Showing 1–7 of 7 results for author: Swerdlow, A

FASTER: Value-Guided Sampling for Fast RL

Authors: Perry Dong, Alexander Swerdlow, Dorsa Sadigh, Chelsea Finn

Abstract: Some of the most performant reinforcement learning algorithms today can be prohibitively expensive as they use test-time scaling methods such as sampling multiple action candidates and selecting the best one. In this work, we propose FASTER, a method for getting the benefits of sampling-based test-time scaling of diffusion-based policies without the computational cost by tracing the performance ga… ▽ More Some of the most performant reinforcement learning algorithms today can be prohibitively expensive as they use test-time scaling methods such as sampling multiple action candidates and selecting the best one. In this work, we propose FASTER, a method for getting the benefits of sampling-based test-time scaling of diffusion-based policies without the computational cost by tracing the performance gain of action samples back to earlier in the denoising process. Our key insight is that we can model the denoising of multiple action candidates and selecting the best one as a Markov Decision Process (MDP) where the goal is to progressively filter action candidates before denoising is complete. With this MDP, we can learn a policy and value function in the denoising space that predicts the downstream value of action candidates in the denoising process and filters them while maximizing returns. The result is a method that is lightweight and can be plugged into existing generative RL algorithms. Across challenging long-horizon manipulation tasks in online and batch-online RL, FASTER consistently improves the underlying policies and achieves the best overall performance among the compared methods. Applied to a pretrained VLA, FASTER achieves the same performance while substantially reducing training and inference compute requirements. Code is available at https://github.com/alexanderswerdlow/faster . △ Less

Submitted 21 April, 2026; originally announced April 2026.

TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse

Authors: Perry Dong, Kuo-Han Hung, Alexander Swerdlow, Dorsa Sadigh, Chelsea Finn

Abstract: Despite scale driving substantial recent advancements in machine learning, reinforcement learning (RL) methods still primarily use small value functions. Naively scaling value functions -- including with a transformer architecture, which is known to be highly scalable -- often results in learning instability and worse performance. In this work, we ask what prevents transformers from scaling effect… ▽ More Despite scale driving substantial recent advancements in machine learning, reinforcement learning (RL) methods still primarily use small value functions. Naively scaling value functions -- including with a transformer architecture, which is known to be highly scalable -- often results in learning instability and worse performance. In this work, we ask what prevents transformers from scaling effectively for value functions? Through empirical analysis, we identify the critical failure mode in this scaling: attention scores collapse as capacity increases. Our key insight is that we can effectively prevent this collapse and stabilize training by controlling the entropy of the attention scores, thereby enabling the use of larger models. To this end, we propose Transformer Q-Learning (TQL), a method that unlocks the scaling potential of transformers in learning value functions in RL. Our approach yields up to a 43% improvement in performance when scaling from the smallest to the largest network sizes, while prior methods suffer from performance degradation. △ Less

Submitted 1 February, 2026; originally announced February 2026.

$π^{*}_{0.6}$: a VLA That Learns From Experience

Authors: Physical Intelligence, Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Kevin Black, Ken Conley, Grace Connors, James Darpinian, Karan Dhabalia, Jared DiCarlo, Danny Driess, Michael Equi, Adnan Esmail, Yunhao Fang, Chelsea Finn, Catherine Glossop, Thomas Godden, Ivan Goryachev, Lachy Groom, Hunter Hancock, Karol Hausman, Gashon Hussein, Brian Ichter, Szymon Jakubczak, Rowan Jen , et al. (31 additional authors not shown)

