SeongWan Kim

idgmatrix's activity

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

upvoted 2 papers 1 day ago

OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources

Paper • 2605.29250 • Published 3 days ago • 61

Self-Improving Language Models with Bidirectional Evolutionary Search

Paper • 2605.28814 • Published 4 days ago • 52

upvoted 3 papers 2 days ago

Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents

Paper • 2605.28775 • Published 4 days ago • 34

ResearchMath-14K: Scaling Research-Level Mathematics via Agents

Paper • 2605.28003 • Published 4 days ago • 43

Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction

Paper • 2605.26230 • Published 6 days ago • 38

upvoted a paper 3 days ago

Towards Customized Multimodal Role-Play

Paper • 2605.08129 • Published 30 days ago • 8

upvoted 8 papers 4 days ago

Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation

Paper • 2604.27263 • Published 17 days ago • 11

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

Paper • 2605.20258 • Published 13 days ago • 30

LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters

Paper • 2605.13163 • Published 18 days ago • 9

Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation

Paper • 2605.15669 • Published 16 days ago • 8

FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching

Paper • 2605.20910 • Published 11 days ago • 29

Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?

Paper • 2605.22109 • Published 10 days ago • 169

Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback

Paper • 2605.17448 • Published 14 days ago • 18

HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents

Paper • 2605.17873 • Published 13 days ago • 9

upvoted 3 papers 9 days ago

When Vision Speaks for Sound

Paper • 2605.16403 • Published 18 days ago • 149

Matérn Noise for Triangulation-Agnostic Flow Matching on Meshes

Paper • 2605.19305 • Published 12 days ago • 6

Harnessing LLM Agents with Skill Programs

Paper • 2605.17734 • Published 13 days ago • 34

upvoted 2 papers 10 days ago

Code as Agent Harness

Paper • 2605.18747 • Published 13 days ago • 210

Targeted Neuron Modulation via Contrastive Pair Search

Paper • 2605.12290 • Published 19 days ago • 15

upvoted a paper 11 days ago

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection

Paper • 2605.16839 • Published 15 days ago • 12