multitask-learning

Tag

Cards List
#multitask-learning

Unified Law for Visual Tasks (The Four Laws of Computer Vision)

Hugging Face Daily Papers ↗ · 4d ago Cached

The paper proposes World Snapshot Models (WSMs), a unified framework reformulating nearly all visual tasks as generation tasks, validating a 'Unified Law for Visual Tasks' across more than 1,000 visual tasks akin to how LLMs unified NLP.

0 favorites 0 likes
#multitask-learning

Iris-Z: Scaling One Generative Model Past Specialist Geometry Models

Hugging Face Daily Papers ↗ · 2026-11-11 Cached

Iris-Z is a unified generative backbone that jointly models image appearance and depth, surpassing specialized monocular depth models at scale while retaining general image generation abilities, with two models released to the community.

0 favorites 0 likes
#multitask-learning

Sparsity-driven emergence of functional modularity in multitask neural networks

arXiv cs.LG ↗ · 2026-10-27 Cached

The paper shows that sparsity-inducing regularization causes functional modularity to emerge in multitask neural networks, identifying compact task-selective subnetworks ('functional tokens') that can be recombined across pathways without retraining.

0 favorites 0 likes
#multitask-learning

Exploring Recurrent-Depth Language Models for Multitask Clinical Text Processing

arXiv cs.CL ↗ · 2026-10-21 Cached

This paper evaluates small recurrent-depth language models (Ouro-1.4B/2.6B-Thinking, HRM-Text-1B) fine-tuned jointly across 13 clinical NLP datasets, finding they outperform or match similarly sized Qwen3 transformers on most tasks, especially inference and question answering.

0 favorites 0 likes
#multitask-learning

DPTM-DT: Dual-Pretrained Transformer Multitask Representation Learning for Drug-Target Prediction

arXiv cs.LG ↗ · 2026-09-22 Cached

The paper presents DPTM-DT, a dual-pretrained Transformer framework for multitask drug-target prediction that combines molecular graph embeddings, protein language-model embeddings, and physicochemical descriptors, achieving state-of-the-art performance on benchmark datasets.

0 favorites 0 likes
#multitask-learning

Automatic Lyric Transcription for Greek Songs: Scaling and Task Composition Effects in Whisper Adaptation

arXiv cs.CL ↗ · 2026-09-11 Cached

This paper introduces the first benchmark for automatic lyric transcription in Greek songs, demonstrating that adapting Whisper through multitask learning and two-stage training achieves a 27.2% Word Error Rate, significantly improving over zero-shot baselines.

0 favorites 0 likes
#multitask-learning

Population-Robust Feature Selection via Generalized Welfare Optimization

arXiv cs.LG ↗ · 2026-08-05 Cached

This paper introduces PopFS, a method for learning a shared feature set that is robust across heterogeneous populations, allowing each population to train its own model. Experiments on diverse tabular datasets and a 43-state COVID-19 nowcasting study show strong average and worst-population performance.

0 favorites 0 likes
#multitask-learning

Representation Learning Enables Scalable Multitask Deep Reinforcement Learning

arXiv cs.LG ↗ · 2026-06-05 Cached

This paper argues that representation learning, not model-based planning, is the key to scalable multitask deep reinforcement learning. It introduces MR.Q, a simple model-free algorithm with auxiliary predictive objectives that outperforms prior world-model-based methods across diverse continuous control tasks.

0 favorites 0 likes
#multitask-learning

TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data

arXiv cs.LG ↗ · 2026-05-21 Cached

TabPFN-MT extends PFNs to multitask in-context learning for tabular data, achieving state-of-the-art on small-to-medium datasets while reducing inference cost from O(T) to O(1) forward passes.

0 favorites 0 likes
← Back to home

Submit Feedback