8 papers
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
Jiarui Feng, Hanqing Zeng, Karish Grover +11
Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performa…
Code as Agent Harness
Xuying Ning, Katherine Tieu, Dongqi Fu +39
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineerin…
Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning
Sirui Chen, Yunzhe Qi, Mengting Ai +4
Supervised fine-tuning (SFT) relies critically on selecting training data that most benefits a model's downstream performance. Gradient-based data selection methods such as TracIn…
Don't Waste It: Guiding Generative Recommenders with Structured Human Priors via Multi-Head Decoding
Yunkai Zhang, Qiang Zhang, Feng Lin +7
Optimizing recommender systems for objectives beyond accuracy, such as diversity, novelty, and personalization, is crucial for long-term user satisfaction. To this end, industrial…
AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs
Chengming Cui, Tianxin Wei, Ziyi Chen +6
Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling pr…
CoFiRec: Coarse-to-Fine Tokenization for Generative Recommendation
Tianxin Wei, Xuying Ning, Xuxing Chen +6
In web environments, user preferences are often refined progressively as users move from browsing broad categories to exploring specific items. However, existing generative recomme…