Basil Cheer

basilcheer's activity

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

upvoted a paper about 7 hours ago

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

Paper • 2603.16932 • Published 11 days ago • 66

upvoted a paper about 8 hours ago

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

Paper • 2603.21606 • Published 2 days ago • 31

upvoted a paper about 22 hours ago

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

Paper • 2603.21383 • Published 3 days ago • 13

upvoted a paper about 23 hours ago

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

Paper • 2603.22285 • Published 1 day ago • 45

upvoted a paper 1 day ago

Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD

Paper • 2603.20155 • Published 5 days ago • 7

upvoted an article 1 day ago

view article

Article

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

• 

8 days ago

•

14

upvoted a paper 1 day ago

WorldAgents: Can Foundation Image Models be Agents for 3D World Models?

Paper • 2603.19708 • Published 5 days ago • 10

liked a model 1 day ago

Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF

Image-Text-to-Text • 27B • Updated about 8 hours ago • 41.3k • 116

upvoted 2 papers 2 days ago

LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation

Paper • 2603.20192 • Published 5 days ago • 22

FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow

Paper • 2603.19598 • Published 5 days ago • 31

liked 2 datasets 2 days ago

th1nhng0/vietnamese-legal-documents

Viewer • Updated 3 days ago • 1.04M • 5.2k • 67

Lossfunk/Esolang-Bench

Viewer • Updated 18 days ago • 160 • 67 • 8

upvoted a paper 3 days ago

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer

Paper • 2603.19227 • Published 6 days ago • 40

liked a dataset 3 days ago

open-index/hacker-news

Updated 1 minute ago • 9.33k • 177

upvoted 3 papers 3 days ago

LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition

Paper • 2603.17965 • Published 7 days ago • 5

Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens

Paper • 2603.19232 • Published 6 days ago • 32

Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing

Paper • 2603.17942 • Published 7 days ago • 6

liked a Space 3 days ago

Running

Featured

50

Nemotron 3 Nano WebGPU

⚛

50

A compact reasoning-capable model running in your browser.

upvoted 2 papers 3 days ago

FASTER: Rethinking Real-Time Flow VLAs

Paper • 2603.19199 • Published 6 days ago • 53

BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs

Paper • 2603.16557 • Published 8 days ago • 21