…FlashEvolve further improves throughput and token efficiency with speculative stage completion and adaptive workflow control . On GEPA workloads, FlashEvolve improves proposal throughput by 3.5times on local vLLM and 4.9times on…
…scaling strategy discovery by formulating it as controller synthesis over reasoning trajectories and probe signals, achieving improved accuracy-cost tradeoffs with minimal computational overhead. AI-generated summary Test-time scaling (TTS) has…
…At each step, a VLM controller observes the current canvas and accumulated trajectory, reasons about the remaining semantic gaps, and decides whether to invoke image generation/editing, perform validation, or terminate. The…
…AI-generated summary Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation methods have achieved strong results in the chunk-wise 4-step regime…
…Error analysis and applications in model-based reinforcement learning (2026) Generative optimal transport via forward-backward HJB matching (2026) HJ-Gauss: A Monte-Carlo HJ Reachability Scheme (2026) Policy Iteration for Stationary…
…AI-generated summary Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging…
…Experimental results demonstrate that ESC-Skills improves both response-level quality and dialogue-level emotional outcomes while providing more interpretable and controllable support behaviors. We will release the code, prompts, and ESC…
…Yixuan Huang , , , , , , , , , , , Abstract KinDER is a benchmark for physical reasoning in robotics that includes procedurally generated environments and baselines spanning multiple learning paradigms to address kinematic and dynamic constraint challenges. AI-generated…
…EVA-Bench includes 213 scenarios across three enterprise domains, a controlled perturbation suite for accent and noise robustness , and pass@1 , pass@k , pass^k measurements that distinguish peak from reliable capability…
…Jona te Lintelo , , , , Abstract MASCing is a framework that enables flexible reconfiguration of Mixture-of-Experts model behavior for safety objectives through steering matrices and routing gate modifications without requiring retraining. AI…