RealtimeWAM: One-Step Asynchronous World Action Models

RealtimeWAM uses teacher-anchored consistency distillation and cross-expert wavefront pipelining for one-step asynchronous action generation, achieving near-lossless performance with ~25x speedup.

Chengtao Lv, Jinyang Du, Shuyi Feng, Yang Yong and 6 more

Published Oct 5, 2026 · ▲ 12 on Hugging Face · Code ★ 2,880

Arm-wise Compositional Generalization in Dual-Arm Vision-Language-Action Models

ACG-Bench evaluates arm-wise compositional generalization in dual-arm vision-language-action models via AE-VLA, which achieves 21.53% simulated and 39% real-world success versus under 6% baselines.

Zaibin Zhang, Binghao Ran, Yuhan Wu, Zhongbo Zhang and 9 more

Published Oct 5, 2026 · ▲ 4 on Hugging Face

When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models

RACE predicts subskill transition timing to extend VLA action chunks reliably, reducing stop-and-go idle time ~5x on real robots while improving success rates.

Seonghoon Yu, Dongwon Kim, HyungRok Jung, Yoonjae Baek and 3 more

Published Oct 5, 2026 · ▲ 13 on Hugging Face · Code ★ 3

A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies

Feasible-future decoding reranks VLA actions by future safe-completion mass, reducing cumulative safety costs by up to 57.5% without retraining or rollouts.

Tu Nguyen, Matthieu Zimmer, Vu Anh Vu, Ziyi Wang and 3 more

Published Oct 4, 2026 · ▲ 3 on Hugging Face

DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling

DiVeR improves verifier-guided VLA test-time scaling by reweighting learning toward decision-critical states using action representation dispersion, boosting success without extra annotations or overhead.

Seongheon Park, Heecheol Kim, Shulin Tian, Lilika Makabe and 4 more

Published Oct 4, 2026 · ▲ 1 on Hugging Face

PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training

PerturbBot breaks vision-language-action shortcut priors via perturbative training while GroundingFscore diagnoses shortcut reliance, enabling healthier scaling without altering inference.

Mingyu Liu, Chonghao Sima, Tianjian Feng, Hanqing Wang and 3 more

Published Oct 3, 2026 · ▲ 13 on Hugging Face · Code ★ 6

Native Action-Prior Learning from Videos for World Action Models

NAVA-WAM pretrains robot action policies directly from observation-only videos via flow-matching and joint attention, improving control accuracy and label efficiency.

Zhaochong An, Fei Zhang, Menglin Jia, Duncan Frost and 9 more

Published Oct 2, 2026 · 0 citations · ▲ 81 on Hugging Face

Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models

Kinematic MeanFlow decouples MeanFlow's time derivative via a kinematic identity to stabilize one-step robotic action generation, cutting latency by up to 74% while outperforming multi-step flow matching.

Jiawei Fan, Sifeng Wang, Yuqing Hou, Anbang Yao

Published Oct 1, 2026 · 0 citations · Code

World Action Modeling with Progressive Visual Planning

ProWAM predicts sparse visual sub-goals and actions via progressive planning, achieving state-of-the-art long-horizon robotic control and strong zero-shot real-world generalization.

Fei Zhang, Zhaochong An, Duncan Frost, Yikai Wang and 4 more

Published Oct 1, 2026 · 0 citations · ▲ 83 on Hugging Face

Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models

FailBank turns runtime shield feedback into persistent VLA policy updates via failure-bank self-evolution, raising success rates up to 25.4 points and cutting policy-induced cost up to 35.6%.

Mingyue Cui, Zheyuan Liu, Yihan Zhu, Zheyuan Zhang and 1 more

Published Sep 30, 2026 · 0 citations · ▲ 15 on Hugging Face · Code ★ 2

Toward Real-Time VLAs: Stage-Aware Two-Step Flow Denoising and System-Level Evaluation

Two-step non-uniform flow denoising reduces VLA inference time from 61.6 ms to 22 ms by exploiting early-stage velocity stability. A distributed real-time framework and garment-folding evaluation show joint model-system optimization preserves task success with lower latency.

