Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use
Paper • 2610.40738 • Published • 35 •
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 3 hours ago
Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use commentedon a paper about 3 hours ago
CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems commentedon a paper about 3 hours ago
Latent Reasoning in Continuous Space for Unified Multimodal ModelsOrganizations
commented 9
papers about 3 hours ago
CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems
Paper • 2610.34722 • Published • 21 •
2
Latent Reasoning in Continuous Space for Unified Multimodal Models
Paper • 2610.42149 • Published • 26 •
2
Wizard: Manipulate Any World in Real Time via Agentic Control
Paper • 2610.40339 • Published • 25 •
2
SketchDirector: Complex Scene Sketching via Agentic Layout Reasoning and Detail Refinement
Paper • 2610.41260 • Published • 1 •
2
TernScope: Model-Hardware Co-Design for Efficient Ternary Endoscopic Segmentation
Paper • 2610.29617 • Published • 3 •
2
Follow the Gradient: Tracing Safety Degradation Back to Training Data
Paper • 2610.37481 • Published • 27 •
2
SOMA: A Benchmark for Fine-Grained Egocentric Behavior and Body-Motion Understanding
Paper • 2610.36384 • Published • 4 •
2
Learning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling
Paper • 2610.37393 • Published • 7 •
2
updated a
dataset about 3 hours ago
commented 10
papers about 3 hours ago
rTaste: Do Research Agents Have Taste? Evaluating Early Stage Research Judgment
Paper • 2610.40488 • Published • 2 •
2
CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents
Paper • 2610.40799 • Published • 20 •
2
WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search
Paper • 2610.16927 • Published • 27 •
2
CausalWAM: Learning the Causes of Actions in World Action Models
Paper • 2610.42096 • Published • 4 •
2
SciGame: Let Agents Play the Scientific Discovery Games in the Real and Counterfactual World
Paper • 2610.37919 • Published • 4 •
2
Think Twice: The Metis-1.6 Technical Report
Paper • 2610.37903 • Published • 4 •
2
REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control
Paper • 2610.42053 • Published • 115 •
3
OSWAM: An Effective World Action Model with One-Step Action Generation
Paper • 2610.35850 • Published • 25 •
2
FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation
Paper • 2610.36545 • Published • 113 •
3
Probing Spatial State Representations in Visual Foundation Models
Paper • 2610.40636 • Published • 17 •
2