Jinheon Baek

jinheon's activity

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

upvoted a paper 2 days ago

Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay

Paper • 2610.27954 • Published 16 days ago • 34

upvoted a paper 3 days ago

Latent Reasoning in Continuous Space for Unified Multimodal Models

Paper • 2610.42149 • Published 6 days ago • 44

upvoted 2 papers 6 days ago

Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs

Paper • 2610.36671 • Published 9 days ago • 116

OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images

Paper • 2610.35684 • Published 10 days ago • 59

upvoted a paper 8 days ago

Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data

Paper • 2610.37386 • Published 9 days ago • 25

upvoted a paper 9 days ago

Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery

Paper • 2610.32195 • Published 13 days ago • 26

upvoted a paper 13 days ago

Self-Distilling Future Video Representations for World Action Models

Paper • 2610.30320 • Published 15 days ago • 37

upvoted a paper 15 days ago

Learning the 4D World through Point Trajectory Forecasting

Paper • 2610.28594 • Published 16 days ago • 51

upvoted a paper 17 days ago

Into the Unknown: Benchmarking AI agents on open scientific research problems

Paper • 2610.19159 • Published 23 days ago • 56

upvoted a paper 22 days ago

ResidualQuant: KV Cache Quantization for Looped Transformers with 2-Bit Residuals

Paper • 2610.10381 • Published 29 days ago • 9

upvoted a paper 28 days ago

RunningTab: Direct Workspace Interaction with Environment-Side Tabs

Paper • 2610.10444 • Published 29 days ago • 38

submitted a paper to Daily Papers 28 days ago

RunningTab: Direct Workspace Interaction with Environment-Side Tabs

Paper • 2610.10444 • Published 29 days ago • 38

upvoted a paper 29 days ago

AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents

Paper • 2610.05140 • Published Oct 4 • 33

upvoted 7 papers about 1 month ago

Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers

Paper • 2610.00531 • Published Sep 30 • 30

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published Sep 30 • 95

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

Paper • 2606.29082 • Published Jun 27 • 42

EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery

Paper • 2609.40340 • Published Sep 30 • 91

Follow the Entities: A Corpus Map for Agentic Search

Paper • 2609.37226 • Published Sep 29 • 56

Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR

Paper • 2609.37868 • Published Sep 29 • 38

Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning

Paper • 2609.33781 • Published Sep 27 • 33