…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach. AI…
…AI-generated summary On-policy distillation (OPD) is a powerful paradigm for model alignment , yet its reliance on teacher logits restricts its application to white-box scenarios. We contend that structured semantic…
…existing reinforcement learning approaches in both training efficiency and final performance. AI-generated summary Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing…
…reduced latency and improved quality compared to existing chunk-wise approaches. AI-generated summary Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation methods…
…when all sampled rollouts for a query fail, the relative advantage collapses to zero. Consequently, the model loses effective training signals for these questions, wasting the training data and computational budget. While…
…AI-generated summary Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objective in a single prompt, increasingly capable…
…We distill 107K trajectories from MiniMax-M2.5 and Qwen3.5-397B, introduce credit-assignment SFT to learn from productive segments of unresolved trajectories, and apply Balanced Adaptive Rollout for RL. Starting…
…This approach suffers from a sample-level mismatch because most rollouts are specialist samples, highly informative for certain reward dimensions but irrelevant for others; consequently, weighted summation dilutes their supervision. To address…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.