Lucas Oliveira

lucasolive

·

AI & ML interests

Reinforcement learning, reward modeling, RLHF, policy optimization, offline RL

Recent Activity

liked a dataset about 2 hours ago

introvoyz041/reinforcement-learning

liked a dataset about 2 hours ago

andersonbcdefg/dolly_reward_modeling_pairwise

liked a dataset about 2 hours ago

andersonbcdefg/sharegpt_reward_modeling_pairwise

View all activity

Organizations

None yet

upvoted 2 papers about 2 hours ago

PACT: From Credit Assignment to Critic Alignment

Paper • 2609.26355 • Published 7 days ago • 26

PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing

Paper • 2609.23784 • Published 9 days ago • 13

upvoted 2 papers 2 days ago

VideoGen-Agent: Reinforcing Video Generation Agents

Paper • 2609.24997 • Published 8 days ago • 71

LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay

Paper • 2609.25053 • Published 22 days ago • 17

upvoted 5 papers 7 days ago

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2609.20784 • Published 12 days ago • 57

Region-Level Policy Optimization for Fine-grained MLLM Perception

Paper • 2609.19745 • Published 12 days ago • 41

PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?

Paper • 2609.18605 • Published 13 days ago • 41

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Paper • 2609.18708 • Published 13 days ago • 82

SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization

Paper • 2609.14320 • Published 16 days ago • 34