Pinned Loading

1. rethink_sft_generalization rethink_sft_generalization Public

   Repo for paper "Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability"

   Python 65

2. ShaoShuai0605/Misevolution ShaoShuai0605/Misevolution Public

   Official Repo of Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents

   Python 71 1

3. AI45Lab/AgentDoG AI45Lab/AgentDoG Public

   A Diagnostic Guardrail Framework for AI Agent Safety and Security

   Python 449 16

4. bottleneck bottleneck Public

   PyTorch implementation of the paper "Discovering and Explaining the Representation Bottleneck of DNNs" (ICLR 2022 Oral)

   Python 37 2

5. sjtu-xai-lab/interaction-sparsity sjtu-xai-lab/interaction-sparsity Public

   PyTorch implementation of the paper "Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in AI Models" (ICLR 2024)

   Python 4

6. sjtu-xai-lab/BNN-concepts sjtu-xai-lab/BNN-concepts Public

   PyTorch implementation of the paper "Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts" (ICML 2023)

   Python 2