---
title: 'LIBERO-CF: Coarse-to-Fine Action Generation'
url: https://www.emergentmind.com/topics/libero-cf
type: topic
---

# LIBERO-CF: Coarse-to-Fine Action Generation

LIBERO-CF is an ambiguous term in the recent Vision-Language-Action literature rather than a uniformly standardized benchmark name. In the clearest documented usage among currently cited arXiv sources, it denotes the coarse-to-fine setting introduced by CF-VLA on the LIBERO manipulation benchmark, where action generation is restructured into a coarse initialization step followed by a single-step local refinement [2604.24622]. At the same time, later LIBERO-family papers use the label differently or question its benchmark status: one source states that “LIBERO-CF (Collision-Free) is not an established official LIBERO benchmark,” while another describes “LIBERO-CF” as “Counterfactual Failures, Fang et al. 2026” in contrast to language-only perturbation studies [2606.23686; 2603.28301]. This suggests that, in current usage, LIBERO-CF is best understood through its surrounding context: most concretely as the LIBERO evaluation setting for CF-VLA’s coarse-to-fine action generation, and more loosely as a non-canonical label invoked by later benchmark papers.

## 1. Terminological status in the LIBERO literature

The term’s ambiguity is itself a substantive feature of the literature. CF-VLA does not introduce a benchmark titled “LIBERO-CF”; instead, it reports results on the existing LIBERO benchmark and describes a “coarse-to-fine” action generation mechanism that establishes a strong low-NFE operating point on LIBERO [2604.24622]. In that sense, “LIBERO-CF” functions as a convenient shorthand for LIBERO evaluated under coarse-to-fine action generation rather than as the name of a formally separate benchmark.

Later papers make the ambiguity explicit. LIBERO-Safety states that earlier LIBERO variants such as “LIBERO (and variants like LIBERO-Plus/PRO/X/CF)” primarily focus on task completion, generalization, and robustness rather than explicit safety, but it also adds that “LIBERO-CF (Collision-Free) is not an established official LIBERO benchmark per the cited paper” and may instead refer to collision-free data subsets in prior works [2606.23686]. LIBERO-Para, by contrast, places “LIBERO-CF” in a different conceptual slot, describing it as “Counterfactual Failures, Fang et al. 2026,” complementary to language-only paraphrase perturbations [2603.28301]. These usages do not define a single canonical artifact.

## 2. Substrate benchmark: LIBERO

Any account of LIBERO-CF must begin with LIBERO itself. LIBERO is a benchmark for lifelong learning in robot manipulation, or Lifelong Learning in Decision Making, designed to study transfer of both declarative knowledge and procedural knowledge [2306.03310]. It introduces an extendible procedural generation pipeline grounded in language templates, PDDL-based scene descriptions, predicate-based goals, and robosuite as the underlying simulator.

For benchmarking, LIBERO provides four task suites, 130 tasks in total: LIBERO-Spatial, LIBERO-Object, LIBERO-Goal, and LIBERO-100, with LIBERO-100 further split into LIBERO-90 for pretraining and LIBERO-Long for evaluation [2306.03310]. The benchmark also provides 50 high-quality, human-teleoperated demonstrations for each of the 130 tasks, enabling imitation learning via behavioral cloning. In CF-VLA’s LIBERO evaluation, training is conducted on replay-filtered LIBERO trajectories from four suites—Spatial, Object, Goal, and Long—using demonstrations with successful outcomes [2604.24622].

This benchmark context matters because the coarse-to-fine contribution is not a new scene generator or a new taxonomy of perturbations. Rather, it is an action-generation mechanism evaluated within LIBERO’s established manipulation suites, where the primary metric is task success rate and the experimental emphasis is the efficiency–performance trade-off under low numbers of function evaluations [2604.24622].

## 3. Coarse-to-fine action generation in CF-VLA

CF-VLA is a flow-based Vision-Language-Action policy that addresses the inefficiency of multi-step inference from uninformative Gaussian noise by changing the role of the starting point in generative action modeling [2604.24622]. Its backbone is a standard Vision-Language-Model, such as PaliGemma, which receives visual observations, language instructions, and proprioceptive state as input. The architectural novelty lies in the action expert, which is decomposed into a coarse stage and a fine stage.

The coarse stage predicts a distribution over endpoint velocity and transforms Gaussian noise into an action-prior-guided initialization close to the action manifold. Concretely, the process begins by sampling Gaussian noise $\epsilon_1 \sim \mathcal{N}(0, I)$, predicting a conditional posterior over endpoint velocity $q_\theta(u \mid o, \epsilon_1)$, and transforming the noise toward an AP-guided initialization via
$$
\tilde{\epsilon} = \epsilon_1 - \hat{u}, \quad \hat{u} \sim q_\theta(u \mid o, \epsilon_1).
$$
The fine stage then takes $\tilde{\epsilon}$ and applies a local correction in a single step to recover the final action [2604.24622].

