Search Results for author:
Found 5 papers, 4 papers with code
AdaR1: From Long-CoT to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
To address this, we propose a novel two-stage framework for adaptive and efficient reasoning.
Bag of Tricks for Inference-time Computation of LLM Reasoning
In this paper, we investigate and benchmark diverse inference-time computation strategies across reasoning tasks of varying complexity.
Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
Mainstream defenses aim to vaccinate the model such that the later harmful fine-tuning attack is less effective.
O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
Experiments on various mathematical reasoning benchmarks show that O1-Pruner not only significantly reduces inference overhead but also achieves higher accuracy, providing a novel and promising solution to this challenge.
Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Prediction
Rapid urbanization has significantly escalated traffic congestion, underscoring the need for advanced congestion prediction services to bolster intelligent transportation systems.
