dooho lee

BlueYellowGreen's activity

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

upvoted 4 papers 3 days ago

Shaping capabilities with token-level data filtering

Paper • 2601.21571 • Published 8 days ago • 25

ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation

Paper • 2601.21420 • Published 8 days ago • 42

Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives

Paper • 2601.20833 • Published 9 days ago • 172

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

Paper • 2601.22975 • Published 7 days ago • 80

upvoted a paper 7 days ago

Qwen3-ASR Technical Report

Paper • 2601.21337 • Published 8 days ago • 33

upvoted 11 papers 8 days ago

Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow

Paper • 2601.14243 • Published 17 days ago • 21

Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification

Paper • 2601.15808 • Published 15 days ago • 20

SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents

Paper • 2601.16746 • Published 14 days ago • 89

LongCat-Flash-Thinking-2601 Technical Report

Paper • 2601.16725 • Published 14 days ago • 174

AR-Omni: A Unified Autoregressive Model for Any-to-Any Generation

Paper • 2601.17761 • Published 12 days ago • 14

VIBEVOICE-ASR Technical Report

Paper • 2601.18184 • Published 11 days ago • 20

DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints

Paper • 2601.18137 • Published 11 days ago • 25

Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability

Paper • 2601.18778 • Published 11 days ago • 40

Linear representations in language models can change dramatically over a conversation

Paper • 2601.20834 • Published 9 days ago • 21

DeepSeek-OCR 2: Visual Causal Flow

Paper • 2601.20552 • Published 9 days ago • 53

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation

Paper • 2601.20614 • Published 9 days ago • 116

upvoted 4 papers 11 days ago

FlowAct-R1: Towards Interactive Humanoid Video Generation

Paper • 2601.10103 • Published 22 days ago • 73

Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs

Paper • 2601.08763 • Published 24 days ago • 146

Your Group-Relative Advantage Is Biased

Paper • 2601.08521 • Published 24 days ago • 150

OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer

Paper • 2601.14250 • Published 17 days ago • 47