collaborators

9 papers

cs.CL2026

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Ailin Huang, Ang Li, Aobo Kong +213

We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most wh…

cs.LG2026

Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap

Yifan Sun, Yushan Liang, Zhen Zhang +2

Self-improvement is a significant techniques within the realm of large language model (LLM), aiming to enhance the LLM performance without relying on external data. Despite its sig…

cs.LG2026

DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training

Xinwei Qiang, Hongmin Chen, Shixuan Sun +3

Determinism is indispensable for reproducibility in large language model (LLM) training, yet it often exacts a steep performance cost. In widely used attention implementations such…

cs.CL2025

Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models

Xin Liu, Qiyang Song, Qihang Zhou +5

Large language models (LLMs) increasingly support multilingual understanding and generation. Meanwhile, efforts to interpret their internal mechanisms have emerged, offering insigh…

cs.LG2025

Matryoshka Model Learning for Improved Elastic Student Models

Chetan Verma, Aditya Srinivas Timmaraju, Cho-Jui Hsieh +7

Industry-grade ML models are carefully designed to meet rapidly evolving serving constraints, which requires significant resources for model development. In this paper, we propose…

cs.AI2025

WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance

Genglin Liu, Shijie Geng, Sha Li +4

Multimodal LLM-powered agents have recently demonstrated impressive capabilities in web navigation, enabling agents to complete complex browsing tasks across diverse domains. Howev…