Di Wu, Rongtian Shen, Ping Liu, Yan Shen and 7 more

Published Sep 30, 2026 · 0 citations · Code ★ 1

Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing

Self-compensating VLA adapts online to robot execution errors via residual feedback, improving success over 30 points on physical arms and outperforming training-time robustness methods on RoboStress.

Sohyun Lee, Yoonjae Baek, Jaesang Won, Jinnyeong Kim and 4 more

Published Sep 29, 2026 · 0 citations · ▲ 18 on Hugging Face

Beyond Future Prediction: Denoising as Generative Adaptation for Robot Control

NowWAM adapts pretrained diffusion transformers to robot control via current-observation denoising and action prediction, achieving 87.7% on LIBERO-Plus with halved tokens and 1.8x speedup.

Zanyi Wang, Yuheng Lei, Dengyang Jiang, Ping Luo and 3 more

Published Sep 23, 2026 · 0 citations · ▲ 25 on Hugging Face · Code ★ 8

MolmoAct2: Action Reasoning Models for Real-world Deployment

MolmoAct2 is an open vision-language-action model with a specialized reasoning backbone, open action tokenizer, continuous-action expert, and adaptive reasoning that outperforms closed and open baselines across embodied reasoning and robot deployment benchmarks.

Haoquan Fang, Jiafei Duan, Donovan Clay, Sam Wang and 25 more

Published May 4, 2026 · 0 citations · ▲ 357 on Hugging Face · Code ★ 794

Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

Green-VLA stages vision-language-action training across five curriculum levels to generalize across robot embodiments. It uses scaled demonstration processing, embodiment-aware actions, and RL alignment to improve real-world humanoid success rates and long-horizon efficiency.

I. Apanasevich, M. Artemyev, R. Babakyan, P. Fedotova and 24 more

Published Jan 31, 2026 · 0 citations · ▲ 323 on Hugging Face · Code ★ 141

DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation

DynamicVLA combines efficient inference with continuous action streaming to fix latency-induced mismatches, improving dynamic manipulation success across synthetic and real-world benchmarks.

Haozhe Xie, Beichen Wen, Jiarui Zheng, Zhaoxi Chen and 3 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 77 on Hugging Face · Code ★ 348

Lift, See, Act: Hierarchical Robot Policy Pretraining with 3D Foundation Models

Yiyuan Ge, Changxing Ding, Ziyu Hao, Zijie Zheng and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Learning a Trajectory-Geometric Condition from Reasoning for VLA Planning

Yuguang Yang, Zhewen Tan, Canyu Chen, Cheng Chi and 8 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

TGPO: Trace-Guided Policy Optimization for Robot Task Planning via Verifiable Subgoal Generation

Zhihong Liu, Yang Li, RenMing Huang, Chendong Zeng and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Coarse-to-Refine: Trajectory Self-Refinement in Single Autoregressive Pass for Driving VLA

Canyu Chen, Yuguang Yang, Jianing Pang, Zhewen Tan and 8 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Long-term Embodied Visual Tracking with Lightweight Vision-Language-Action Models

Haowei Sun, Kaining Chen, Xutao Wen, Xinze Xie and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models

Nilaksh, Saurav Jha, Artem Zholus, Sarath Chandar

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

JRDB-AVR: An Active Visual Reasoning Benchmark for Real-World Embodied Environments

Zhixi Cai, Fucai Ke, Sukai Huang, Maria Garcia de la Banda and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

SpatialVAM: Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy

Peiyan Li, Yixiang Chen, Yuan Xu, Jiabing Yang and 12 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Locating and Repairing Domain Shift in VLM Trajectory Planning

Zhihong Cui, Hengyu Liu, Michael A. Riegler, Guandong Xu and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

