Weak-to-Strong Generalization via Direct On-Policy Distillation Paper • 2607.05394 • Published 10 days ago • 125
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation Paper • 2607.05147 • Published 12 days ago • 36
Dockerless: Environment-Free Program Verifier for Coding Agents Paper • 2606.28436 • Published 22 days ago • 110
Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs Paper • 2602.02338 • Published Feb 2 • 43
IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse Paper • 2603.12201 • Published Mar 12 • 62
How LoRA Remembers? A Parametric Memory Law for LLM Finetuning Paper • 2605.30260 • Published May 28 • 44
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published May 12 • 196