9 15 53

Tong Zhu

Spico

https://Spico197.github.io

AI & ML interests

Information Extraction, Mixture-of-Experts, LLM

Recent Activity

upvoted a paper 8 days ago

Iterative Value Function Optimization for Guided Decoding

upvoted a paper 21 days ago

MoM: Linear Sequence Modeling with Mixture-of-Memories

upvoted an article 24 days ago

Finally, a Replacement for BERT: Introducing ModernBERT

View all activity

Organizations

Spico's activity

upvoted a paper 8 days ago

Iterative Value Function Optimization for Guided Decoding

Paper • 2503.02368 • Published 9 days ago • 14

upvoted a paper 21 days ago

MoM: Linear Sequence Modeling with Mixture-of-Memories

Paper • 2502.13685 • Published 22 days ago • 33

upvoted an article 24 days ago

Article

Finally, a Replacement for BERT: Introducing ModernBERT

Dec 19, 2024

• 571

upvoted a paper 28 days ago

LASP-2: Rethinking Sequence Parallelism for Linear Attention and Its Hybrid

Paper • 2502.07563 • Published 30 days ago • 24

upvoted a paper about 1 month ago

UltraIF: Advancing Instruction Following from the Wild

Paper • 2502.04153 • Published Feb 6 • 22

upvoted a paper about 2 months ago

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

Paper • 2501.12895 • Published Jan 22 • 57

upvoted a paper 5 months ago

NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models

Paper • 2410.11805 • Published Oct 15, 2024 • 13

upvoted a collection 5 months ago

UI Agent

Collection

a collection of algorithmic agents for user interfaces/interactions, program synthesis, and robots • 312 items • Updated about 4 hours ago • 47

upvoted a paper 5 months ago

CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling

Paper • 2409.19291 • Published Sep 28, 2024 • 19

upvoted 3 papers 8 months ago

upvoted a paper 11 months ago

MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Paper • 2404.06395 • Published Apr 9, 2024 • 22

upvoted 2 papers over 1 year ago

BitNet: Scaling 1-bit Transformers for Large Language Models

Paper • 2310.11453 • Published Oct 17, 2023 • 97

OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch

Paper • 2309.10706 • Published Sep 19, 2023 • 17