How I Study AI - Learn AI Papers & Lectures the Easy Way

Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR

Intermediate

Fanfan Liu, Youyang Yin et al.Feb 5arXiv

The paper discovers that popular RLVR methods for training language and vision-language models secretly prefer certain answer lengths, which can hurt learning.

#LUSPO#RLVR#GRPO

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding

Intermediate

Gang Lin, Dongfang Li et al.Feb 4arXiv

Long texts make language models slow because they must keep and re-check a huge memory called the KV cache for every new word they write.

#long-context LLM#sparse attention#head specialization

TTCS: Test-Time Curriculum Synthesis for Self-Evolving

Intermediate

Chengyi Yang, Zhishang Xiang et al.Jan 30arXiv

TTCS is a way for a model to teach itself during the test by first making easier practice questions that are similar to the real hard question and then learning from them.

#test-time training#test-time reinforcement learning#curriculum learning

Papers3

Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding

TTCS: Test-Time Curriculum Synthesis for Self-Evolving