25 citations · 37 across the 5 of their papers we have counts for
7 papers
Measuring and Reducing Cross-Vendor Mismatch in Language Models
Erland Hilman Fuadi, Chong Tian, Xiaosong Ma +1
Running the same language model on different graphics processing unit (GPU) vendors can produce different logits, even when the model weights and inputs are the same. We analyze cr…
MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale
Jiadong Zhang, Xiaosong Ma
Edge-deployed personal memory assistants must handle private interpersonal conversations on-device with open-weight models. Yet, existing memory benchmarks often under-test the com…
Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models
Yongjiang Liu, Haoxi Li, Xiaosong Ma +2
Recent Large Reasoning Models (LRMs) excel at complex reasoning tasks but often suffer from overthinking, generating overly long and redundant reasoning trajectories. To explore it…
LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning
Haoyue Zhang, Hualei Zhang, Xiaosong Ma +2
Large Language Models (LLMs) exhibit enhanced capabilities by Chain-of-Thought reasoning. However, the extended reasoning sequences introduce significant GPU memory overhead due to…
Towards Unbiased Training in Federated Open-world Semi-supervised Learning
Jie Zhang, Xiaosong Ma, Song Guo +1
Federated Semi-supervised Learning (FedSSL) has emerged as a new paradigm for allowing distributed clients to collaboratively train a machine learning model over scarce labeled dat…
Layer-wised Model Aggregation for Personalized Federated Learning
Xiaosong Ma, Jie Zhang, Song Guo +1
Personalized Federated Learning (pFL) not only can capture the common priors from broad range of distributed data, but also support customized models for heterogeneous clients. Res…
Parameterized Knowledge Transfer for Personalized Federated Learning
Jie Zhang, Song Guo, Xiaosong Ma +3
In recent years, personalized federated learning (pFL) has attracted increasing attention for its potential in dealing with statistical heterogeneity among clients. However, the st…