#VLA (185)

A one-stop VLA toolbox from Dexmal: the unified DexData format spans pretraining, fine-tuning (full/LoRA/RL), inference, and evaluation, supporting mainstream models (π0, CogACT, OFT, MemVLA, GR00T N1) plus the in-house dual-expert DM0; DB-pretraining brings consistent gains across five simulation benchmarks, with 62% average success on RoboChallenge Table30 real-robot evaluation.

VLAManipulationNavigation

Python1.4k1814

VT-Bridge: Bridging Pretrained Foundation VLAs to VTLAs via Lightweight Residual Adaptation

Vision-Tactile-Language-Action (VTLA) models have demonstrated clear advantages over Vision-Language-Action (VLA) models in contact-rich manipulation. However, developing VTLA models is severely constrained by the massive amounts of vision-tactile data and computational resources required. To address this bottleneck, we propose VT-Bridge, a lightweight residual adaptation strategy that bridges pretrained foundation VLAs to VTLAs. Rather than training a VTLA model from scratch or modifying the original architecture of a pretrained VLA, VT-Bridge employs an identical lightweight residual-adapter architecture across VLA backbones and uses backbone-specific weights to refine actions at the robot execution frequency. This design substantially lowers the data and training barriers. Specifically, it requires up to 50 vision-tactile demonstrations per task to fine-tune a VLA backbone and train a 0.98M-parameter residual adapter. Experiments with three representative VLA backbones (π₀, π_0.5, and SmolVLA) across four contact-rich manipulation tasks further demonstrate its consistent effectiveness across VLA architectures. On average, VT-Bridge raises the task completion rate from 11.7% with task-level VLA fine-tuning alone to 62.9%. Together, these findings demonstrate the broad applicability, effectiveness, and accessibility of VT-Bridge for contact-rich manipulation. The project page is available at https://hoxnocha.github.io/vt-bridge-web/.

Yansong Wu, Tuo Yang, Rongping Zhao · 42 views · Sep 18, 2026

Tactile SensingVLAContact-Rich ManipulationSep 18, 2026

TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency

Textual reasoning before acting has improved vision-language-action (VLA) models, but at the cost of latency: every action conditioned on the reasoning text must wait for autoregressive decoding. We show that actions do not need to wait for or condition on the generated reasoning to benefit from it, because the reasoning supervision already improves the backbone representation. We introduce TacitVLA, a reasoning VLA whose action expert never attends to the reasoning it generates for the current call. On long-horizon tasks where the reasoning text also serves as episodic memory, it can generate each entry during action execution rather than before acting. We evaluate it in a controlled study on four benchmarks spanning manipulation and autonomous driving, memory and non-memory tasks: RoboMME, RMBench, LIBERO, and PhysicalAI-AV. On all four, TacitVLA matches the performance of its explicit-reasoning counterpart at up to 3.4x lower latency, and matches the latency of the same architecture trained without reasoning at up to +17.1% success. In absolute terms, it surpasses the best previously published results on the RoboMME Counting suite (82.7% vs. 66.8%) and RMBench (77.5% vs. 56.5%), and reaches 72.9% on LIBERO-Plus and a 52.5% scene score on the public split of the PhysicalAI-AV closed-loop driving challenge. Project page: https://tacitvla.github.io.

Jack Lu, Yurong You, Boyi Li · 59 views · Oct 13, 2026

VLAEmbodied ReasoningManipulationOct 13, 2026

0:10

In-Context Learning for Robots: Methods and Applications

General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL) for robots supports this process by using demonstrations and interaction to direct existing competence with neural parameters held fixed during deployment. We organize this literature review around the interfaces connecting contextual evidence to execution, distinguishing four families: context-conditioned policies, geometric demonstration transfer, world-model-based control, and skill- and agent-based execution. Comparing these interfaces clarifies their transfer assumptions and the roles of training, correspondence, and memory in making context useful. Across manipulation and navigation, we examine how these mechanisms preserve taught requirements as objects, environments, and execution conditions change. This analysis links method design to evaluation practices that distinguish responsiveness to teaching, physical transfer, and benefits from retained experience. The resulting agenda connects compositional task acquisition and faithful transfer with physical recursive self-improvement, in which experience improves the ability to learn subsequent tasks.

