Pith. sign in

REVIEW 23 cited by

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2508.10333 v1 pith:FNUUT2P3 submitted 2025-08-14 cs.RO cs.CV

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver

classification cs.RO cs.CV
keywords visualmodelattentiongroundingreconvlatargetallocategeneralization
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention to target regions. Instead, visual attention is always dispersed. To guide the visual attention grounding on the correct target, we propose ReconVLA, a reconstructive VLA model with an implicit grounding paradigm. Conditioned on the model's visual outputs, a diffusion transformer aims to reconstruct the gaze region of the image, which corresponds to the target manipulated objects. This process prompts the VLA model to learn fine-grained representations and accurately allocate visual attention, thus effectively leveraging task-specific visual information and conducting precise manipulation. Moreover, we curate a large-scale pretraining dataset comprising over 100k trajectories and 2 million data samples from open-source robotic datasets, further boosting the model's generalization in visual reconstruction. Extensive experiments in simulation and the real world demonstrate the superiority of our implicit grounding method, showcasing its capabilities of precise manipulation and generalization. Our project page is https://zionchow.github.io/ReconVLA/.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 23 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Premover: Fast Vision-Language-Action Control by Acting Before Instructions Are Complete

    cs.RO 2026-05 unverdicted novelty 7.0

    Premover enables VLA policies to act on partial instructions by precomputing focus maps from intermediate backbone layers, reducing wall-clock time 13.6 percent on LIBERO while preserving 95 percent success rate.

  2. CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models

    cs.CV 2026-05 unverdicted novelty 7.0

    Capability vectors extracted from parameter differences between standard and auxiliary-finetuned VLA models can be merged into pretrained weights to match auxiliary-training performance while reducing computational ov...

  3. Mask World Model: Predicting What Matters for Robust Robot Policy Learning

    cs.RO 2026-04 unverdicted novelty 7.0

    Mask World Model predicts semantic mask dynamics with video diffusion and integrates it with a diffusion policy head, outperforming RGB world models on LIBERO and RLBench while showing better real-world generalization...

  4. Towards Generalizable Robotic Manipulation in Dynamic Environments

    cs.CV 2026-03 unverdicted novelty 7.0

    DOMINO dataset and PUMA architecture enable better dynamic robotic manipulation by incorporating motion history, delivering 6.3% higher success rates than prior VLA models.

  5. Towards Generalizable Robotic Manipulation in Dynamic Environments

    cs.CV 2026-03 conditional novelty 6.5

    DOMINO supplies 110K+ dynamic dual-arm trajectories across 35 tasks, and PUMA’s optical-flow history plus object-centric future queries raise dynamic success rate by 6.3 points over strong VLA baselines.

  6. Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment

    cs.RO 2026-07 conditional novelty 6.0

    Preserving pretrained VLM features with layer-wise distillation plus supervising the language head on discretized action directions improves OOD generalization of VLA policies on LIBERO, CALVIN, and a real xArm7.

  7. AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding

    cs.RO 2026-06 unverdicted novelty 6.0

    AffordanceVLA proposes a VLA model with affordance-aware modules (Which2Act, Where2Act, How2Act) in a Mixture-of-Transformer trained in three stages to improve robotic manipulation.

  8. OneVLA: A Unified Framework for Embodied Tasks

    cs.RO 2026-05 unverdicted novelty 6.0

    OneVLA is a unified VLA model using a shared action head and multi-stage progressive training with CoT fine-tuning that reports state-of-the-art results on both navigation and manipulation in simulation and real-world...

  9. NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End Driving

    cs.CV 2026-05 unverdicted novelty 6.0

    NTR adds a self-distillation masked latent reconstruction objective that uses only scene tokens to reconstruct masked patch features, improving visual representation quality and planning performance in end-to-end auto...

  10. $M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills

    cs.RO 2026-04 unverdicted novelty 6.0

    M²-VLA shows that generalized VLMs can serve as direct backbones for robotic manipulation by selectively extracting task-critical features via Mixture of Layers and adding Meta Skill Modules for efficient trajectory learning.

  11. $M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills

    cs.RO 2026-04 conditional novelty 6.0

    Freezing a VLM backbone and routing its layers through Mixture-of-Layers plus a Meta-Skill memory yields higher success and stronger zero-shot generalization than fine-tuned VLAs on LIBERO and real robots.

  12. CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors

    cs.RO 2026-04 conditional novelty 6.0

    Sparse action-aligned spatial anchors impose an explicit tolerance corridor that improves flow-matching VLA success rates by 4–12 points on LIBERO and LIBERO-Plus.

  13. CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors

    cs.RO 2026-04 unverdicted novelty 6.0

    CorridorVLA improves VLA models by using predicted sparse anchors to impose explicit spatial corridors on action trajectories, yielding 3.4-12.4% success rate gains on LIBERO-Plus with GR00T-Corr reaching 83.21%.

  14. Grounded World Model for Semantically Generalizable Planning

    cs.RO 2026-04 conditional novelty 6.0

    A vision-language-aligned world model turns visuomotor MPC into a language-following planner that reaches 87% success on 288 unseen semantic tasks where standard VLAs drop to 22%.

  15. Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation

    cs.RO 2026-02 unverdicted novelty 6.0

    OptimusVLA augments hierarchical VLA models with Global Prior Memory for shorter generative paths and Local Consistency Memory for temporal coherence, yielding higher success rates and 2.9x faster inference on simulat...

  16. TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective Bridging

    cs.RO 2026-07 conditional novelty 5.0

    A 0.5B VLA with bridge-conditioned discrete diffusion and 2D temporal–spatial action masking reaches 95.7% LIBERO success and 4.19 CALVIN average length.

  17. GEM: Generative Supervision Helps Embodied Intelligence

    cs.CV 2026-05 unverdicted novelty 5.0

    GEM adds generative depth supervision to VLM pre-training and reports improved results on embodied benchmarks plus real-world robot execution.

  18. From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model

    cs.CV 2026-05 unverdicted novelty 5.0

    BehaviorVLA introduces a symmetric encoder-decoder architecture with causal Mamba and phase conditioning to learn unified long-horizon behavioral representations for improved generalization in VLA models.

  19. HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System

    cs.CV 2026-04 unverdicted novelty 5.0

    HiVLA decouples VLM-based semantic planning from DiT-based motor control via structured plans and cascaded cross-attention to outperform end-to-end VLA baselines in long-horizon and fine-grained manipulation.

  20. HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System

    cs.CV 2026-04 unverdicted novelty 5.0

    HiVLA decouples VLM-based semantic planning with visual grounding from a cascaded cross-attention DiT action expert, outperforming end-to-end VLAs on long-horizon and fine-grained manipulation.

  21. AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention

    cs.LG 2025-11 unverdicted novelty 5.0

    AVA-VLA reformulates VLA learning as a POMDP using recurrent states and active visual attention to achieve state-of-the-art results on LIBERO, CALVIN, and real dual-arm tasks.

  22. QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models

    cs.CV 2025-10 conditional novelty 5.0

    Adding an auxiliary quantized-depth-token prediction task to a VLA policy improves manipulation success rates on LIBERO, Simpler, and real-robot pick-and-place tasks versus the open-pi-zero baseline.

  23. From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model

    cs.CV 2026-05 unverdicted novelty 4.0

    BehaviorVLA learns long-horizon behavioral representations via causal Mamba encoder and phase-conditioned decoder, reporting SOTA results of 58% on RoboTwin 2.0, 98% on LIBERO, 4.36 on CALVIN, and matching OpenVLA-OFT...