Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment

• URL: http://arxiv.org/abs/2607.13429v1
• Date: Wed, 15 Jul 2026 04:13:54 GMT
• Title: Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment
• Abstract summary: Anchor-Align improves vision-language-action policies on robot demonstrations.<n>It distills layer-wise representations from a frozen VLM copy to prevent this drift.<n>It converts each action target into a discrete motion-direction label and jointly trains language and action prediction.
• Score: 42.503300854478795
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Finetuning a pretrained vision-language model (VLM) on robot demonstrations via behavior cloning (BC) has become the standard recipe for vision-language-action (VLA) policies. However, BC finetuning progressively overwrites the pretrained representations that support visual and semantic generalization. Co-training on web image-text data, a common remedy, does not prevent this; it applies language and action losses to separate observations, leaving VLAs with language-action misalignment that standard manipulation benchmarks do not expose. We propose Anchor-Align, which augments BC with two objectives: Vision-Language Anchoring distills layer-wise representations from a frozen VLM copy to prevent this drift, while Language-Action Alignment converts each action target into a discrete motion-direction label and jointly trains language and action prediction on the same robot observation. On a physical xArm7 robot, across two widely used VLA architectures, Anchor-Align improves real-robot success on both (28% to 54% and 37% to 60%). At scale in simulation, we demonstrate consistent improvements on OOD perturbations, perceptual robustness, and long-horizon control across LIBERO-PRO, LIBERO-Plus, and CALVIN, respectively, suggesting that preserving pretrained representations and effective action learning are not fundamentally at odds. Project page: anchoralignvla.github.io

Related papers

• CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding [16.03159066719039]
  CLAP (Causal Language-Action Prediction) prepends each numeric action sequence with a natural-language action description.<n>We will release CLAP at 0.8B, 2B, and 4B as an open-weight, multi-scale compact VLA family from a single VLM lineage.
  arXiv  Detail & Related papers  (2026-07-09T22:34:11Z)
• VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment [17.204682551730205]
  We present VLAFlow, a unified flow-matching framework for comparison of VLA training objectives.<n>We evaluate four paradigms under the same pi0-style architecture, shared VLM backbone, action expert, and 14-dimensional action space.
  arXiv  Detail & Related papers  (2026-07-02T01:38:16Z)
• Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data [93.7685703383343]
  Vision-language models (VLMs) are powerful general-purpose reasoners, yet converting them into robot control policies is surprisingly difficult.<n>We argue that this gap can be bridged gradually with the right intermediate data.<n>We show that mixing task-relevant out-of-distribution ETC data with a small amount of action data enables the model to generalize to novel visual-language conditions.
  arXiv  Detail & Related papers  (2026-06-07T08:57:51Z)
• QuoVLA: Quotient Space for Vision-Language-Action Models [51.02329790939691]
  Vision-Language-Action (VLA) models commonly adapt pretrained VLM latents to robot control by mapping visual observations and language instructions to continuous actions.<n>Our textitQuotient Theory for VLA shows that pretrained VLM latents are not action-insufficient but action-sufficient.<n>We propose QuoVLA, a quotient-space framework for VLA that compresses pretrained VLM latents into action-sufficient representations.
  arXiv  Detail & Related papers  (2026-05-24T06:28:53Z)
• RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models [58.83401587988675]
  RoboAlign trains vision-language-action models (VLAs) to translate multimodal understanding into low-level actions.<n>Our key idea is to sample action tokens via zero-shot natural language reasoning and refine this reasoning using reinforcement learning (RL) to improve action accuracy.<n>RoboAlign achieves performance improvements of 17.5%, 18.9%, and 106.6% over SFT baselines on LIBERO, CALVIN, and real-world environments, respectively.
  arXiv  Detail & Related papers  (2026-03-22T17:57:55Z)
• Universal Pose Pretraining for Generalizable Vision-Language-Action Policies [83.39008378156647]
  Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency.<n>We propose Pose-VLA, a decoupled paradigm that separates VLA training into a pre-training phase for extracting universal 3D spatial priors.<n>Our framework follows a two-stage pre-training pipeline, establishing fundamental spatial grounding via poses followed by motion alignment.
  arXiv  Detail & Related papers  (2026-02-23T11:00:08Z)
• Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization [65.37179698521766]
  Vision-Language-Action (VLA) models show strong promise for generalist robot control.<n>It remains unclear whether -- and under what conditions -- the standard "scale data" recipe translates to robotics.<n>We present a systematic, controlled study of VLA scaling that revisits core training choices for pretraining across diverse robots.
  arXiv  Detail & Related papers  (2026-02-10T12:25:43Z)
• CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos [73.51386721543135]
  We propose Contrastive Latent Action Pretraining (CLAP), a framework that aligns the visual latent space from videos with a proprioceptive latent space from robot trajectories.<n>CLAP maps video transitions onto a quantized, physically executable codebook.<n>We introduce a dual-formulation VLA framework offering both CLAP-NTP, an autoregressive model excelling at instruction following and object generalization, and CLAP-RF, a Rectified Flow-based policy designed for high-frequency, precise manipulation.
  arXiv  Detail & Related papers  (2026-01-07T16:26:33Z)
• Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification [17.948161564138033]
  Reasoning Vision Language Action (VLA) models improve robotic instruction-following by generating step-by-step textual plans before low-level actions.<n>But even with a correct textual plan, the generated actions can still miss the intended outcomes in the plan, especially in out-of-distribution scenarios.<n>We formalize this phenomenon as a lack of embodied CoT faithfulness, and introduce a training-free, runtime policy steering method for reasoning-action alignment.
  arXiv  Detail & Related papers  (2025-10-18T00:38:45Z)
• Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models [25.45513133247862]
  Vision-Language-Action (VLA) models have achieved revolutionary progress in robot learning.<n>Despite this progress, their adversarial robustness remains underexplored.<n>We propose both adversarial patch attack and corresponding defense strategies for VLA models.
  arXiv  Detail & Related papers  (2025-10-15T07:42:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.