SeongWan Kim

idgmatrix's activity

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

upvoted 2 papers about 4 hours ago

Video-Oasis: Rethinking Evaluation of Video Understanding

Paper • 2603.29616 • Published 9 days ago • 38

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

Paper • 2601.16211 • Published 9 days ago • 39

upvoted 3 papers 1 day ago

SceneFrom3D: Geometry-Conditioned Outdoor 3D Scene Generation via View Scheduling with Object-Level Control

Paper • 2607.04540 • Published 6 days ago • 2

LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

Paper • 2607.04412 • Published 6 days ago • 22

Gemma 4 Technical Report

Paper • 2607.02770 • Published 9 days ago • 45

upvoted a paper 2 days ago

3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance

Paper • 2606.31329 • Published 11 days ago • 6

upvoted a paper 3 days ago

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Paper • 2606.29526 • Published 13 days ago • 160

upvoted 2 papers 7 days ago

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

Paper • 2607.02512 • Published 9 days ago • 118

Morphing into Hybrid Attention Models

Paper • 2606.30562 • Published 12 days ago • 47

upvoted 2 papers 8 days ago

Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts

Paper • 2607.00666 • Published 10 days ago • 22

Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning

Paper • 2606.29985 • Published 12 days ago • 20

upvoted 4 papers 9 days ago

DOPD: Dual On-policy Distillation

Paper • 2606.30626 • Published 12 days ago • 103

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

Paper • 2503.15558 • Published Mar 18, 2025 • 52

PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation

Paper • 2606.30673 • Published 16 days ago • 12

Orca: The World is in Your Mind

Paper • 2606.30534 • Published 12 days ago • 310

upvoted 3 papers 10 days ago

AsyncOPD: How Stale Can On-Policy Distillation Be?

Paper • 2606.24143 • Published 18 days ago • 30

PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents

Paper • 2606.29225 • Published 13 days ago • 8

Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs

Paper • 2606.27378 • Published May 7 • 60

upvoted a paper 11 days ago

Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents

Paper • 2606.27595 • Published 16 days ago • 8

upvoted a paper 14 days ago

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Paper • 2606.26790 • Published 16 days ago • 54