ByteSpan: Information-Driven Subword Tokenisation
Paper
•
2506.18639
•
Published
•
3
CLIMB
community
AI & ML interests
Cambridge University submission for the 2023 CoNLL baby language modeling shared task competition.
Recent Activity
View all activity
suchirsalhanÂ
authored
a
paper
about 2 months ago
rdiehlmartinezÂ
authored
7
papers
4 months ago
CLIMB: Curriculum Learning for Infant-inspired Model Building
Paper
•
2311.08886
•
Published
Mitigating Frequency Bias and Anisotropy in Language Model Pre-Training with Syntactic Smoothing
Paper
•
2410.11462
•
Published
Attention-based Contextual Language Model Adaptation for Speech Recognition
Paper
•
2106.01451
•
Published
From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes
Paper
•
2410.22906
•
Published
Less is More: Pre-Training Cross-Lingual Small-Scale Language Models with Cognitively-Plausible Curriculum Learning Strategies
Paper
•
2410.22886
•
Published
•
2
Tending Towards Stability: Convergence Challenges in Small Language Models
Paper
•
2410.11451
•
Published
Automatically Neutralizing Subjective Bias in Text
Paper
•
1911.09709
•
Published
suchirsalhanÂ
authored
a
paper
4 months ago
rdiehlmartinezÂ
updated
a
dataset
12 months ago
clap-labÂ
authored
a
paper
over 1 year ago
rdiehlmartinezÂ
updated
8
models
almost 2 years ago
cambridge-climb/objective_curriculum-roberta_pre_layer_norm-model
Updated
cambridge-climb/combination-roberta_pre_layer_norm-model
Updated
cambridge-climb/data_curriculum-roberta_pre_layer_norm-model
Updated
cambridge-climb/vocabulary_curriculum-roberta_pre_layer_norm-model
Updated
cambridge-climb/CamBabyTokenizer-8192
Updated
cambridge-climb/CamBabyTokenizer-32768
Updated
cambridge-climb/CamBabyTokenizer-16384
Updated
cambridge-climb/baseline-roberta_pre_layer_norm-model
Fill-Mask
•
Updated
•
8
rdiehlmartinezÂ
updated
a
Space
almost 2 years ago