Byung-Kwan Lee

BK-Lee's activity

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

upvoted a paper about 2 hours ago

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

Paper • 2605.18739 • Published May 18 • 116

upvoted a paper 1 day ago

One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications

Paper • 2606.25621 • Published 3 days ago • 13

upvoted 3 papers 10 days ago

ProCUA-SFT Technical Report

Paper • 2606.17321 • Published 12 days ago • 9

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

Paper • 2606.18216 • Published 11 days ago • 61

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Paper • 2606.15007 • Published 15 days ago • 16

upvoted a paper 15 days ago

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published 16 days ago • 106

upvoted a paper 28 days ago

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

Paper • 2605.30161 • Published 30 days ago • 60

upvoted a paper 29 days ago

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published Jan 30 • 113

upvoted a paper 30 days ago

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Paper • 2605.28774 • Published about 1 month ago • 93

upvoted 6 papers about 1 month ago

Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention

Paper • 2605.22791 • Published May 21 • 33

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

Paper • 2511.21689 • Published Nov 26, 2025 • 128

Harnessing LLM Agents with Skill Programs

Paper • 2605.17734 • Published May 18 • 36

Process Rewards with Learned Reliability

Paper • 2605.15529 • Published May 15 • 53

CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization

Paper • 2605.19436 • Published May 19 • 14

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

Paper • 2605.11609 • Published May 12 • 196

upvoted 5 papers 3 months ago

Vero: An Open RL Recipe for General Visual Reasoning

Paper • 2604.04917 • Published Apr 6 • 34

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

Paper • 2603.24472 • Published Mar 25 • 57

Efficient Reasoning with Balanced Thinking

Paper • 2603.12372 • Published Mar 12 • 151

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

Paper • 2603.19220 • Published Mar 19 • 69

ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents

Paper • 2603.18815 • Published Mar 19 • 14