Jiayu (Mila) Wang's picture

Open to Collab

Jiayu (Mila) Wang

MilaWang

·

http://jiayuww.github.io

AI & ML interests

Large Language Model, Multimodal Large Language Model, Agentic System, Reasoning, Efficiency

Recent Activity

published a model about 5 hours ago

MilaWang/es-qwen-math-base-7b-3k-40k-ds_o2

updated a model about 6 hours ago

MilaWang/lirpg-fullparam-qwen2-5-math-7b-longseq

published a model about 18 hours ago

MilaWang/lirpg-fullparam-qwen2-5-math-7b-longseq

View all activity

Organizations

authored a paper about 2 months ago

SkillOrchestra: Learning to Route Agents via Skill Transfer

Paper • 2602.19672 • Published Feb 23 • 57

submitted a paper to Daily Papers about 2 months ago

SkillOrchestra: Learning to Route Agents via Skill Transfer

Paper • 2602.19672 • Published Feb 23 • 57

authored 3 papers 6 months ago

Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning

Paper • 2506.04723 • Published Jun 5, 2025 • 1

LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild

Paper • 2510.14240 • Published Oct 16, 2025 • 13

Synthesizing Agentic Data for Web Agents with Progressive Difficulty Enhancement Mechanisms

Paper • 2510.13913 • Published Oct 15, 2025 • 4

authored a paper 10 months ago

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows

Paper • 2506.03332 • Published Jun 3, 2025 • 2

authored a paper 11 months ago

COSMOS: Predictable and Cost-Effective Adaptation of LLMs

Paper • 2505.01449 • Published Apr 30, 2025 • 4

authored 2 papers over 1 year ago

Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models

Paper • 2406.14852 • Published Jun 21, 2024

Grammar-Aligned Decoding

Paper • 2405.21047 • Published May 31, 2024