Seong Joon Oh

coallaoh's activity

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

upvoted 2 papers 3 days ago

Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery

Paper • 2610.32195 • Published 8 days ago • 43

Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL

Paper • 2610.33512 • Published 7 days ago • 49

upvoted a paper 7 days ago

Self-Distilling Future Video Representations for World Action Models

Paper • 2610.30320 • Published 10 days ago • 52

upvoted a paper 16 days ago

ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models

Paper • 2610.18596 • Published 18 days ago • 23

upvoted a paper 29 days ago

Follow the Entities: A Corpus Map for Agentic Search

Paper • 2609.37226 • Published Sep 29 • 101

upvoted 3 papers about 1 month ago

Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR

Paper • 2609.37868 • Published Sep 29 • 65

Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge

Paper • 2609.34327 • Published Sep 28 • 41

Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning

Paper • 2609.33781 • Published Sep 27 • 46

upvoted a paper about 2 months ago

SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

Paper • 2609.07064 • Published Sep 7 • 83

upvoted a paper 5 months ago

How can embedding models bind concepts?

Paper • 2605.31503 • Published May 29 • 5

upvoted a paper 6 months ago

MEME: Multi-entity & Evolving Memory Evaluation

Paper • 2605.12477 • Published May 12 • 7

upvoted 2 papers 8 months ago

Half-Truths Break Similarity-Based Retrieval

Paper • 2602.23906 • Published Feb 27 • 6

Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models

Paper • 2602.24264 • Published Feb 27 • 14

upvoted a paper 12 months ago

Qwen-Image Technical Report

Paper • 2508.02324 • Published Aug 4, 2025 • 278

upvoted 3 papers about 1 year ago

Is Multilingual LLM Watermarking Truly Multilingual? A Simple Back-Translation Solution

Paper • 2510.18019 • Published Oct 20, 2025 • 18

Dr.LLM: Dynamic Layer Routing in LLMs

Paper • 2510.12773 • Published Oct 14, 2025 • 32

DISCO: Diversifying Sample Condensation for Efficient Model Evaluation

Paper • 2510.07959 • Published Oct 9, 2025 • 16

upvoted a collection about 1 year ago

🫗 Leaky Thoughts

Collection

Data of the "Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers" paper • 2 items • Updated Oct 15, 2025 • 1

upvoted 2 papers over 1 year ago

On the rankability of visual embeddings

Paper • 2507.03683 • Published Jul 4, 2025 • 16

Diffusion Classifiers Understand Compositionality, but Conditions Apply

Paper • 2505.17955 • Published May 23, 2025 • 22