HeBA: Heterogeneous Bottleneck Adapters for Robust Vision-Language Models
Paper • 2603.16653 • Published • 1 •
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 2 hours ago
HeBA: Heterogeneous Bottleneck Adapters for Robust Vision-Language Models commentedon a paper about 2 hours ago
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild commentedon a paper about 2 hours ago
Unified Spatio-Temporal Token Scoring for Efficient Video VLMsOrganizations
commented 20
papers about 2 hours ago
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
Paper • 2603.17187 • Published • 98 •
3
Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
Paper • 2603.18004 • Published • 5 •
1
Complementary Reinforcement Learning
Paper • 2603.17621 • Published • 28 •
2
RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference
Paper • 2603.17891 • Published • 2 •
3
Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA
Paper • 2603.08501 • Published •
2
Stereo World Model: Camera-Guided Stereo Video Generation
Paper • 2603.17375 • Published • 8 •
2
Alignment Makes Language Models Normative, Not Descriptive
Paper • 2603.17218 • Published • 36 •
3
BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs
Paper • 2603.16557 • Published • 15 •
2
Conservative Offline Robot Policy Learning via Posterior-Transition Reweighting
Paper • 2603.16542 • Published • 10 •
2
GigaWorld-Policy: An Efficient Action-Centered World--Action Model
Paper • 2603.17240 • Published • 20 •
2
Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing
Paper • 2603.11535 • Published • 7 •
2
Video-CoE: Reinforcing Video Event Prediction via Chain of Events
Paper • 2603.14935 • Published • 86 •
3
PRISM: Demystifying Retention and Interaction in Mid-Training
Paper • 2603.17074 • Published •
1
Efficient Reasoning with Balanced Thinking
Paper • 2603.12372 • Published • 6 •
3
Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing
Paper • 2603.17942 • Published • 2 •
2
When AI Navigates the Fog of War
Paper • 2603.16642 • Published • 22 •
3
Efficient Exploration at Scale
Paper • 2603.17378 • Published • 8 •
1
AI Scientist via Synthetic Task Scaling
Paper • 2603.17216 • Published • 1 •
1
LoST: Level of Semantics Tokenization for 3D Shapes
Paper • 2603.17995 • Published • 14 •
1