Abstract: We study how vision-language-action (VLA) models can improve through real-world deployments via reinforcement learning (RL). We present a general-purpose method, RL with Experience and Corrections via Advantage-conditioned Policies (RECAP), that provides for RL training of VLAs via advantage conditioning. Our method incorporates heterogeneous data into the self-improvement process, including demon… ▽ More We study how vision-language-action (VLA) models can improve through real-world deployments via reinforcement learning (RL). We present a general-purpose method, RL with Experience and Corrections via Advantage-conditioned Policies (RECAP), that provides for RL training of VLAs via advantage conditioning. Our method incorporates heterogeneous data into the self-improvement process, including demonstrations, data from on-policy collection, and expert teleoperated interventions provided during autonomous execution. RECAP starts by pre-training a generalist VLA with offline RL, which we call $π^{*}_{0.6}$, that can then be specialized to attain high performance on downstream tasks through on-robot data collection. We show that the $π^{*}_{0.6}$ model trained with the full RECAP method can fold laundry in real homes, reliably assemble boxes, and make espresso drinks using a professional espresso machine. On some of the hardest tasks, RECAP more than doubles task throughput and roughly halves the task failure rate. △ Less

Submitted 18 November, 2025; v1 submitted 18 November, 2025; originally announced November 2025.

Unified Multimodal Discrete Diffusion

Authors: Alexander Swerdlow, Mihir Prabhudesai, Siddharth Gandhi, Deepak Pathak, Katerina Fragkiadaki

Abstract: Multimodal generative models that can understand and generate across multiple modalities are dominated by autoregressive (AR) approaches, which process tokens sequentially from left to right, or top to bottom. These models jointly handle images, text, video, and audio for various tasks such as image captioning, question answering, and image generation. In this work, we explore discrete diffusion m… ▽ More Multimodal generative models that can understand and generate across multiple modalities are dominated by autoregressive (AR) approaches, which process tokens sequentially from left to right, or top to bottom. These models jointly handle images, text, video, and audio for various tasks such as image captioning, question answering, and image generation. In this work, we explore discrete diffusion models as a unified generative formulation in the joint text and image domain, building upon their recent success in text generation. Discrete diffusion models offer several advantages over AR models, including improved control over quality versus diversity of generated samples, the ability to perform joint multimodal inpainting (across both text and image domains), and greater controllability in generation through guidance. Leveraging these benefits, we present the first Unified Multimodal Discrete Diffusion (UniDisc) model which is capable of jointly understanding and generating text and images for a variety of downstream tasks. We compare UniDisc to multimodal AR models, performing a scaling analysis and demonstrating that UniDisc outperforms them in terms of both performance and inference-time compute, enhanced controllability, editability, inpainting, and flexible trade-off between inference time and generation quality. Code and additional visualizations are available at https://unidisc.github.io. △ Less

Submitted 26 March, 2025; originally announced March 2025.

Comments: Project Website: https://unidisc.github.io

Unifying 2D and 3D Vision-Language Understanding

Authors: Ayush Jain, Alexander Swerdlow, Yuzhou Wang, Sergio Arnaud, Ada Martin, Alexander Sax, Franziska Meier, Katerina Fragkiadaki

Abstract: Progress in 3D vision-language learning has been hindered by the scarcity of large-scale 3D datasets. We introduce UniVLG, a unified architecture for 2D and 3D vision-language understanding that bridges the gap between existing 2D-centric models and the rich 3D sensory data available in embodied systems. Our approach initializes most model weights from pre-trained 2D models and trains on both 2D a… ▽ More Progress in 3D vision-language learning has been hindered by the scarcity of large-scale 3D datasets. We introduce UniVLG, a unified architecture for 2D and 3D vision-language understanding that bridges the gap between existing 2D-centric models and the rich 3D sensory data available in embodied systems. Our approach initializes most model weights from pre-trained 2D models and trains on both 2D and 3D vision-language data. We propose a novel language-conditioned mask decoder shared across 2D and 3D modalities to ground objects effectively in both RGB and RGB-D images, outperforming box-based approaches. To further reduce the domain gap between 2D and 3D, we incorporate 2D-to-3D lifting strategies, enabling UniVLG to utilize 2D data to enhance 3D performance. With these innovations, our model achieves state-of-the-art performance across multiple 3D vision-language grounding tasks, demonstrating the potential of transferring advances from 2D vision-language learning to the data-constrained 3D domain. Furthermore, co-training on both 2D and 3D data enhances performance across modalities without sacrificing 2D capabilities. By removing the reliance on 3D mesh reconstruction and ground-truth object proposals, UniVLG sets a new standard for realistic, embodied-aligned evaluation. Code and additional visualizations are available at https://univlg.github.io . △ Less

Submitted 8 June, 2025; v1 submitted 13 March, 2025; originally announced March 2025.

