Siyeol Kim
siyeolkim
AI & ML interests
None yet
Organizations
RL/RL-like methods
-
Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
Paper • 2502.19328 • Published • 22 -
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
Paper • 2502.18449 • Published • 74 -
Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids
Paper • 2502.20396 • Published • 16 -
Visual-RFT: Visual Reinforcement Fine-Tuning
Paper • 2503.01785 • Published • 80
Interestings
-
Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement
Paper • 2411.06558 • Published • 37 -
SlimLM: An Efficient Small Language Model for On-Device Document Assistance
Paper • 2411.09944 • Published • 12 -
Look Every Frame All at Once: Video-Ma^2mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing
Paper • 2411.19460 • Published • 11 -
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale
Paper • 2412.05237 • Published • 48
Long-context
RL/RL-like methods
-
Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
Paper • 2502.19328 • Published • 22 -
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
Paper • 2502.18449 • Published • 74 -
Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids
Paper • 2502.20396 • Published • 16 -
Visual-RFT: Visual Reinforcement Fine-Tuning
Paper • 2503.01785 • Published • 80
YOLO
Interestings
-
Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement
Paper • 2411.06558 • Published • 37 -
SlimLM: An Efficient Small Language Model for On-Device Document Assistance
Paper • 2411.09944 • Published • 12 -
Look Every Frame All at Once: Video-Ma^2mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing
Paper • 2411.19460 • Published • 11 -
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale
Paper • 2412.05237 • Published • 48