Indramal Wansekara
Indramal
AI & ML interests
NLP
Reinforcement Learning
Computer Vision
Robotics
Electronics
Electrical
Data-Driven Systems
Cloud
App (Desktop/Mobile)
Organizations
None yet
Reasoning
-
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 47 -
VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
Paper • 2505.23359 • Published • 38 -
OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation
Paper • 2506.02397 • Published • 35 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 143
Video Diffusion
Optimization
-
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
Paper • 2510.11696 • Published • 176 -
Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation
Paper • 2510.21583 • Published • 30 -
Sparser Block-Sparse Attention via Token Permutation
Paper • 2510.21270 • Published • 24
Robotics
Diffusion
Reasoning
-
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 47 -
VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
Paper • 2505.23359 • Published • 38 -
OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation
Paper • 2506.02397 • Published • 35 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 143
Agent
Video Diffusion
Multi Model
Optimization
-
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
Paper • 2510.11696 • Published • 176 -
Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation
Paper • 2510.21583 • Published • 30 -
Sparser Block-Sparse Attention via Token Permutation
Paper • 2510.21270 • Published • 24
Reinforcement Learning