Basil Cheer

basilcheer's activity

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

upvoted 3 papers about 10 hours ago

NeuROK: Generative 4D Neural Object Kinematics

Paper • 2605.30347 • Published 4 days ago • 6

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

Paper • 2605.30161 • Published 4 days ago • 38

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation

Paper • 2605.27366 • Published 6 days ago • 24

liked a dataset about 22 hours ago

open-thoughts/AgentTrove

Viewer • Updated 24 days ago • 1.7M • 12k • 174

upvoted 2 papers about 24 hours ago

EarlyTom: Early Token Compression Completes Fast Video Understanding

Paper • 2605.30010 • Published 4 days ago • 27

Native Audio-Visual Alignment for Generation

Paper • 2605.30073 • Published 4 days ago • 24

liked a model 1 day ago

nvidia/LocateAnything-3B

Image-Text-to-Text • 4B • Updated 4 days ago • 24.6k • 550

upvoted a paper 1 day ago

LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training

Paper • 2605.29888 • Published 4 days ago • 21

upvoted an article 1 day ago

view article

Article

Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler

• 
• 
• +3

ariG23498, sayakpaul, sergiopaniego, ror, pcuenq

•

3 days ago

• 44

upvoted 2 papers 1 day ago

YoCausal: How Far is Video Generation from World Model? A Causality Perspective

Paper • 2605.30346 • Published 4 days ago • 40

Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving

Paper • 2605.23163 • Published 7 days ago • 17

liked a dataset 1 day ago

openbmb/UltraData-SFT-2605

Updated 3 days ago • 11k • 227

liked a model 1 day ago

ernie-research/NAVA

Text-to-Video • Updated about 20 hours ago • 71 • 33

upvoted 3 papers 1 day ago

How LoRA Remembers? A Parametric Memory Law for LLM Finetuning

Paper • 2605.30260 • Published 4 days ago • 27

Colored Noise Diffusion Sampling

Paper • 2605.30332 • Published 4 days ago • 18

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models

Paper • 2605.30263 • Published 4 days ago • 49

upvoted 2 papers 2 days ago

CubePart: An Open-Vocabulary Part-Controllable 3D Generator

Paper • 2605.28763 • Published 5 days ago • 12

VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild

Paper • 2605.27882 • Published 5 days ago • 11

upvoted a changelog 2 days ago

view changelog

Hugging Face Changelog

Filter Models page by Base Models only

3 days ago

• 63

upvoted a paper 2 days ago

DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes

Paper • 2605.28421 • Published 5 days ago • 44