11 papers
Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation
Wei-Rui Chen, Vignesh Kothapalli, Ata Fatahibaarzi +5
Distilling the capabilities from a large reasoning model (LRM) to a smaller student model often involves training on substantial amounts of reasoning data. However, knowledge disti…
Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert Signatures
Pingzhi Li, Morris Yu-Chao Huang, Zhen Tan +6
Knowledge Distillation (KD) accelerates training of large language models (LLMs) but poses intellectual property protection and LLM diversity risks. Existing KD detection methods b…
LANTERN: Scalable Distillation of Large Language Models for Job-Person Fit and Explanation
Zhoutong Fu, Yihan Cao, Yi-Lin Chen +16
Large language models (LLMs) have achieved strong performance across a wide range of natural language processing tasks. However, deploying LLMs at scale for domain specific applica…
Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs
Siyu Zhu, Yanbin Jiang, Hejian Sang +6
We investigated Agentic RL with large language models on the \textsc{TravelPlanner} benchmark. Our approach, \textsc{Planner-R1}, achieved a \textbf{56.9\%} final-pass rate with on…
Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction
Ryan Lucas, Kayhan Behdin, Zhipeng Wang +3
Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale. We show that using compression t…
Heterogeneity-Oblivious Robust Federated Learning
Weiyao Zhang, Jinyang Li, Qi Song +5
Federated Learning (FL) remains highly vulnerable to poisoning attacks, especially under real-world hyper-heterogeneity, where clients differ significantly in data distributions, c…