FASA: Frequency-aware Sparse Attention
Paper
• 2602.03152 • Published
• 148
Jeongjae Park
jjp97
AI & ML interests
I’m interested in the latest NLP and AI technologies, such as uncertainty, retrieval, agentic approaches, and long-context models!
Recent Activity
upvoted a paper 4 days ago
FASA: Frequency-aware Sparse Attention upvoted a paper 6 days ago
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger liked
a model 8 days ago
allenai/OLMoE-1B-7B-0125 Organizations
upvoted a paper 4 days ago
upvoted a paper 6 days ago
upvoted a paper 11 days ago
upvoted 2 papers 18 days ago
upvoted 3 papers 19 days ago
Why Language Models Hallucinate
Paper
• 2509.04664 • Published
• 196
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
Paper
• 2512.07461 • Published
• 78
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Paper
• 2512.01374 • Published
• 105
upvoted a paper 21 days ago
upvoted a paper 22 days ago
upvoted a paper 24 days ago
upvoted a paper 25 days ago
upvoted 3 papers 26 days ago
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
Paper
• 2601.06487 • Published
• 53
Nested Learning: The Illusion of Deep Learning Architectures
Paper
• 2512.24695 • Published
• 44
LLM-in-Sandbox Elicits General Agentic Intelligence
Paper
• 2601.16206 • Published
• 84
upvoted 5 papers about 1 month ago
Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards
Paper
• 2601.06021 • Published
• 47
Your Group-Relative Advantage Is Biased
Paper
• 2601.08521 • Published
• 154
Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
Paper
• 2601.08763 • Published
• 148
mHC: Manifold-Constrained Hyper-Connections
Paper
• 2512.24880 • Published
• 309
Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
Paper
• 2601.08808 • Published
• 39