Basil Cheer

basilcheer's activity

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

upvoted 3 papers about 4 hours ago

Process Rewards with Learned Reliability

Paper • 2605.15529 • Published 6 days ago • 47

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Paper • 2605.15178 • Published 7 days ago • 80

Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation

Paper • 2605.16003 • Published 6 days ago • 3

upvoted 2 papers about 17 hours ago

TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking

Paper • 2605.12587 • Published 9 days ago • 37

Aurora: Unified Video Editing with a Tool-Using Agent

Paper • 2605.18748 • Published 3 days ago • 24

upvoted 8 papers 1 day ago

Qwen-Image-VAE-2.0 Technical Report

Paper • 2605.13565 • Published 8 days ago • 58

PhysBrain 1.0 Technical Report

Paper • 2605.15298 • Published 7 days ago • 138

KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration

Paper • 2605.14278 • Published 7 days ago • 37

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models

Paper • 2605.17672 • Published 4 days ago • 20

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Paper • 2605.18401 • Published 3 days ago • 119

Quantitative Video World Model Evaluation for Geometric-Consistency

Paper • 2605.15185 • Published 7 days ago • 3

Orchard: An Open-Source Agentic Modeling Framework

Paper • 2605.15040 • Published 7 days ago • 19

Code as Agent Harness

Paper • 2605.18747 • Published 3 days ago • 182

upvoted 3 papers 19 days ago

Efficient Training on Multiple Consumer GPUs with RoundPipe

Paper • 2604.27085 • Published 22 days ago • 40

PhyCo: Learning Controllable Physical Priors for Generative Motion

Paper • 2604.28169 • Published 21 days ago • 13

Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling

Paper • 2604.27039 • Published 22 days ago • 24

upvoted a collection 19 days ago

IBM Granite 4.1

Collection

now with high IQ • 22 items • Updated 7 days ago • 4

upvoted 2 papers 19 days ago

Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows

Paper • 2604.28139 • Published 21 days ago • 42

FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments

Paper • 2604.25135 • Published 23 days ago • 12

upvoted a paper 20 days ago

RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments

Paper • 2604.26067 • Published 23 days ago • 73