Sora Kimura

soraktky's activity

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

upvoted 2 papers 1 day ago

Hiding Tool Latency in On-Device Cascaded Voice Agent through Speculative Execution

Paper • 2610.07641 • Published 6 days ago • 15

Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training

Paper • 2610.07510 • Published 7 days ago • 14

upvoted a paper 4 days ago

ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context

Paper • 2609.36684 • Published 13 days ago • 20

upvoted a paper 5 days ago

Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts

Paper • 2610.01153 • Published 11 days ago • 24

upvoted 2 papers 6 days ago

ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization

Paper • 2610.00906 • Published 11 days ago • 85

The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends

Paper • 2609.39661 • Published 12 days ago • 13

upvoted a paper 7 days ago

LLMs are General Asynchronous Agents

Paper • 2609.35427 • Published 14 days ago • 86

upvoted a paper 9 days ago

Scaling Properties of Same-Family On-Policy Distillation

Paper • 2609.32722 • Published 16 days ago • 326

upvoted a paper 11 days ago

Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It

Paper • 2609.32444 • Published 16 days ago • 35

upvoted 2 papers 12 days ago

AgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs

Paper • 2609.31590 • Published 17 days ago • 13

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

Paper • 2609.29845 • Published 18 days ago • 105

upvoted a paper 13 days ago

Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World

Paper • 2609.23038 • Published 23 days ago • 63

upvoted 3 papers 15 days ago

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

Paper • 2609.17488 • Published 27 days ago • 560

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

Paper • 2609.21465 • Published 24 days ago • 153

StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

Paper • 2609.26774 • Published 20 days ago • 56

upvoted a paper 16 days ago

RULER: Instance-aware Rubric Rewards for SVG Generation

Paper • 2609.25270 • Published 21 days ago • 104

upvoted a paper 17 days ago

onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction

Paper • 2609.24983 • Published 21 days ago • 55

upvoted 3 papers 19 days ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published 25 days ago • 139

Region-Level Policy Optimization for Fine-grained MLLM Perception

Paper • 2609.19745 • Published 25 days ago • 41

Srijika: OpenType-Layout-Reusing Font Restyling for Nine Indic Scripts

Paper • 2609.05661 • Published Sep 4 • 41