Count Anything at Any Granularity
Paper • 2605.10887 • Published •
2
Librarian Bot (Bot)
librarian-bot
AI & ML interests
I am a friendly librarian bot working to help improve metadata on the 🤗 hub. Run by Hugging Face'ss Machine Learning Librarian (HF username: davanstrien)
Recent Activity
commentedon a paper about 10 hours ago
Count Anything at Any Granularity commentedon a paper about 18 hours ago
Latent Spatial Memory for Video World Models commentedon a paper about 18 hours ago
Trajectory-Refined DistillationOrganizations
commented a
paper about 10 hours ago
commented 19
papers about 18 hours ago
Latent Spatial Memory for Video World Models
Paper • 2606.09828 • Published • 62 •
2
Trajectory-Refined Distillation
Paper • 2606.08432 • Published • 5 •
2
OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning
Paper • 2606.08572 • Published • 13 •
3
EmpiriGraph-Psy: A Dataset and LLM Pipeline for Extracting Empirical Relation Graphs from Psychology Abstracts
Paper • 2606.08362 • Published • 1 •
2
End-to-End Context Compression at Scale
Paper • 2606.09659 • Published • 22 •
2
CoVEBench: Can Video Editing Models Handle Complex Instructions?
Paper • 2606.08415 • Published • 47 •
3
FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention
Paper • 2606.09079 • Published • 56 •
5
OASIS: From Simulation Data Collection to Real-World Humanoid Loco-Manipulation
Paper • 2606.08548 • Published • 2 •
2
Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
Paper • 2606.09365 • Published • 2 •
2
Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting
Paper • 2606.09809 • Published • 2 •
2
Echo-Memory: A Controlled Study of Memory in Action World Models
Paper • 2606.09803 • Published • 31 •
2
Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short
Paper • 2606.09380 • Published • 7 •
3
Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses
Paper • 2606.08348 • Published • 13 •
2
Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops
Paper • 2606.08960 • Published • 1 •
2
OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics
Paper • 2606.09826 • Published • 16 •
3
Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle
Paper • 2606.09376 • Published •
6
What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
Paper • 2606.05304 • Published • 5 •
2
BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling
Paper • 2606.09707 • Published • 6 •
2
Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning
Paper • 2606.11087 • Published • 3 •
2