Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs
Paper • 2608.12781 • Published • 29
Yuseung "Phillip" Lee
phillipinseoul
AI & ML interests
Computer Vision
Recent Activity
upvoted a paper about 5 hours ago
Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs upvoted a paper about 5 hours ago
Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection upvoted a paper about 5 hours ago
Prime Agent: A Self-Improving RLM HarnessOrganizations
upvoted 3
papers about 5 hours ago
upvoted 2
papers 3 days ago
upvoted a paper 4 days ago
upvoted 2
papers 6 days ago
upvoted a paper 7 days ago
upvoted 3
papers 8 days ago
Self-Supervised Visual On-Policy Distillation
Paper • 2608.14144 • Published • 169
PRM-as-a-Judge 1.5: A Toolkit for Robot Process Assessment
Paper • 2608.14284 • Published • 14
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
Paper • 2608.13417 • Published • 55
upvoted a paper 10 days ago
upvoted 4
papers 21 days ago
Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures
Paper • 2607.28802 • Published • 10
DiffusionGemma Technical Report
Paper • 2608.00146 • Published • 39
SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation
Paper • 2608.02287 • Published • 31
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
Paper • 2608.01964 • Published • 181
upvoted 3
papers 26 days ago
Visual prompt engineering for video models
Paper • 2607.25537 • Published • 22
PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models
Paper • 2607.24957 • Published • 20
ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition
Paper • 2607.25565 • Published • 66