7 papers
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment
Tianyu Dong, Yangyang Liu, Jiang Zhou +9
Sparse Mixture-of-Experts (MoE) architectures have emerged as an increasingly influential paradigm as they offer a strategic balance between parameter scalability and computational…
LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning
Yu Zhao, Zekun Zhang, Fan Jiang +6
Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-time scaling paradigm. Howeve…
ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
Yuanyang Li, Xue Yang, Longyue Wang +2
Current LLM agents are proficient at calling isolated APIs but struggle with the "last mile" of commercial software automation. In real-world scenarios, tools are not independent;…
CaptchaMind: Training CAPTCHA Solvers via Reinforcement Learning with Explicit Reasoning Supervision
Pengcheng Wang, Haoxiang Liu, Yang Dai +5
CAPTCHAs are widely deployed as human verification mechanisms and frequently block intelligent agents from completing end-to-end automation in real-world web environments. Solving…
DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection
Junchao Wu, Yefeng Liu, Chenyu Zhu +8
The effective detection and governance of Large Language Model (LLM) generated content has become increasingly critical due to the growing risk of misuse. Despite the impressive pe…
Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling
Fan Jiang, Yu Zhao, Chenyang Lyu +5
We present Marco-MoE, a suite of fully open multilingual sparse Mixture-of-Experts (MoE) models. Marco-MoE features a highly sparse design in which only around 5\% of the total par…