LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference
Paper • 2605.01058 • Published •
1
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 5 hours ago
LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference commentedon a paper about 5 hours ago
TIDE: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference new activity about 12 hours ago
nahidhasan/MedS-Ins-QA-Conversations:Librarian Bot: Add language metadata for datasetOrganizations
commented 2
papers about 5 hours ago
Librarian Bot: Add language metadata for dataset
#2 opened about 12 hours ago
by librarian-bot
commented 17
papers about 17 hours ago
Video Generation with Predictive Latents
Paper • 2605.02134 • Published • 11 •
3
The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail
Paper • 2605.03073 • Published • 2 •
2
X2SAM: Any Segmentation in Images and Videos
Paper • 2605.00891 • Published • 19 •
3
HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness
Paper • 2605.02396 • Published • 16 •
3
SymptomAI: Towards a Conversational AI Agent for Everyday Symptom Assessment
Paper • 2605.04012 • Published • 8 •
1
OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
Paper • 2605.04036 • Published • 55 •
2
A Benchmark for Interactive World Models with a Unified Action Generation Framework
Paper • 2605.03941 • Published • 2 •
2
StateSMix: Online Lossless Compression via Mamba State Space Models and Sparse N-gram Context Mixing
Paper • 2605.02904 • Published • 5 •
2
Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
Paper • 2605.02801 • Published • 5 •
2
Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO
Paper • 2604.27488 • Published • 4 •
2
TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis
Paper • 2605.01717 • Published • 4 •
2
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
Paper • 2604.28123 • Published • 40 •
3
SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion
Paper • 2605.01466 • Published • 4 •
2
ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue
Paper • 2605.01371 • Published • 4 •
2
Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
Paper • 2605.03596 • Published • 5 •
1
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
Paper • 2605.02913 • Published • 4 •
2
PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination
Paper • 2605.03571 • Published • 5 •
2