Comments: The first two authors contributed equally

Street-View Image Generation from a Bird's-Eye View Layout

Authors: Alexander Swerdlow, Runsheng Xu, Bolei Zhou

Abstract: Bird's-Eye View (BEV) Perception has received increasing attention in recent years as it provides a concise and unified spatial representation across views and benefits a diverse set of downstream driving applications. At the same time, data-driven simulation for autonomous driving has been a focal point of recent research but with few approaches that are both fully data-driven and controllable. I… ▽ More Bird's-Eye View (BEV) Perception has received increasing attention in recent years as it provides a concise and unified spatial representation across views and benefits a diverse set of downstream driving applications. At the same time, data-driven simulation for autonomous driving has been a focal point of recent research but with few approaches that are both fully data-driven and controllable. Instead of using perception data from real-life scenarios, an ideal model for simulation would generate realistic street-view images that align with a given HD map and traffic layout, a task that is critical for visualizing complex traffic scenarios and developing robust perception models for autonomous driving. In this paper, we propose BEVGen, a conditional generative model that synthesizes a set of realistic and spatially consistent surrounding images that match the BEV layout of a traffic scenario. BEVGen incorporates a novel cross-view transformation with spatial attention design which learns the relationship between cameras and map views to ensure their consistency. We evaluate the proposed model on the challenging NuScenes and Argoverse 2 datasets. After training, BEVGen can accurately render road and lane lines, as well as generate traffic scenes with diverse different weather conditions and times of day. △ Less

Submitted 13 February, 2024; v1 submitted 11 January, 2023; originally announced January 2023.

SCALER: A Tough Versatile Quadruped Free-Climber Robot

Authors: Yusuke Tanaka, Yuki Shirai, Xuan Lin, Alexander Schperberg, Hayato Kato, Alexander Swerdlow, Naoya Kumagai, Dennis Hong

Abstract: This paper introduces SCALER, a quadrupedal robot that demonstrates climbing on bouldering walls, overhangs, ceilings and trotting on the ground. SCALER is one of the first high-degrees of freedom four-limbed robots that can free-climb under the Earth's gravity and one of the most mechanically efficient quadrupeds on the ground. Where other state-of-the-art climbers specialize in climbing, SCALER… ▽ More This paper introduces SCALER, a quadrupedal robot that demonstrates climbing on bouldering walls, overhangs, ceilings and trotting on the ground. SCALER is one of the first high-degrees of freedom four-limbed robots that can free-climb under the Earth's gravity and one of the most mechanically efficient quadrupeds on the ground. Where other state-of-the-art climbers specialize in climbing, SCALER promises practical free-climbing with payload \textit{and} ground locomotion, which realizes true versatile mobility. A new climbing gait, SKATE gait, increases the payload by utilizing the SCALER body linkage mechanism. SCALER achieves a maximum normalized locomotion speed of $1.87$ /s, or $0.56$ m/s on the ground and $1.0$ /min, or $0.35$ m/min in bouldering wall climbing. Payload capacity reaches $233$ % of the SCALER weight on the ground and $35$ % on the vertical wall. Our GOAT gripper, a mechanically adaptable underactuated two-finger gripper, successfully grasps convex and non-convex objects and supports SCALER. △ Less

Submitted 30 July, 2022; v1 submitted 3 July, 2022; originally announced July 2022.

Comments: Proceeding to IROS 2022, Preprint and not a final version