韩沛煊

HakHan's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 5 papers about 12 hours ago

SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals

Paper • 2502.01042 • Published Feb 3, 2025 • 1

Energy-Based Transformers are Scalable Learners and Thinkers

Paper • 2507.02092 • Published Jul 2, 2025 • 69

EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents

Paper • 2412.13549 • Published Dec 18, 2024

Self-Aligned Reward: Towards Effective and Efficient Reasoners

Paper • 2509.05489 • Published Sep 5, 2025 • 1

DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal

Paper • 2601.18081 • Published 2 days ago • 5

updated a dataset about 18 hours ago

HakHan/DRPG_Dataset

Preview • Updated about 18 hours ago • 5

upvoted a paper about 18 hours ago

DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal

Paper • 2601.18081 • Published 2 days ago • 5

submitted a paper to Daily Papers about 18 hours ago

DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal

Paper • 2601.18081 • Published 2 days ago • 5

updated a collection about 18 hours ago

DRPG_RebuttalAgent

Collection

https://arxiv.org/pdf/2601.18081 • 4 items • Updated about 18 hours ago

published a dataset about 18 hours ago

HakHan/DRPG_Dataset

Preview • Updated about 18 hours ago • 5

updated a model about 18 hours ago

HakHan/DRPG_Planner

Updated about 18 hours ago

updated a model about 19 hours ago

HakHan/DRPG_JudgeModel

4B • Updated about 19 hours ago • 1

published 2 models about 19 hours ago

HakHan/DRPG_JudgeModel

4B • Updated about 19 hours ago • 1

HakHan/DRPG_Planner

Updated about 18 hours ago

upvoted a paper 3 months ago

SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals

Paper • 2502.01042 • Published Feb 3, 2025 • 1

updated a model 3 months ago

HakHan/SafeSwitch

Updated Oct 31, 2025

upvoted a paper 6 months ago

The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination

Paper • 2502.16143 • Published Feb 22, 2025 • 6