pseudo-labeling

Tag

Cards List
#pseudo-labeling

RoleHear: Pseudo-Labeling for Semi-Supervised Role-Attributed Streaming Speech Recognition

arXiv cs.CL ↗ · 2026-10-27 Cached

RoleHear is a semi-supervised pipeline that enables a single cache-aware streaming transducer to emit speaker roles inline via lightweight in-vocabulary role tokens, using an offline teacher for pseudo-labeling and an LLM for silver role labels on unlabeled audio.

0 favorites 0 likes
#pseudo-labeling

Pretrained ASR Pseudo-labeling for Noisy Police Audio

arXiv cs.AI ↗ · 2026-09-28 Cached

This paper systematically evaluates pseudo-labeling for adapting pretrained ASR models like Whisper and Qwen3-ASR to noisy police audio, introducing an LLM-as-a-judge filtering method and a cross-model paradigm to reduce word error rates.

0 favorites 0 likes
#pseudo-labeling

Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces

Hugging Face Daily Papers ↗ · 2026-09-28 Cached

The paper proposes label-free bias-only TTRL, which uses majority-vote pseudo-labels as rewards and optimizes only ~100K bias parameters with a frozen backbone, reaching 76.67% on MATH-500 with Qwen2.5-7B and transferring across vision-language and audio reasoning tasks.

0 favorites 0 likes
#pseudo-labeling

StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition

arXiv cs.CL ↗ · 2026-08-17 Cached

StreamHear is a semi-supervised pipeline that adapts streaming speech recognition to domain-shifted audio by fine-tuning a teacher model on labeled data, generating pseudo-labels for unlabeled data, and fine-tuning a student model, with a realignment step for better word placement.

0 favorites 0 likes
#pseudo-labeling

Selective Synergistic Learning for Video Object-Centric Learning

Hugging Face Daily Papers ↗ · 2026-06-14 Cached

Selective Synergistic Learning (SSync) improves video object-centric learning by selectively distilling reliable cues via pseudo-labeling and transitive merging, avoiding error propagation from indiscriminate dense alignment.

0 favorites 0 likes
#pseudo-labeling

Label-Efficient Dataset Pruning via Semi-Supervised Pseudo-Labeling

arXiv cs.LG ↗ · 2026-05-25 Cached

SemiPrune is a label-efficient dataset pruning framework that uses semi-supervised learning to generate pseudo-labels from a small labeled subset, enabling existing supervised pruning methods to work with unlabeled data. It achieves state-of-the-art performance on domain-specific, image-corrupted, and long-tailed datasets.

0 favorites 0 likes
← Back to home

Submit Feedback