松田 涼子

Matryok's activity

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

upvoted 2 papers 5 days ago

Latent Reasoning in Continuous Space for Unified Multimodal Models

Paper • 2610.42149 • Published 13 days ago • 45

LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers

Paper • 2611.05304 • Published 8 days ago • 11

upvoted 3 papers 6 days ago

Is Forgetting Unified? Exploring Concept Unlearning in Unified Multimodal Models

Paper • 2611.04467 • Published 9 days ago • 5

YANAMI: A Large-Scale Multimodal Dataset and Benchmark for Multiturn Stateful Interaction

Paper • 2611.05280 • Published 9 days ago • 34

WebHarbor: Docking Real Websites for Evolving GUI Agent Environments

Paper • 2611.03634 • Published 10 days ago • 27

upvoted 2 papers 7 days ago

SIMIT: Self-Improving Vision-Language Models via Imagination at Test-Time

Paper • 2611.00053 • Published Oct 11 • 6

Advancing SVD-based LLM Compression via Layer-Wise Error Model Search

Paper • 2610.32878 • Published 20 days ago • 7

upvoted 3 papers 9 days ago

Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers

Paper • 2610.40647 • Published 14 days ago • 27

EditAgent: Rethinking Agentic Image Editing

Paper • 2610.39664 • Published 14 days ago • 13

Intrinsic Distribution Matching

Paper • 2610.39633 • Published 14 days ago • 31

upvoted 2 papers 11 days ago

Beyond the Estimate: Wiener-Informed Decoding for Easier Training of Pixel-Space Flow Models

Paper • 2610.36192 • Published 17 days ago • 12

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

Paper • 2610.37230 • Published 16 days ago • 26

upvoted a paper 13 days ago

Hy-Nomas: Towards Free-form Interactive World Generation

Paper • 2610.36729 • Published 16 days ago • 113

upvoted a paper 14 days ago

ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence

Paper • 2610.34283 • Published 18 days ago • 40

upvoted 3 papers 15 days ago

Work Agents: Systems, Capabilities, and Optimization

Paper • 2610.35845 • Published 17 days ago • 116

SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing

Paper • 2610.14253 • Published 29 days ago • 4

DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation

Paper • 2610.32002 • Published 21 days ago • 16