FACET; EnvHarness; ForgeWM

Key Findings

• •

  Each task couples an instruction, an initialized environment, a reference solution, and an executable verifier; if these artifacts are generated from

• •

  Meanwhile, multi-stage synthesis can discard the goals, dependencies, state transitions, and procedural constraints encoded in the original sources.

• •

  We present FACET (Fine-grained Agentic Construction of Executable Tasks), a framework that addresses both information preservation and cross-artifact

Key Findings

• •

  While recent environment generation methods attempt to address this, they require domain-specific pipelines, rely on expensive or unreliable verifiers

• •

  To alleviate the engineering burden of rebuilding environments from scratch, we propose Environment Harness (EnvHarness), a programmable layer of plug

• •

  Operating through standard interfaces, EnvHarness applies across diverse domains while ensuring every reshaped environment retains its original verifi

Key Findings

• •

  Although causal distillation enables one- or few-step video synthesis, extending it to interactive world models remains challenging, as discrete keybo

• •

  We introduce ForgeWM, a progressive framework that transforms a bidirectional action-conditioned video generator into efficient few-step world models

• •

  The resulting budget-specialized students operate at steady-state denoising budgets of 1, 2, and 4 steps.

Key Findings

• •

  Beyond retaining each identity, the model must bind every reference to a distinct person and location, while training-time identity losses must establ

• •

  We introduce WithEveryone, a unified framework for generating group images up to ten reference identities.

• •

  WithEveryone injects each selected identity as an addressed token, predicts a structured identity--layout plan, and renders the plan as a visual condi

Key Findings

• •

  State of the art robotic manipulation policies are based on behaviour cloning of large vision-language-action (VLA) models with billions of parameters

• •

  While this simple approach has enabled significant advances for robotic manipulation, finetuning of VLA policies for learning new tasks still remains

• •

  In particular, collecting teleoperation datasets requires hundreds of hours of expensive human labour and the alternative, reinforcement learning (RL)

Key Findings

• •

  Compliance failures arise from either forbidden actions, such as granting an ineligible change, or omitted procedural requirements, such as identifica

• •

  Runtime safeguards can intervene on risky actions, but action-local checks do not guide an agent through a multi-step procedure.

• •

  Workflow-following systems support prescribed process execution, but primarily target workflow completion rather than safeguarding agent behavior.