The paper contrasts this with standard flow-matching interpolation,
$$
x_t = t\epsilon + (1-t)a;\qquad u_t = \epsilon - a,
$$
where iterative denoising or refinement is typically required to recover action structure from noise [2604.24622]. The central claim is not merely that fewer iterations are used, but that a structured initialization can make low-NFE inference viable.

## 4. Training procedure and objective

CF-VLA uses a stepwise training strategy intended to stabilize the coupling between coarse initialization and fine refinement [2604.24622]. Training alternates between a stabilization phase, in which proxy inputs support reliable coarse output learning for the refinement branch, and a subsequent joint optimization phase in which coarse and fine stages are coupled.

The joint loss is given as
$$
\mathcal{L}(\theta) = \mathcal{L}_{\text{fine}}(\theta) + \lambda\,\mathcal{L}_{\text{coarse}}(\theta),
$$
where $\mathcal{L}_{\text{coarse}}$ is the KL divergence between predicted and target endpoint-velocity distributions, and $\mathcal{L}_{\text{fine}}$ is the MSE between predicted and true local corrections [2604.24622].

On LIBERO, the model is trained for 60,000 steps using 8×A100 GPUs, batch size 16, and learning rate $5 \times 10^{-5}$, with the same recipe applied to compared baselines including PI\_0.5 and MIP variants [2604.24622]. Evaluation is performed with 10 simulation rollouts per task, measuring success rate per LIBERO suite and then averaging. The main reported metrics are success rate, action sampling latency excluding visual-language encoding and KV-cache, and Number of Function Evaluations.

## 5. Reported LIBERO results

On LIBERO simulation, CF-VLA reports 96.5% average success at NFE = 2, with suite-wise scores of 98.0 on Spatial, 99.2 on Object, 96.6 on Goal, and 92.0 on Long [2604.24622]. Under the same evaluation, MIP $(\pi_0)$ at NFE = 2 reports 92.7 average success; MIP $(\pi_{0.5})$ at NFE = 2 reports 93.6; $\pi_{0.5}^*$ at NFE = 2 reports 94.8; and $\pi_{0.5}^*$ at NFE = 10 reports 95.7 [2604.24622].

The paper emphasizes that CF-VLA at NFE = 2 matches or beats the NFE = 10 $\pi_{0.5}$ baseline on several metrics, while reducing action sampling latency from 29.17 ms to 7.81 ms, a 75.4% reduction [2604.24622]. It also reports especially strong gains on the Object and Long suites, described as tasks sensitive to long-term consistency and structured generation. Ablation studies are summarized as showing that removing phase-II coupling or the fine refinement step significantly degrades performance, indicating that both stages are necessary for the reported gains.

The same work reports an average real-robot success rate of 83.0%, outperforming MIP by 19.5 points and $\pi_{0.5}$ by 4.0 points [2604.24622]. The cited challenging tasks include Wipe Table, Pour Water, and Fold Towel into Thirds, which the paper characterizes as requiring long-horizon consistency and precise physical control.

## 6. Significance and relation to adjacent LIBERO variants

Within the CF-VLA paper, the significance of the LIBERO results is framed as an efficiency–performance frontier: the key design move is restructuring the starting point of action generation through AP-guided initialization rather than relying on more denoising or refinement steps [2604.24622]. The method is described as plug-and-play for arbitrary flow-based VLA policies and different VLM backbones with minimal modification. This suggests that the most consequential aspect of “LIBERO-CF” in this sense is methodological rather than taxonomic: it is a way of operating on LIBERO that tests whether structured initialization can displace iterative inference.

That emphasis differs from later LIBERO-family extensions, each of which isolates a distinct failure mode of VLA evaluation. LIBERO-X introduces a five-level hierarchical evaluation protocol for spatial generalization, object recognition, and task instruction understanding under cumulative perturbations [2602.06556]. LIBERO-Occ studies scene-induced occlusion and proposes Viewpoint Imagination as a complementary-view generation mechanism [2606.10862]. LIBERO-Para isolates paraphrase robustness and introduces PRIDE as a difficulty-aware metric [2603.28301]. LIBERO-PRO argues that standard LIBERO evaluation inflates performance estimates through memorization and proposes controlled perturbations over manipulated objects, initial states, instructions, and environments [2510.03827]. LIBERO-Safety adds explicit physical and semantic safety constraints, along with a keypose-driven collision-free data generation pipeline [2606.23686].

Against that background, “LIBERO-CF” does not denote a parallel benchmark family with its own formal protocol in the same way as LIBERO-X, LIBERO-Occ, LIBERO-Para, LIBERO-PRO, or LIBERO-Safety. Instead, the evidence in the cited literature indicates a context-dependent label attached either to coarse-to-fine generation on LIBERO, to collision-free subsets, or to counterfactual-failure evaluation, depending on the paper [2604.24622; 2606.23686; 2603.28301]. The most defensible encyclopedic characterization is therefore that LIBERO-CF is a non-canonical term whose most concrete instantiation is CF-VLA’s coarse-to-fine action-generation study on the LIBERO benchmark.

Source: https://www.emergentmind.com/topics/libero-cf