SeongWan Kim

idgmatrix's activity

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

upvoted a paper 4 days ago

EvoOntology: A Self-Evolving Ontology Layer for Data Agents

Paper • 2609.15779 • Published 12 days ago • 152

upvoted a paper 7 days ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 9 days ago • 179

upvoted a paper 9 days ago

EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents

Paper • 2609.17632 • Published 11 days ago • 39

upvoted a paper 10 days ago

AI for Games in the Foundation Model Era

Paper • 2609.16679 • Published 11 days ago • 146

upvoted a paper 11 days ago

PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization

Paper • 2608.30597 • Published 26 days ago • 27

upvoted 2 papers 12 days ago

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

Paper • 2609.07064 • Published 19 days ago • 146

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published 28 days ago • 478

upvoted 3 papers 16 days ago

Revisiting Complete Reasoning Traces for Post-Training

Paper • 2609.07103 • Published 19 days ago • 23

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published 18 days ago • 174

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

Paper • 2609.08798 • Published 18 days ago • 83

upvoted 3 papers 17 days ago

Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models

Paper • 2609.04714 • Published 22 days ago • 6

Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models

Paper • 2609.04720 • Published 22 days ago • 9

Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs

Paper • 2609.04753 • Published 22 days ago • 16

upvoted 2 papers 19 days ago

PACE: Towards Surfacing Hidden Conflicts in User Requests

Paper • 2609.03293 • Published 23 days ago • 24

RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests

Paper • 2608.27831 • Published 26 days ago • 33

upvoted 3 papers 22 days ago

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Paper • 2609.02749 • Published 24 days ago • 402

MULTI3IR: A Benchmark for Multi-perspective Multi-domain Multi-modal Information Retrieval

Paper • 2608.30949 • Published 26 days ago • 10

Language Models Can Control Their Own Attention

Paper • 2609.02737 • Published 24 days ago • 79

upvoted a paper 23 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 25 days ago • 387

upvoted a paper 24 days ago

ReFlowSET: Representation-Aligned Latent Flow Matching for SAR-to-EO Image Translation

Paper • 2609.00968 • Published 25 days ago • 5