PRISM: Primitive Routing via In-context Skill Mixing for Lifelong VLA

Jiachen Tao, Gengyu Zhang, Haoxuan Wang, Bing Liu and 1 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Apple-$\pi$: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence

Runmao Yao, Kairui Hu, Yukang Cao, Ruisi Wang and 10 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

OT-Robust3DVLA: A Wasserstein Barycenter is the Right Inductive Bias for Robust Multi-View 3D Vision-Language-Action Policies

Pawan Kumar

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Rethink Action Chunking in VLA Through Human Motor Control

Wenxi Chen, Yuejiang Liu, Zijian He, Shaoshuai Mou and 1 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Unified Noise Steering for Efficient Human-Guided VLA Adaptation

Junjie Lu, Xinyao Qin, Yuhua Jiang, Kaixin Wang and 5 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

VISTA: Support-Anchored Value Targeting for Fast Flow-Based Vision-Language-Action Policies

Hongjie Cao, Yuxuan Yang, Yunpeng Mei, Peng Cheng and 7 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

Denoising-Time Heterogeneity in VLA Action Generation: A Controlled Study via Step-Wise Expert

Baolong Gao, Yuhan Dong, Xudong Zhang, Yikai Wang

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Understanding Multimodal Failure in Action-Chunking Behavioral Cloning

Lorenzo Mazza, Massimiliano Datres, Ariel Rodriguez, Sebastian Bodenstedt and 2 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

$\text{A}^3$-VLA: Automatic Perception-Guided Attention Alignment for Robot Manipulation

Shengzhe Zhang, Qi Zhang, Dazhong Shen, Chao Wang and 2 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

FIVE-VLA: Fast and EffectIVE Closed-Loop Autonomous Driving with Recurrent Action Memory

Kemal Oksuz, Alexandru Buburuzan, Yuhan Yao, Puneet Dokania

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

Dodge-It: Learning Collision-Aware VLA Models for Robotic Manipulation

Jiawei Feng, Chuzhao Huang, Xinli Xu, Yingcong Chen

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Exploring the Limits of Compositional Generalization in Vision-Language-Action Manipulation

Xupeng Zhang, Yantai Yang, Chang Guo, Zhaokai Yin and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

SelfCritic-VLA: Language as Intrinsic Critic for Vision Language Action Models in Autonomous Driving

Fang Li, Shaoqing Xu, Yuechen Luo, Hanbing Li and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Perception for Action in Latent World Models

Petr Ivashkov, Randall Balestriero, Bernhard Schölkopf

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

SynerVLA: Exploiting Embodied Execution Phases for On-Device Dual-System VLA Acceleration

Qi Lu, Haotian Xiong, Ziyu Gong, TIANJUN SHI and 3 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Less Language, More Latents: Annotation-Efficient VLAs for Driving

LADA trains vision-language-action models using under 5% language annotations via latent action codebooks, achieving 87.98 driving scores on Bench2Drive.

Alexey Zakharov, Kemal Oksuz, Puneet Dokania

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

RotVLA: Rotational Latent Action for Vision-Language-Action Model

RotVLA introduces continuous rotational latent actions on SO(n) for vision-language-action pretraining, using a flow-matching head guided by latent planning to achieve state-of-the-art robot control.

Qiwei Li, Xicheng Gong, Xinghang Li, Peiyan Li and 4 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models

PriorVLA freezes a prior expert and trains an adaptation expert via expert queries to preserve pretrained vision-language-action priors, updating only 25% of full fine-tuning parameters while outperforming baselines on OOD and few-shot robot manipulation.

Xinyu Guo, Bin Xie, Wei Chai, Xianchi Deng and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling

UniT unifies human and humanoid actions via visual anchoring into shared latent tokens for scalable policy learning and world modeling. It achieves state-of-the-art data efficiency, zero-shot transfer, and cross-embodiment dynamics alignment.