Huang, Haojian, Li, Zexi, Guo, Junhao · 147 views · Sep 28, 2026

In-Context LearningRobot LearningSurveySep 28, 2026

0:40

GAM: 3D Grounding as a Robot Foundation

@DJiafei · 105 views · 2026-09-22

GAM3D GroundingRobot foundation models

Exposing the Long-tail in Embodied Urban Navigation via Scalable Learning from In-the-Wild Videos

Learning embodied urban navigation policies from real-world data is constrained by the cost of task-specific data collection and the limited coverage of rare yet safety-critical scenarios. To address these challenges, we present a scalable framework for learning point-goal urban navigation from web-scale in-the-wild egocentric videos while systematically exposing its long tail. The framework automatically annotates uncurated web videos with metric trajectories and structured navigation semantics, which are then used to train a vision-language-action policy for interpretable navigation planning. We characterize the long tail based on model performance and the distribution of perception-motion patterns, and employ reflection-based analysis to diagnose recurring failure modes. Experiments on web-video data and real-world urban navigation tasks demonstrate effective knowledge transfer from unconstrained videos and reveal coherent long-tail structures beyond aggregate navigation performance.

Bingyi Xia, Han Bao, Zhewei Chen · 143 views · Aug 17, 2026

Urban NavigationVLAEmbodied AIAug 17, 2026

VioLA: Learning Generalist Humanoid Control Policies from Human Data

VioLA is a generalist humanoid policy that predicts body and hand motion latents instead of joint commands. Frozen SONIC-based encoders map human and robot demonstrations into the same action space, so 93.2% of its 140.6M training frames come from human recordings. On a real Unitree G1 it reaches 100% locomotion and 88.6% manipulation success with no task-specific fine-tuning.

Mert Albaba, Jens Beißwenger, Anna Manasyan · 191 views · Oct 8, 2026

HumanoidVLAWhole-Body ControlOct 8, 2026

Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models

Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models, yet robot trajectories are harder to scale than web-scale image-text data because embodied collection is costly and sparsely covers the physical world. This makes representation quality a central bottleneck: under a fixed robot-data budget, continued pre-training must turn limited trajectories into transferable visual-action knowledge rather than merely fit actions. We propose VLAct, a VLA-oriented VLM backbone trained on broad, heterogeneous, multi-embodiment robot data before task-specific fine-tuning. VLAct preserves the broad VLM prior and encourages shared action semantics across embodiments through VLM-prior preservation, multi-head continuous action co-supervision, and a partially unified cross-embodiment action layout, while allowing task-specific action heads during fine-tuning. Across simulation, real-world, and unseen-embodiment transfer, VLAct consistently improves downstream performance under fixed fine-tuning protocols. On LIBERO-Plus and RoboTwin 2.0, VLAct surpasses industrial VLA systems including ABot-M0 and LingBot-VLA, achieving success rates of 82.6% and 92.5%. On RoboDojo, VLAct ranks sixth among all policies by success rate and outperforms all explicitly designated world-action model (WAM) entries on both metrics. Most notably, on RoboCasa-GR1, an unseen humanoid embodiment, VLAct using only 20% of downstream trajectories outperforms the full-data GR00T-N1.6 baseline. These results are obtained using fully open-source data and only a 16-GPU training setup, showing that representation-centric continued pre-training can deliver highly competitive performance under a modest compute budget and is an important independent axis of VLA progress beyond data scaling.

Senqiao Yang, Chengyao Wang, Yuxin Chen · 242 views · Aug 27, 2026

VLAContinued Pre-trainingCross-EmbodimentAug 27, 2026

EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning

Egocentric human data offer a path to scaling robot learning beyond costly robot demonstrations, yet the embodiment gap makes raw human trajectories a poor supervisory target for control. Our key insight is that, although low-level actions are embodiment-specific, their underlying motion intent can capture task-relevant structure that transfers across humans and robots. We introduce EgoLAP, a VLA pre-training framework that jointly learns from human and robot trajectories through a shared language-based action chain-of-thought. EgoLAP expresses motion intent as structured, temporally abstracted language actions and pairs them with motion-level reasoning grounded in scene geometry, physics, and object affordances. Across extensive real-world and simulated experiments, EgoLAP transfers human experience to robot control more effectively than alternative action representations and reaches 80.1% mean real-world task progress, a 2.3x performance gain over alternative action representations. Motion-level reasoning also outperforms a composite reasoning format that combines subtask, object-box, and visual-trace reasoning.

Lihan Zha, Shresth Grover, Tenny Yin · 304 views · Oct 6, 2026

VLAManipulationEgocentric VisionOct 6, 2026

2:38

Long-WAM: Scaling World-Action Model Context to 19.2s in Real Time

@AaronWeiHuang · 370 views · 2026-10-08

World-action modelsVLAReal-time control

0:21

SEAR: Benchmark for Self-Evolving LLM Agents on Robots

@BangzhengL · 856 views · 2026-10-07

LLMRobot ControlVLA

SkeleWAM: squeezing a manipulation scene into a sparse 3D skeleton

World action models usually represent future state as video or visual latents, which encode geometry only implicitly and carry appearance irrelevant to control. SkeleWAM keeps just three kinds of 3D landmarks - robot joints, object centres and interaction points - and uses that sparse skeleton for both action generation and future-skeleton prediction, training with the latter as auxiliary supervision and dropping it at inference. On LIBERO-Plus it reaches 85.9% zero-shot success with 57.1M parameters, beating the 2B-parameter Cosmos-Policy by 3.7 points.

