Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio
Paper • 2603.25926 • Published • 6 •
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
new activity about 15 hours ago
Dhiraj45/NuminaMath-CoT:Librarian Bot: Add language metadata for dataset commentedon a paper about 19 hours ago
Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio commentedon a paper about 19 hours ago
Unified Number-Free Text-to-Motion Generation Via Flow MatchingOrganizations
Librarian Bot: Add language metadata for dataset
#1 opened about 15 hours ago
by librarian-bot
commented 19
papers about 19 hours ago
Unified Number-Free Text-to-Motion Generation Via Flow Matching
Paper • 2603.27040 • Published • 3 •
2
KAT-Coder-V2 Technical Report
Paper • 2603.27703 • Published • 4 •
2
Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design
Paper • 2603.28376 • Published • 14 •
2
SEAR: Schema-Based Evaluation and Routing for LLM Gateways
Paper • 2603.26728 • Published • 8 •
3
A Comparative Study in Surgical AI: Datasets, Foundation Models, and Barriers to Med-AGI
Paper • 2603.27341 • Published • 5 •
2
PRBench: End-to-end Paper Reproduction in Physics Research
Paper • 2603.27646 • Published • 27 •
2
Towards a Medical AI Scientist
Paper • 2603.28589 • Published • 80 •
3
GEditBench v2: A Human-Aligned Benchmark for General Image Editing
Paper • 2603.28547 • Published • 31 •
2
ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks
Paper • 2603.27862 • Published • 21 •
2
MOOZY: A Patient-First Foundation Model for Computational Pathology
Paper • 2603.27048 • Published • 4 •
2
Make Geometry Matter for Spatial Reasoning
Paper • 2603.26639 • Published • 27 •
2
Think over Trajectories: Leveraging Video Generation to Reconstruct GPS Trajectories from Cellular Signaling
Paper • 2603.26610 • Published • 5 •
2
MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences
Paper • 2603.27813 • Published • 18 •
2
INSID3: Training-Free In-Context Segmentation with DINOv3
Paper • 2603.28480 • Published • 3 •
2
Text Data Integration
Paper • 2603.27055 • Published • 5 •
3
DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing
Paper • 2603.28713 • Published • 14 •
1
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms
Paper • 2603.28489 • Published • 25 •
2
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Paper • 2603.28767 • Published • 50 •
3