Reducing the representation within retained tokens provides an effective complement to token pruning for aggressive VLA compression, and can be applied to language values, allowing visual and language representations to be compressed without removing additional tokens.
Abstract
Vision-Language-Action (VLA) models process long multimodal token sequences, making inference expensive in both memory and computation. Existing efficiency methods mainly reduce visual tokens, but aggressive token pruning becomes fragile because removing a token discards its entire representation. Sub-token compression provides a complementary alternative by retaining more tokens while reducing their value width. However, directly applying sub-token compression to VLA policies is less effective because information important for perception, language understanding, and control is distributed differently across the multimodal representation. We introduce Role-Conditioned Sub-Token Routing (RoleSub), which learns how to compress the value representations of retained tokens. After visual token reduction, RoleSub partitions each retained value representation into groups in an orthogonal space and uses a lightweight router to determine which groups should be preserved. The routing decision is conditioned on the token representation, a learned latent role representation, and language context. The same mechanism can also be applied to language values, allowing visual and language representations to be compressed without removing additional tokens. We evaluate RoleSub on OpenVLA-OFT-7B across the four LIBERO suites. At matched visual-KV budgets, RoleSub outperforms a trained token-only control in 33 of 36 settings, with the largest gains under aggressive compression. Combining visual and language compression reduces total KV to 9.2--11.3% of the original while retaining strong control performance on most tasks. These results show that reducing the representation within retained tokens provides an effective complement to token pruning for aggressive VLA compression.
This work introduces RUTA, a principled Rate-Utility Token Allocation method that performs pre-LLM reduction by jointly learning which tokens to retain and how many to allocate to each image-query pair, and is optimized with a penalized rate-utility objective that balances downstream task loss against expected token usage.
Jiangyu Zou, Xiaoyu Xu, Zhihua Wang et al.· 0 citations
Token compression has become a key technique for reducing the inference cost of large foundation models, with approaches such as token pruning and KV-cache reuse widely adopted in vision-language models and recently explored for embodied agents. In embodied agents, tokens not only support perception and semantic understanding but also directly affect latency-sensitive closed-loop robot action prediction. Existing schemes typically guide compression using redundancy or importance cues, such as visual similarity, attention scores, and saliency. However, these cues only indirectly measure the key factor for safe compression: how much a token can change before causing an unacceptable deviation in downstream actions. This receiver-dependent tolerance is closely related to the principle of just noticeable difference (JND). Classical JND characterizes signal tolerance in the human visual system, while machine-oriented JND extends this concept to downstream machine responses. Building on this progression, we introduce Action-JND, which extends JND modeling to embodied perception by defining noticeability through the language-conditioned action response of a vision-language-action (VLA) policy in closed-loop control. A token change is considered admissible only when the induced action deviation remains within a tolerated margin. To realize this concept, we develop a lightweight token-wise JND estimator in deep visual-feature space to predict the maximum tolerable perturbation while preserving policy responses. The resulting action-tolerance score serves as a plug-and-play criterion for VLA compression paradigms, including stale-KV reuse and token pruning, prioritizing action-tolerant tokens for compression. Experiments on the LIBERO benchmark with OpenVLA and OpenVLA-OFT demonstrate that Action-JND consistently improves compression reliability, especially under aggressive compression ratios.
Zhuo-Yuan Li, Rui Zhao, Jin Wang et al.· 0 citations
This work proposes Greedy Orthogonal Token Selection (GOTS), a training-free and query-agnostic method that achieves higher average performance retention than the strongest evaluated baselines, and a controlled OCRBench study shows that it reduces model-side time-to-first-token after accounting for selection overhead.
Jun Ling, Tao Huang, Junzhuo Liu et al.· arXiv.org· 0 citations
SmartVL is proposed, a unified adaptive inference framework that jointly controls vision token number and model compute capability in response to varying input contents and compute budgets and consistently outperforms prior adaptive methods and achieves superior accuracy-efficiency Pareto frontiers.
Pengcheng Wang, Zhiquan Wang, Jayoung Lee et al.· arXiv.org· 0 citations
Visual prefixes account for a major portion of the per-layer computation in multimodal large language models (MLLMs), making visual-token pruning a direct approach to accelerating inference. Existing top-K methods typically evaluate tokens independently and apply a uniform budget to all inputs, overlooking both selection-dependent interactions and variations in visual complexity across samples. In contrast, we propose StepPrune, which formulates visual-token pruning as an adaptive sequential decision process. Conditioned on previously selected tokens and textual context, StepPrune progressively constructs the retained subset and automatically determines its size through a learned STOP action. During training, a variance-preserving noise gate provides a differentiable surrogate for the discrete selection process, whereas during inference, unselected tokens are physically removed before language-model prefill. A grouped selection mechanism further extends StepPrune to high-resolution inputs. Experiments across LLaVA-1.5, LLaVA-NeXT, Qwen2.5-VL, and InternVL3 show that StepPrune achieves the best average normalized performance retention across all evaluated pruning rates on LLaVA-1.5, Qwen2.5-VL, and InternVL3, while remaining competitive on the substantially longer AnyRes prefixes of LLaVA-NeXT. On LLaVA-1.5, StepPrune retains 94.6% of the full-prefix normalized performance while pruning 88.9% of the visual tokens. At a mean retained count of 64, StepPrune reduces prefill latency from 59.95 ms to 40.05 ms, corresponding to a 1.50x prefill speed-up.
Han-Sen Zhang, Lan He, Min Yao et al.· 0 citations
Trend-aware Pruning is proposed, a novel framework that elevates pruning from a local snapshot decision to a temporal trajectory modeling problem, and enables a dynamic rectification mechanism that selectively reactivates "late-blooming" tokens, those initially undervalued but exhibiting rising semantic importance, thereby preventing the loss of critical visual cues.
Jie Ma, Zhike Qiu, Jie Gao et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