Boyu Chen, Yi Chen, Lu QIU, Jerry Bai and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 32 on Hugging Face · Code ★ 103

PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models

PAPO-VLA improves vision-language-action reliability by identifying planning actions via action variation and trajectory outcomes, weighting them by causal importance in policy optimization, and boosting benchmark performance.

Peizheng Guo, Jingyao Wang, Changwen Zheng, Wenwen Qiang

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention

CofactVLA deconfounds vision-language-action models via counterfactual intervention to eliminate visual confounders and boost out-of-distribution success by 52.3%.

Yan Zhang, Yinan Wu, Haoran Duan, Jungong Han

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts

APIVOT adaptively interleaves language and visual reasoning for robot planning, outperforming baselines on long-horizon kitchen tasks with greatest gains in spatially constrained settings.

Emily Jin, Joy Hsu, Yiqing Xu, Weiyu Liu and 2 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models

RePO-VLA improves vision-language-action robustness by assigning roles to success, recovery, and failure trajectories, raising adversarial success from 20% to 75%.

Weijia Liufu, Xiaoyu Guo, Ruiyi Chen, Jingzhi Liu and 15 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

ATI-VLA: Action-Centric Predictive Vision–Language–Action Models via Actionable Alignment Then Adaptive Injection

ATI-VLA aligns predictive observations and actions in a shared discrete codebook, then adaptively injects predictive latents into action decoding, achieving state-of-the-art robotic manipulation with faster convergence.

Yijie Zhu, Rui Shao, Jie He, Wei Li and 7 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models

NS-VLA introduces neuro-symbolic encoding and hierarchical optimization to improve robotic manipulation generalization and exploration over prior VLA methods.

Ziyue Zhu, Shangyang Wu, Shuai Zhao, Zhao ZhiQiu and 7 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models

BAS-VLA calibrates frozen VLA actions via breaking-centered calibration and selective preservation gating to suppress stale-task drift and separate semantics. It achieves 98% clean success, 0% under target swaps, and 70% under style shifts versus 42%.

Shuaijun Liu, Feiyang You, Chengyu Wu, Shuyang Hao and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon

VLA-Corrector detects visual deviation via a lightweight monitor and triggers online replanning to adaptively correct action chunks without retraining VLA backbones.

Yi Pan, Miao Pan, Qi Lu, Jiaming Huang and 7 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 28 on Hugging Face · Code ★ 94

Reinforcing VLAs in Task-Agnostic World Models

RAW-Dream disentangles world models from task data by using task-agnostic pre-trained dynamics and VLM rewards to fine-tune VLAs entirely in zero-shot imagination with verified rollouts.

Yucen Wang, Rui Yu, Fengming Zhang, Junjie Lu and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs

Realtime-VLA FLASH uses a draft model and parallel verification to replace most full diffusion-based VLA inference rounds with faster speculative ones, cutting average latency 3.04x to 19.1 ms.

Jiahui Niu, Kefan Gu, Yucheng Zhao, shengwen Liang and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face

HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning

HumanoidArena benchmarks egocentric hierarchical whole-body learning via seven leg-critical tasks, finding policies solve diverse interactions but cross-tracker transfer remains fragile.

Taowen Wang, Zikang Xie, Bin Yang, Yunheng Wang and 12 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 18 on Hugging Face

ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models

ROCKET aligns multiple VLA layers to a 3D vision model via residual streams and shared projectors, achieving near-state-of-the-art LIBERO success with about 4% compute.

Guoheng Sun, Tingting Du, Kaixi Feng, Chenxiang Luo and 5 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control

GeCO replaces fixed-schedule flow matching with time-unconditional optimization that adaptively allocates inference compute and uses field norms as training-free OOD detectors.

Zunzhe Zhang, Runhan Huang, Yicheng Liu, Shaoting Zhu and 2 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

Embodied-R1.5 is an 8B-parameter embodied foundation model achieving state-of-the-art results on 16 of 24 embodied VLM benchmarks via multi-task balanced RL and a closed-loop planner-grounder-corrector framework.

