeepLab), a framework...

arXiv CS 6d ago

Show HN: A CSS 3D Engine (no WebGL)

A CSS polygon mesh library. A 3D engine for the DOM. Renders OBJ/MTL, GLB and VOX as real HTML elements transformed with CSS matrix3d(...) .

Hacker News 9d ago

Mind the Gap: Bridging Behavioral Silos with LLMs in Multi-Vertical Recommendations

Announce Type: new Abstract: In multi-vertical e-commerce platforms like DoorDash, relatively newer product verticals such as grocery and retail present a significant opportunity for personalization innovation. A key challenge lies in solving the "cold start" problem for users. This paper introduces a novel framework for enhancing recommendation quality by transferring knowledge from data-rich verticals (e.g., restaurants at DoorDash) to data-sparse ones.

arXiv CS 2d ago

PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks

arXiv:2605.19145v2 Announce Type: replace Abstract: In the literature, many continual learning (CL) algorithms have been proposed to address the issue of catastrophic forgetting in ML models (i.e., learning new tasks leads to the loss of performance on previously learned tasks). Although all CL approaches use some form of memory to retain information about past tasks, a grounded understanding of what information needs to be stored to minimize catastrophic forgetting remains elusive....

arXiv CS 9d ago