Basil Cheer

basilcheer's activity

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

upvoted 5 papers 3 days ago

MARS: Enabling Autoregressive Models Multi-Token Generation

Paper • 2604.07023 • Published 4 days ago • 29

How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings

Paper • 2604.04323 • Published 6 days ago • 36

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Paper • 2604.05015 • Published 6 days ago • 225

Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression

Paper • 2604.01609 • Published 10 days ago • 11

Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning

Paper • 2604.05404 • Published 5 days ago • 39

upvoted a changelog 4 days ago

view changelog

Hugging Face Changelog

Agent Traces on the Hub

5 days ago

• 92

upvoted 2 papers 4 days ago

VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors

Paper • 2604.02486 • Published 10 days ago • 9

LightThinker++: From Reasoning Compression to Memory Management

Paper • 2604.03679 • Published 8 days ago • 30

upvoted 6 papers 5 days ago

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published 6 days ago • 101

MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale

Paper • 2604.04771 • Published 6 days ago • 113

OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

Paper • 2604.04707 • Published 6 days ago • 198

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Paper • 2604.04804 • Published 6 days ago • 27

Self-Distilled RLVR

Paper • 2604.03128 • Published 9 days ago • 154

Test-Time Scaling Makes Overtraining Compute-Optimal

Paper • 2604.01411 • Published 11 days ago • 26

upvoted 5 papers 8 days ago

FlowSlider: Training-Free Continuous Image Editing via Fidelity-Steering Decomposition

Paper • 2604.02088 • Published 10 days ago • 6

UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving

Paper • 2604.02190 • Published 10 days ago • 25

VOID: Video Object and Interaction Deletion

Paper • 2604.02296 • Published 10 days ago • 52

GPA: Learning GUI Process Automation from Demonstrations

Paper • 2604.01676 • Published 10 days ago • 16

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

Paper • 2604.02029 • Published 10 days ago • 137

upvoted a paper 9 days ago

QuitoBench: A High-Quality Open Time Series Forecasting Benchmark

Paper • 2603.26017 • Published 16 days ago • 31