Yifu Yuan, Yaoting Huang, Xianze Yao, Shuoheng Zhang and 19 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 59 on Hugging Face · Code ★ 60

ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models

ElegantVLA accelerates vision-language-action models via adaptive compute scheduling, achieving up to 3.77x speedup and doubling control frequency without retraining.

Ye Li, Huanan Liu, Kangye Ji, Yuan Meng and 6 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model

METIS is a vision-language-action model pretrained on multi-source egocentric data that achieves the highest success rate across six real-world dexterous manipulation tasks.

Yankai Fu, Ning Chen, Junkai Zhao, Shaozhe Shan and 4 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face

Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring

Hide-and-Seek formulates VLA failure detection as coarsely supervised learning to localize failure-indicative actions from trajectory-level labels alone via contrastive objectives, achieving state-of-the-art multi-task detection with practical accuracy-timeliness trade-offs.

Seongheon Park, Wendi Li, Changdae Oh, Samuel (Min-Hsuan) Yeh and 3 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 8 on Hugging Face

Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs

A frozen vision-language-action model improves test-time reliability by retrieving past successful actions to guide flow-matching generation without parameter updates.

Jianchao Zhao, Huoren Yang, Hu Yusong, Yuyang Gao and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies

FineVLA introduces fine-grained action-aligned supervision for steerable vision-language-action policies, yielding up to 86.8% simulation and 62.7 real-world success and boosting steerable control over coarse instructions.

Xintong Hu, Xuhong Huang, JINYU ZHANG, Yutong Yao and 8 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 9 on Hugging Face

FASTER: Rethinking Real-Time Flow VLAs

FASTER accelerates real-time flow vision-language-action models via horizon-aware sampling that compresses immediate-action denoising into one step, slashing reaction latency on dynamic robot tasks.

Yuxiang Lu, Zhe Liu, Xianzhe Fan, Zhenya YANG and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 61 on Hugging Face · Code ★ 157

Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation

Embodied chain-of-thought improves generalization when grounded in action guidance, and ERVLA uses reasoning-dropout supervision to avoid unstable autoregressive reasoning at inference, achieving state-of-the-art robot manipulation results.

Nan Sun, Yuan Zhang, Yongkun Yang, Wentao Zhao and 9 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Continually Evolving Skill Knowledge in Vision Language Action Model

Stellar VLA learns evolving skills via parameter-free continual imitation with knowledge-guided routing, achieving strong LIBERO performance with 1% replay and real-world transfer.

Yuxuan Wu, Guangming Wang, Zhiheng Yang, Tianchen Deng and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving

MAPLE trains vision-language-action driving models via latent multi-agent rollout and reinforcement learning, achieving state-of-the-art closed-loop performance without external simulators.

Rajeev Yasarla, Deepti Hegde, Hsin-Pai Cheng, Shizhong Han and 8 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models

MCF-Proto equips VLA policies with motion-centric action frames and prototype-based parameterization, improving robustness to geometric perturbations via compact, structured action representations.

Huoren Yang, Jianchao Zhao, Hu Yusong, Qiguan Ou and 6 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Pose6DAug: Physically Plausible Multi-View Object Swapping for Robot Data Augmentation

Pose6DAug augments robot training by swapping objects in successful episodes via 3D mesh pose trajectories, improving VLA success on novel objects by 16.5%.

Jonghoon Lee, Seong Hyeon Park, Minha Lee, Byungwoo Jeon and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model

Evo-Depth is a lightweight 0.9-billion-parameter vision-language-action model using implicit depth encoding from RGB to improve spatial manipulation without extra sensors. It achieves top benchmark performance with minimal GPU memory and highest inference speed among compared methods.

Tao Lin, Yuxin Du, Jiting Liu, Nuobei Zhu and 13 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies

PhaseLoRA conditions LoRA updates on control-regime descriptors at each step, improving continuous-action VLA success by 12.2 points over high-rank baselines.

Yufei Guo, Yinan Wu, Haoran Duan, guiguang ding and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026