Juyi Sheng, Hua Wang, Mengyuan Liu · 402 views · Oct 1, 2026

VLAWorldActionModelManipulationOct 1, 2026

1:00

Reka Releases Rho-1, a 19B Omni Model

@RekaAILabs · 425 views · 2026-10-05

Embodied AIOmni ModelMultimodal

NavVerse: Benchmarking Indoor-to-Outdoor Embodied Navigation in Continuous Robot Simulation

NavVerse from UMich CURLY Lab and Tsinghua builds a physics-enabled navigation benchmark on Isaac Sim with 100 indoor, 50 outdoor and 50 indoor-to-outdoor hybrid scenes and 10,000 ObjNav/PlaceNav/VLN episodes evaluated through a unified waypoint interface and PID execution layer. Zero-shot experiments across RL, VLA and modular baselines show the strongest VLA drops from 17.65% outdoor to 3.64% hybrid on PlaceNav, identifying the indoor-to-outdoor transition as the major bottleneck; the benchmark further contributes collision-rate, obstacle-clearance and navigable-surface safety diagnostics plus embodiment-dynamics controls.

Junzhe Wu, Yue Hu, Zeyu Han · 521 views · Jul 22, 2026

Embodied NavigationNavVerseBenchmarksJul 22, 2026

2:51

NavVerse (CoRL 2026): a 200-scene, 10K-episode indoor-to-outdoor navigation benchmark — best zero-shot VLA reaches 11.6%, then halves across the door

@GhaffariMaani · 448 views · 2026-10-02

Embodied NavigationNavVerseBenchmarks

0:22

Stanford Real-Time EXPO-FT makes slow-but-smart VLAs real-time on robots: 42% to 97% with just 10 minutes of online data

@LeoKharon · 482 views · 2026-10-02

VLAReinforcement LearningReal-time control

2:37

LimX TRON 2: a multi-form embodied robot bringing manipulation, perception and autonomous mobility into human workspaces

@andresvilarino · 495 views · 2026-10-01

LimX DynamicsTRON-2Embodied AI

One Policy, Many Embodiments: Unified Camera-Centric Action Geometry Pre-training for Heterogeneous Embodied Manipulation

UCAG-P from Xiaomi Embodied Intelligence and University of Macau unifies robot arms, bimanual platforms, humanoids and human-hand videos into one camera-centric action schema: 3D camera-frame anchor trajectories of the wrist (p0) and grasp center (p1), with a geometry-conditioned translator emitting executable commands — no retargeting or human-to-robot video synthesis needed. Built on Qwen3-VL-4B with three-stage training over 1.02M episodes / 6,373.6 hours / nine embodiments (36.7% human data), a single checkpoint without benchmark fine-tuning reaches 98.3% on LIBERO, 88.7%/89.2% on RoboTwin Easy/Hard, 82.0% zero-shot on LIBERO-Plus and 62.0% on RoboCasa GR-1; on real Piper robots bread pickup hits 60% vs 20% for pi0.5, with 35% zero-shot ALOHA-to-ARX transfer.

Xiaomi Embodied Intelligence Team, University of Macau, : · 612 views · Aug 26, 2026

VLACross-EmbodimentManipulation learningAug 26, 2026

1:07

Uni-VLaT: adding whole-body touch to pretrained VLAs lifts humanoid loco-manipulation from 32% to 75%

@stepjamUK · 524 views · 2026-09-29

Uni-VLaTTactile PerceptionTactile Sensing

RLT: Physical Intelligence masters the last millimeter with RL Tokens

Physical Intelligence (Sergey Levine's team, Mar 19, 2026) present RL Tokens (RLT): freeze a pretrained VLA, attach an encoder-decoder that compresses its internal embeddings into a bottleneck RL token, then run online RL with a ~1M-parameter actor-critic on the real robot, refining only the critical phase (editing VLA action chunks rather than generating from scratch, anchored by a BC regularizer plus reference-action dropout). Across four sub-millimeter tasks the critical phase speeds up by up to 3x, screw success goes 20% to 65%, and half of Ethernet insertion episodes beat every human teleoperation demo - with just 15 minutes of real robot data.

BLOG

VLAOnline RLRLPDPhysical IntelligenceDexterous Manipulation

As an Amazon Associate, we earn from qualifying purchases.