SOD: Step-wise On-policy Distillation for Small Language Model Agents
Paper • 2605.07725 • Published • 26
Emiko Takahashi
lazy-45
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
SOD: Step-wise On-policy Distillation for Small Language Model Agents upvoted a paper about 2 months ago
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers liked a model about 2 months ago
google-bert/bert-base-uncasedOrganizations
None yet
upvoted 6
papers about 2 months ago
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers
Paper • 2605.06169 • Published • 238
Training Large Language Models to Predict Clinical Events
Paper • 2605.12817 • Published • 17
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
Paper • 2605.21467 • Published • 207
OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation
Paper • 2605.12038 • Published • 4
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Paper • 2605.11609 • Published • 196
upvoted 4
papers 2 months ago
Audio-Visual Intelligence in Large Foundation Models
Paper • 2605.04045 • Published • 35
UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
Paper • 2605.06597 • Published • 16
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
Paper • 2605.06130 • Published • 116
OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
Paper • 2605.05185 • Published • 106
upvoted 8
papers 3 months ago
Scaling Test-Time Compute for Agentic Coding
Paper • 2604.16529 • Published • 12
WildDet3D: Scaling Promptable 3D Detection in the Wild
Paper • 2604.08626 • Published • 248
Adam's Law: Textual Frequency Law on Large Language Models
Paper • 2604.02176 • Published • 509
ClawBench: Can AI Agents Complete Everyday Online Tasks?
Paper • 2604.08523 • Published • 265
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Paper • 2604.02721 • Published • 639
Towards a Medical AI Scientist
Paper • 2603.28589 • Published • 92
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence
Paper • 2603.28032 • Published • 344
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
Paper • 2603.19835 • Published • 353
upvoted 2
papers 4 months ago