Colin Marsh

c-marsh's activity

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

upvoted a paper 1 day ago

Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence

Paper • 2610.17656 • Published 6 days ago • 28

upvoted 2 papers 2 days ago

WAVE-0: Bridging VLA Policies and WAMs with Lightweight Latent Future Prediction

Paper • 2610.18568 • Published 6 days ago • 47

ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling

Paper • 2610.15166 • Published 9 days ago • 89

upvoted 2 papers 3 days ago

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Paper • 2609.39601 • Published 19 days ago • 322

AgentSWE: Can Coding Agents Build the Agent You Actually Want?

Paper • 2610.13361 • Published 10 days ago • 235

upvoted a paper 4 days ago

Universal Textual Teaching for LLMs

Paper • 2610.12114 • Published 11 days ago • 19

upvoted 3 papers 5 days ago

In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks

Paper • 2609.38173 • Published 20 days ago • 65

A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learning

Paper • 2606.03335 • Published 13 days ago • 33

From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation

Paper • 2610.06100 • Published 14 days ago • 144

upvoted 2 papers 6 days ago

Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation

Paper • 2610.02368 • Published 18 days ago • 74

ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation

Paper • 2609.39306 • Published 19 days ago • 44

upvoted a paper 7 days ago

Adaptive Latent Capacity for World Models

Paper • 2609.32921 • Published 23 days ago • 24

upvoted 2 papers 8 days ago

World Action Learning via Interaction-Centric Spectral Latent Guidance

Paper • 2610.03607 • Published 17 days ago • 50

Harness Engineering for Software Engineering via Modular Executable Dev-Primitives

Paper • 2610.07832 • Published 13 days ago • 13

upvoted 3 papers 9 days ago

World Models' Last Exam in Physics

Paper • 2610.08791 • Published 13 days ago • 30

RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning

Paper • 2610.09455 • Published 12 days ago • 46

AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation

Paper • 2610.01218 • Published 18 days ago • 30

upvoted 2 papers 10 days ago

When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models

Paper • 2610.05719 • Published 14 days ago • 35

LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures

Paper • 2610.04292 • Published 16 days ago • 40

upvoted a paper 11 days ago

Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models

Paper • 2609.39820 • Published 19 days ago • 31