SeongWan Kim

idgmatrix's activity

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

upvoted 3 papers 1 day ago

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

Paper • 2609.02749 • Published 3 days ago • 515

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

Paper • 2608.30949 • Published 5 days ago • 8

Language Models Can Control Their Own Attention

Paper • 2609.02737 • Published 3 days ago • 59

upvoted 5 papers 3 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 4 days ago • 480

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

Paper • 2609.00968 • Published 4 days ago • 5

Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching

Paper • 2609.01404 • Published 4 days ago • 26

Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering

Paper • 2608.30468 • Published 5 days ago • 32

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published 5 days ago • 139

upvoted 6 papers 4 days ago

Verification-Aware Training for Speculative Decoding

Paper • 2608.30135 • Published 5 days ago • 9

Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions

Paper • 2608.30428 • Published 5 days ago • 14

Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation

Paper • 2608.24293 • Published 11 days ago • 13

Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase

Paper • 2608.29310 • Published 7 days ago • 27

SHAPE of Chain-of-Thought in Math Reasoning

Paper • 2608.28600 • Published Jun 28 • 31

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Paper • 2604.05091 • Published Apr 6 • 48

upvoted 2 papers 5 days ago

Language Chain in Alignment: Cross-lingual Ranking Preference Optimization

Paper • 2608.23149 • Published 12 days ago • 6

J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data

Paper • 2608.26582 • Published 9 days ago • 43

upvoted a paper 9 days ago

Meta^n: Recursive Self-Improvement through Emergent Depth

Paper • 2608.24735 • Published 11 days ago • 15

upvoted 2 papers 10 days ago

On-policy Distillation with Verifiable Reward

Paper • 2608.24696 • Published 11 days ago • 17

On-Policy Self-Distillation in Diffusion Models

Paper • 2608.24646 • Published 11 days ago • 67

upvoted a paper 11 days ago

EchoWM: Open and Enterable Omnimodal World Models

Paper • 2608.23189 • Published 12 days ago • 79