Suchir Salhan

suchirsalhan's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 3 papers 13 days ago

Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction

Paper • 2510.20411 • Published 15 days ago • 2

What is the Best Sequence Length for BABYLM?

Paper • 2510.19493 • Published 15 days ago • 1

BLiSS 1.0: Evaluating Bilingual Learner Competence in Second Language Small Language Models

Paper • 2510.19419 • Published 16 days ago • 1

upvoted a paper 17 days ago

Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling

Paper • 2510.08470 • Published 28 days ago • 1

upvoted a paper 18 days ago

BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data

Paper • 2510.10159 • Published 27 days ago • 3

upvoted a collection 23 days ago

BabyBabelLM

Collection

A multilingual collection of datasets modeling the language a person observes from birth until they acquire a native language. • 45 items • Updated 8 days ago • 7

upvoted 2 papers about 1 month ago

Meta-Pretraining for Zero-Shot Cross-Lingual Named Entity Recognition in Low-Resource Philippine Languages

Paper • 2509.02160 • Published Sep 2 • 1

Pico: A Modular Framework for Hypothesis-Driven Small Language Model Research

Paper • 2509.16413 • Published Sep 19 • 1

upvoted an article about 1 month ago

view article

Article

There is no such thing as a tokenizer-free lunch

By •

Sep 25

• 86

upvoted a paper 4 months ago

ByteSpan: Information-Driven Subword Tokenisation

Paper • 2506.18639 • Published Jun 23 • 3