Basil Cheer

basilcheer's activity

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

upvoted 2 papers about 3 hours ago

DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models

Paper • 2603.23499 • Published 1 day ago • 38

TrajLoom: Dense Future Trajectory Generation from Video

Paper • 2603.22606 • Published 2 days ago • 5

upvoted 2 papers about 4 hours ago

VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models

Paper • 2603.22003 • Published 3 days ago • 10

Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos

Paper • 2603.22529 • Published 2 days ago • 4

upvoted a paper about 5 hours ago

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

Paper • 2603.22281 • Published 3 days ago • 12

liked a model about 13 hours ago

AviadDahan/LTX-2.3-ID-LoRA-TalkVid-3K

Any-to-Any • Updated 7 days ago • 87 • 18

liked a dataset about 13 hours ago

TeichAI/Claude-Opus-4.6-Reasoning-887x

Viewer • Updated 2 days ago • 887 • 229 • 20

upvoted a paper about 17 hours ago

Repurposing Geometric Foundation Models for Multi-view Diffusion

Paper • 2603.22275 • Published 3 days ago • 40

upvoted 5 papers about 20 hours ago

PEARL: Personalized Streaming Video Understanding Model

Paper • 2603.20422 • Published 6 days ago • 36

The Universal Normal Embedding

Paper • 2603.21786 • Published 3 days ago • 12

MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

Paper • 2603.22458 • Published 3 days ago • 113

Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck

Paper • 2603.08462 • Published 17 days ago • 21

Generalized Discrete Diffusion from Snapshots

Paper • 2603.21342 • Published 4 days ago • 11

upvoted an article about 20 hours ago

view article

Article

Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding

• 

7 days ago

•

43

upvoted 2 papers 1 day ago

Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs

Paper • 2603.16932 • Published 12 days ago • 76

mSFT: Addressing Dataset Mixtures Overfiting Heterogeneously in Multi-task SFT

Paper • 2603.21606 • Published 3 days ago • 35

upvoted 3 papers 2 days ago

PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost

Paper • 2603.21383 • Published 3 days ago • 14

VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding

Paper • 2603.22285 • Published 3 days ago • 45

Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD

Paper • 2603.20155 • Published 6 days ago • 7

upvoted an article 2 days ago

view article

Article

**LoRA Fine-Tuning BitNet b1.58 LLMs on Heterogeneous Edge GPUs via QVAC Fabric**

• 

9 days ago

•

14