Today's trail

Flint is Recursive’s mixture-of-experts language model for coding agents, with 39.8 billion total parameters and approximately 2.5 billion active per token. It is designed to investigate codebases, fix bugs, implement features, and write tests.

As streaming video generation advances, enabling real-time interaction with generated video is becoming increasingly important. We introduce StreamEval, a unified benchmark for interactive streaming video generation spanning five tasks: avatar dialogue, avatar performance,…

Spark-X2.6-4B retains exactly the same architecture as Spark-X2.5-4B, achieving its capability gains through improved post-training. It delivers substantial improvements in coding, agent, long-context, multilingual, reasoning, etc. These advances enable more capable and…

Uncensored release · Native FP8 (e4m3) + FP4 experts · 40-layer MoE · 1M context · Vision + video · Reasoning tiers · Tools

Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and business applications. These environments create safety risks that are difficult to capture with attacks placed at a single, known…

Hybrid reasoning models such as the Qwen3 series switch between a THINK mode and a NO-THINK mode through a few chat-template tokens. A popular recipe trains such models with reinforcement learning in NO-THINK mode and reports improved reasoning performance. We provide evidence…

Multi-teacher on-policy distillation (MOPD) extends on-policy distillation (OPD) by routing domain-specific data to specialized teachers, integrating their capabilities through dense token-level supervision on student-generated trajectories. However, domain routing only…