Junseok Kim

junseokkim00's activity

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

authored 3 papers 1 day ago

Personalized Privacy Control in LLMs via Attention Head Intervention

Paper • 2608.21209 • Published 18 days ago

Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning

Paper • 2601.02970 • Published Apr 20

Persona is a Double-edged Sword: Enhancing the Zero-shot Reasoning by Ensembling the Role-playing and Neutral Prompts

Paper • 2408.08631 • Published Aug 16, 2024 • 1

liked 3 datasets about 1 month ago

user9000/CLEVR-HOPE

Viewer • Updated Aug 19, 2025 • 20.5M • 9.99k • 2

maelic/PSG-coco-format

Viewer • Updated Mar 9 • 48.8k • 361 • 3

Voxel51/GQA-Scene-Graph

Preview • Updated Jul 10, 2024 • 2.33k • 4

published a dataset about 2 months ago

junseokkim00/syndoc

Viewer • Updated Jul 24 • 25k • 23

updated a dataset about 2 months ago

junseokkim00/syndoc

Viewer • Updated Jul 24 • 25k • 23

liked 4 datasets about 2 months ago

ibm-research/VAREX

Viewer • Updated Mar 18 • 1.78k • 905 • 7

mychen76/wildreceipts_ocr_eval

Viewer • Updated Sep 21, 2023 • 20 • 64 • 1

paperboy-ai/desktop-pii-500

Viewer • Updated Jun 1 • 500 • 173 • 2

Soojuu/mpci-bench

Viewer • Updated May 6 • 7.18k • 79 • 2

liked 2 datasets 3 months ago

inclusionAI/ZwZ-RL-VQA

Viewer • Updated May 28 • 111k • 3.62k • 17

siyanzhao/Openthoughts_math_30k_opsd

Viewer • Updated Feb 23 • 29.4k • 11.8k • 9

upvoted 2 papers 4 months ago

Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training

Paper • 2509.25758 • Published Sep 30, 2025 • 25

The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models

Paper • 2605.06196 • Published May 7 • 9

upvoted an article 4 months ago

view article

Article

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

• 

NormalUhr

•

Feb 11, 2025

• 132

upvoted 2 papers 4 months ago

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Paper • 2601.11061 • Published Jan 16 • 8

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting

Paper • 2601.02151 • Published Jan 5 • 116

liked a dataset 4 months ago

etri-vilab/holisafe-bench

Viewer • Updated Jun 1 • 4.03k • 360 • 11