SeongWan Kim

idgmatrix's activity

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

upvoted 3 papers about 7 hours ago

Revisiting Complete Reasoning Traces for Post-Training

Paper • 2609.07103 • Published 3 days ago • 7

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

Paper • 2609.08183 • Published 2 days ago • 384

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

Paper • 2609.08798 • Published 2 days ago • 84

upvoted 3 papers 2 days ago

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

Paper • 2609.04714 • Published 6 days ago • 5

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

Paper • 2609.04720 • Published 6 days ago • 4

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

Paper • 2609.04753 • Published 6 days ago • 14

upvoted 2 papers 3 days ago

PACE: Towards Surfacing Hidden Conflicts in User Requests

Paper • 2609.03293 • Published 7 days ago • 24

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

Paper • 2608.27831 • Published 10 days ago • 32

upvoted a paper 6 days ago

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

Paper • 2609.02749 • Published 8 days ago • 539

upvoted 2 papers 7 days ago

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

Paper • 2608.30949 • Published 10 days ago • 9

Language Models Can Control Their Own Attention

Paper • 2609.02737 • Published 8 days ago • 67

upvoted 5 papers 8 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 9 days ago • 486

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

Paper • 2609.00968 • Published 9 days ago • 5

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

Paper • 2609.01404 • Published 9 days ago • 27

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

Paper • 2608.30468 • Published 10 days ago • 37

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

Paper • 2608.31046 • Published 10 days ago • 149

upvoted 4 papers 9 days ago

Verification-Aware Training for Speculative Decoding

Paper • 2608.30135 • Published 10 days ago • 11

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

Paper • 2608.30428 • Published 10 days ago • 14

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

Paper • 2608.24293 • Published 16 days ago • 13

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

Paper • 2608.29310 • Published 12 days ago • 29