…and recovers by treating a VLA / WAM as an interruptible tool it steers mid-rollout alongside vision models and action primitives. To evaluate these long-horizon capabilities, we introduce RoboVoLo, a high…
…staged reinforcement learning and dense supervision, using sparse rewards for teacher model discovery and dense rewards for student model compression. AI-generated summary In settings where labeled verifiable training data is the…
…Yanzuo Lu , , Abstract RAVEN enables real-time video generation through causal autoregressive extrapolation with improved training alignment, while CM-GRPO enhances performance via reinforcement learning applied to consistency model sampling. AI-generated…
…AI-generated summary Large reasoning models , such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed…
…and lateral heading directions and supervise the model to recover the original expert trajectory. We then fine-tune the full decision--draft--reflect rollout with reinforcement learning (RL), assigning terminal driving reward…
…AI-generated summary Reinforcement learning for agentic large language models (LLMs) typically relies on a sparse, trajectory-level outcome reward , making it difficult to evaluate the contribution of individual tool-calls within…
…Instead of materializing each policy as a merged full checkpoint , MinT keeps the base model resident and moves exported LoRA adapter revisions through rollout, update, export, evaluation, serving , and rollback, hiding distributed…
…Zihao Han , Tiangang Zhang , , Abstract Adaptive Teacher Exposure for Self-Distillation (ATESD) improves large language model reasoning by dynamically adjusting teacher exposure during training through a learnable policy controller. AI-generated summary…
…Yihong Liu , , , Abstract COPSD transfers high-resource language model reasoning behavior to low-resource languages using self-distillation with crosslingual context, improving mathematical reasoning performance. AI-generated summary Large language models (LLMs…
…AI-generated summary Coding harnesses such as Claude Code and OpenHands wrap foundation models with tools, memory, and planning, but no equivalent exists for embodied agents ' long-horizon partial-observability decision-making…