Perplexity Trains Its Computer Agent on Real Mistakes With Hint-Guided Self-Distillation
4 min
PoEM: Predicting RL Outcomes from Existing Policies
Rufus-Air: An Open LLM Post-Training Recipe
Debating RSI, the US-China Gap, and Jaggedness with JS Denain of Epoch AI
15 min
ACLArena: Agent Continue Learning in Multi-stage Post-training
OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher
A Zeroth-Order Paradigm for LLM Preference Alignment
1
Inoculation Midtraining with Learned Neologisms
Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training
Register Tokens for Bounded-State Reasoning in Diffusion Language Models
1
Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition
Expert-Space Exploration in MoE Reinforcement Learning
MInTRL: Off-policy Intervention can boost On-policy RL
RetroThinker: Enabling Retrospective Thinking in Speech LLMs
1
ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation
1
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation
ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation
Miles v0.1: Production-Level Post-Training
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models
Revisiting Complete Reasoning Traces for Post-Training
Multi-Grid Post-Training for Long-Form Multi-Shot Video Generation
TokenRhythm/NeoHorse-1-4B — new model trending #30 on Hugging Face
15 min1
Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work
Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation
