1 citations · 1 across the 31 of their papers we have counts for
7 papers · 1 filter
Adaptive Decoding Methods for Token-Efficient Reinforcement Learning
Zhaonan Li, Zelei Cheng, Amritansh Mishra +5
Rollout decoding affects both which trajectories are used for reinforcement learning with verifiable rewards (RLVR) and how many completion tokens are spent collecting them. We stu…
When Load-Balancing Goes Too Far: Expert Pruning in Over-Dispersed Mixture-of-Experts Models
Berkcan Kapusuzoglu, Connor Pryor, Sangwoo Cho +4
Expert pruning reduces the memory and serving cost of Mixture-of-Experts (MoE) models by removing low-importance experts identified by the router, assuming router probabilities pro…
Efficient Reinforcement Learning for Long-Horizon Tool-Use Agentic Tasks
Zelei Cheng, Amritansh Mishra, Sambit Sahu +1
Long-horizon tool-using agents must reason over user goals, domain policies, tool calls, simulator state, and delayed verifiable rewards. Reinforcement learning (RL) is a natural f…
AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
Duy Nguyen, Hanqi Xiao, Archiki Prasad +7
Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the teacher being conditioned on…
Optimizing Reasoning Efficiency through Prompt Difficulty Prediction
Bo Zhao, Berkcan Kapusuzoglu, Kartik Balasubramaniam +3
Reasoning language models perform well on complex tasks but are costly to deploy due to their size and long reasoning traces. We propose a routing approach that assigns each proble…
Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
Ashwinee Panda, Vatsal Baherwani, Zain Sarwar +4
Mixture of Experts (MoE) pretraining is more scalable than dense Transformer pretraining, because MoEs learn to route inputs to a sparse set of their feedforward parameters. Howeve…
Continual Pre-training of MoEs: How robust is your router?
Benjamin Thérien, Charles-Étienne Joseph, Zain Sarwar +7
Sparsely-activated Mixture of Experts (MoE) transformers are promising architectures for foundation models. Compared to dense transformers that require the same amount of floating-…