Posts by Collection

publications

SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot

Published in International Conference on Machine Learning (ICML), 2025

A training-free, one-shot pruning framework designed for selective structured state-space models.

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

Published in International Conference on Learning Representations (ICLR), 2025

A multi-stage reinforcement learning framework that addresses sparse rewards in fine-grained visual reasoning.