SeongWan Kim

idgmatrix's activity

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

upvoted a paper about 11 hours ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 2 days ago • 416

upvoted 4 papers about 16 hours ago

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

Paper • 2609.00968 • Published 2 days ago • 3

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

Paper • 2609.01404 • Published 2 days ago • 20

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

Paper • 2608.30468 • Published 3 days ago • 24

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

Paper • 2608.31046 • Published 3 days ago • 126

upvoted 6 papers 1 day ago

Verification-Aware Training for Speculative Decoding

Paper • 2608.30135 • Published 3 days ago • 5

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

Paper • 2608.30428 • Published 3 days ago • 12

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

Paper • 2608.24293 • Published 9 days ago • 11

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

Paper • 2608.29310 • Published 5 days ago • 25

SHAPE of Chain-of-Thought in Math Reasoning

Paper • 2608.28600 • Published Jun 28 • 27

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

Paper • 2604.05091 • Published Apr 6 • 48

upvoted 2 papers 2 days ago

Language Chain in Alignment: Cross-lingual Ranking Preference Optimization

Paper • 2608.23149 • Published 9 days ago • 4

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

Paper • 2608.26582 • Published 7 days ago • 40

upvoted a paper 7 days ago

Meta^n: Recursive Self-Improvement through Emergent Depth

Paper • 2608.24735 • Published 9 days ago • 15

upvoted 2 papers 8 days ago

On-policy Distillation with Verifiable Reward

Paper • 2608.24696 • Published 9 days ago • 17

On-Policy Self-Distillation in Diffusion Models

Paper • 2608.24646 • Published 9 days ago • 67

upvoted 3 papers 9 days ago

EchoWM: Open and Enterable Omnimodal World Models

Paper • 2608.23189 • Published 10 days ago • 79

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

Paper • 2608.19567 • Published 14 days ago • 33

Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence

Paper • 2608.21156 • Published 13 days ago • 63

upvoted a paper 10 days ago

Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts

Paper • 2608.20061 • Published 13 days ago • 46