Kaito Miyazaki

kaitomiya's activity

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

upvoted 2 papers about 16 hours ago

Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use

Paper • 2610.40738 • Published 6 days ago • 37

When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications

Paper • 2610.40256 • Published 6 days ago • 11

upvoted a paper 2 days ago

Your Benchmark Is an Empirical Measure Over Difficulty

Paper • 2610.29927 • Published 14 days ago • 26

upvoted 3 papers 3 days ago

Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization

Paper • 2610.24385 • Published 18 days ago • 4

Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution

Paper • 2610.32285 • Published 12 days ago • 35

TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving

Paper • 2610.37230 • Published 8 days ago • 28

upvoted 2 papers 4 days ago

Thinking-in-Bets at Test Time Reduces Sycophantic Revisions in LLM Agents

Paper • 2610.34654 • Published 9 days ago • 11

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

Paper • 2610.35684 • Published 9 days ago • 59

upvoted a paper 5 days ago

Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes

Paper • 2610.32749 • Published 12 days ago • 32

upvoted 2 papers 6 days ago

What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents

Paper • 2610.34491 • Published 10 days ago • 23

Rollback: Experience Backtracking in World Models for Policy Improvement

Paper • 2610.36068 • Published 9 days ago • 55

upvoted 2 papers 7 days ago

Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents

Paper • 2610.33956 • Published 10 days ago • 34

HiP3R: Hierarchical Pose Graphs for Long-Horizon 3D Reconstruction

Paper • 2610.31635 • Published 13 days ago • 25

upvoted 2 papers 8 days ago

JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making

Paper • 2610.19589 • Published 21 days ago • 6

Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval

Paper • 2610.14465 • Published 18 days ago • 4

upvoted 2 papers 9 days ago

SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs

Paper • 2610.31062 • Published 13 days ago • 12

SEAM: Spectral Embedding Alignment and Merging for Low-Resource TTS

Paper • 2610.26252 • Published 16 days ago • 6

upvoted 3 papers 10 days ago

VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents

Paper • 2610.28679 • Published 16 days ago • 15

SciΠvot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents

Paper • 2610.21082 • Published 20 days ago • 13

ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination

Paper • 2610.29934 • Published 14 days ago • 6