Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization
Paper • 2606.12373 • Published • 7 •
2
Librarian Bot (Bot)
librarian-bot
AI & ML interests
I am a friendly librarian bot working to help improve metadata on the 🤗 hub. Run by Hugging Face'ss Machine Learning Librarian (HF username: davanstrien)
Recent Activity
commentedon a paper about 2 hours ago
Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization commentedon a paper about 2 hours ago
Building Social World Models with Large Language Models commentedon a paper about 2 hours ago
Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language ModelsOrganizations
commented 14
papers about 2 hours ago
Building Social World Models with Large Language Models
Paper • 2606.11482 • Published • 1 •
2
Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models
Paper • 2606.12412 • Published • 15 •
3
Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay
Paper • 2606.11786 • Published • 2 •
2
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
Paper • 2606.12191 • Published • 58 •
3
Time-Series Foundation Model Embeddings for Remaining Useful Life Estimation
Paper • 2606.11990 • Published • 3 •
2
On Subquadratic Architectures: From Applications to Principles
Paper • 2606.12364 • Published • 22 •
3
i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
Paper • 2606.11289 • Published • 8 •
2
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
Paper • 2606.12370 • Published • 20 •
4
InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning
Paper • 2606.12195 • Published • 20 •
2
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
Paper • 2606.12344 • Published • 62 •
3
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Paper • 2606.11926 • Published • 104 •
6
Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs
Paper • 2606.12385 • Published • 2 •
2
RepWAM: World Action Modeling with Representation Visual-Action Tokenizers
Paper • 2606.13674 • Published • 5 •
2
commented 6
papers about 3 hours ago
Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning
Paper • 2606.11683 • Published • 28 •
2
World Pilot: Steering Vision-Language-Action Models with World-Action Priors
Paper • 2606.12403 • Published • 23 •
2
Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning
Paper • 2606.13106 • Published • 16 •
2
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
Paper • 2606.13673 • Published • 80 •
3
Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
Paper • 2606.12674 • Published • 3 •
2
PianoKontext: Expressive Performance Rendering from Deadpan Context
Paper • 2606.12282 • Published • 1 •
2