Colin Marsh

c-marsh's activity

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

upvoted 3 papers 1 day ago

PhotoGuider: Composition-Aware Cropping and 360^{circ} View Framing with Explainable Photographic Assessments

Paper • 2611.02897 • Published 4 days ago • 39

WorldBridge: Bridging Video and Action for Task Generalization in World Action Models

Paper • 2610.40748 • Published 8 days ago • 14

R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop

Paper • 2610.22740 • Published 15 days ago • 47

upvoted 2 papers 3 days ago

SO-101 Bench: Accessible Spatial Manipulation

Paper • 2610.36420 • Published 10 days ago • 11

A Broader Look into MLLM's Retrieval Heads

Paper • 2610.32411 • Published 14 days ago • 34

upvoted 4 papers 4 days ago

Toward Recursive Self-Improvement in Physical AI

Paper • 2610.29677 • Published 16 days ago • 19

Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception

Paper • 2610.37037 • Published 10 days ago • 29

ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning

Paper • 2610.37666 • Published 10 days ago • 58

OmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning

Paper • 2601.15351 • Published 14 days ago • 4

upvoted 4 papers 5 days ago

FocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models

Paper • 2610.31423 • Published 15 days ago • 3

MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models

Paper • 2610.22951 • Published 21 days ago • 7

DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning

Paper • 2610.32093 • Published 14 days ago • 19

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

Paper • 2610.32749 • Published 14 days ago • 29

upvoted a paper 7 days ago

RSI Arena: Towards Recursive Self-Improvement with Human Feedback

Paper • 2610.33624 • Published 13 days ago • 26

upvoted 3 papers 8 days ago

RoboHarness: A Simple Harness Outperforms VLA and World Action Models

Paper • 2610.14018 • Published 21 days ago • 6

RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions

Paper • 2610.34356 • Published 12 days ago • 11

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

Paper • 2610.33956 • Published 12 days ago • 34

upvoted a paper 10 days ago

Deep Search in Real-World Web Environments

Paper • 2610.30181 • Published 18 days ago • 108

upvoted a paper 11 days ago

SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation

Paper • 2610.25844 • Published 18 days ago • 31

upvoted a paper 12 days ago

Learning from Fleet Experience: A Collective Learning Paradigm for Robots

Paper • 2610.25736 • Published 18 days ago • 112