arXiv subjects

Agrim Gupta

Publications and source records attributed to Agrim Gupta.

At least 19 recordsLinked to original sources

arXiv2025

Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer

General-purpose robots need a deep understanding of the physical world, advanced reasoning, and general and dexterous control. This report introduces the latest generation of the Gemini Robotics model family: Gemini Robotics 1.5, a multi-embodiment Vision-Language-Action (VLA) model, and Gemini Robotics-ER 1.5, a state-of-the-art Embodied Reasoning (ER) model. We are bringing together three major innovations. First, Gemini Robotics 1.5 features a novel architecture and a Motion Transfer (MT) mechanism, which enables it to learn from heterogeneous, multi-embodiment robot data and makes the VLA more general. Second, Gemini Robotics 1.5 interleaves actions with a multi-level internal reasoning process in natural language. This enables the robot to "think before acting" and notably improves its ability to decompose and execute complex, multi-step tasks, and also makes the robot's behavior more interpretable to the user. Third, Gemini Robotics-ER 1.5 establishes a new state-of-the-art for embodied reasoning, i.e., for reasoning capabilities that are critical for robots, such as visual and spatial understanding, task planning, and progress estimation. Together, this family of models takes us a step towards an era of physical agents-enabling robots to perceive, think and then act so they can solve complex multi-step tasks.

cs.RO↗

arXiv2025

Exploring Diffusion Transformer Designs via Grafting

Designing model architectures requires decisions such as selecting operators (e.g., attention, convolution) and configurations (e.g., depth, width). However, evaluating the impact of these decisions on model quality requires costly pretraining, limiting architectural investigation. Inspired by how new software is built on existing code, we ask: can new architecture designs be studied using pretrained models? To this end, we present grafting, a simple approach for editing pretrained diffusion transformers (DiTs) to materialize new architectures under small compute budgets. Informed by our analysis of activation behavior and attention locality, we construct a testbed based on the DiT-XL/2 design to study the impact of grafting on model quality. Using this testbed, we develop a family of hybrid designs via grafting: replacing softmax attention with gated convolution, local attention, and linear attention, and replacing MLPs with variable expansion ratio and convolutional variants. Notably, many hybrid designs achieve good quality (FID: 2.38-2.64 vs. 2.27 for DiT-XL/2) using <2% pretraining compute. We then graft a text-to-image model (PixArt-Sigma), achieving a 1.43x speedup with less than a 2% drop in GenEval score. Finally, we present a case study that restructures DiT-XL/2 by converting every pair of sequential transformer blocks into parallel blocks via grafting. This reduces model depth by 2x and yields better quality (FID: 2.77) than other models of comparable depth. Together, we show that new diffusion model designs can be explored by grafting pretrained DiTs, with edits ranging from operator replacement to architecture restructuring. Code and grafted models: https://grafting.stanford.edu

cs.LG↗

arXiv2025

Utilizing High Sampling Rate ADCs for Cost Efficient MIMO Radios

In the past decade, $>$1 Gsps ADCs have become commonplace and are used in many modern 5G base station chips. A major driving force behind this adoption is the benefits of digital up/down-conversion and improved digital filtering. Recent works have also advocated for utilizing this high sampling bandwidth to fit-in multiple MIMO streams, and reduce the number of ADCs required to build MIMO base-stations. This can potentially reduce the cost of Massive MIMO RUs, since ADCs are the most expensive electronics in the base-station radio chain. However, these recent works do not model the necessary decimation filters that exist in the signal path of these high sampling rate ADCs. We show in this short paper that because of the decimation filters, there can be introduction of cross-talks which can hinder the performance of these shared ADC interfaces. We simulate the shared ADC interface with Matlab 5G toolbox for uplink MIMO, and show that these cross-talks can be mitigated by performing MMSE equalization atop the PUSCH estimated channels.

eess.SP↗

arXiv2025

MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation

Diffusion models are successful for synthesizing high-quality videos but are limited to generating short clips (e.g., 2-10 seconds). Synthesizing sustained footage (e.g. over minutes) still remains an open research question. In this paper, we propose MALT Diffusion (using Memory-Augmented Latent Transformers), a new diffusion model specialized for long video generation. MALT Diffusion (or just MALT) handles long videos by subdividing them into short segments and doing segment-level autoregressive generation. To achieve this, we first propose recurrent attention layers that encode multiple segments into a compact memory latent vector; by maintaining this memory vector over time, MALT is able to condition on it and continuously generate new footage based on a long temporal context. We also present several training techniques that enable the model to generate frames over a long horizon with consistent quality and minimal degradation. We validate the effectiveness of MALT through experiments on long video benchmarks. We first perform extensive analysis of MALT in long-contextual understanding capability and stability using popular long video benchmarks. For example, MALT achieves an FVD score of 220.4 on 128-frame video generation on UCF-101, outperforming the previous state-of-the-art of 648.4. Finally, we explore MALT's capabilities in a text-to-video generation setting and show that it can produce long videos compared with recent techniques for long text-to-video generation.

cs.CV↗

arXiv2025

PhaseMO: A Universal Massive MIMO Architecture for Sustainable NextG

The rapid proliferation of devices and increasing data traffic in cellular networks necessitate advanced solutions to meet these escalating demands. Massive MIMO (Multiple Input Multiple Output) technology offers a promising approach, significantly enhancing throughput, coverage, and spatial multi-plexing. Despite its advantages, massive MIMO systems often lack flexible software controls over hardware, limiting their ability to optimize operational expenditure (OpEx) by reducing power consumption while maintaining performance. Current software-controlled methods, such as antenna muting combined with digital beamforming and hybrid beamforming, have notable limitations. Antenna muting struggles to maintain throughput and coverage, while hybrid beamforming faces hardware constraints that restrict scalability and future-proofing. This work presents PhaseMO, a versatile approach that adapts to varying network loads. PhaseMO effectively reduces power consumption in low-load scenarios without sacrificing coverage and overcomes the hardware limitations of hybrid beamforming, offering a scalable and future-proof solution. We will show that PhaseMO can achieve up to 30% improvement in energy efficiency while avoiding about 10% coverage reduction and 5dB increase in UE transmit power.

eess.SP↗

arXiv2024

HourVideo: 1-Hour Video-Language Understanding

We present HourVideo, a benchmark dataset for hour-long video-language understanding. Our dataset consists of a novel task suite comprising summarization, perception (recall, tracking), visual reasoning (spatial, temporal, predictive, causal, counterfactual), and navigation (room-to-room, object retrieval) tasks. HourVideo includes 500 manually curated egocentric videos from the Ego4D dataset, spanning durations of 20 to 120 minutes, and features 12,976 high-quality, five-way multiple-choice questions. Benchmarking results reveal that multimodal models, including GPT-4 and LLaVA-NeXT, achieve marginal improvements over random chance. In stark contrast, human experts significantly outperform the state-of-the-art long-context multimodal model, Gemini Pro 1.5 (85.0% vs. 37.3%), highlighting a substantial gap in multimodal capabilities. Our benchmark, evaluation toolkit, prompts, and documentation are available at https://hourvideo.stanford.edu

cs.CV↗

arXiv2024

DAXA: Traversing the X-ray desert by Democratising Archival X-ray Astronomy

We introduce a new, open-source, Python module for the acquisition and processing of archival data from many X-ray telescopes - Democratising Archival X-ray Astronomy (hereafter referred to as DAXA). Our software is built to increase access to, and use of, large archives of X-ray astronomy data; providing a unified, easy-to-use, Python interface to the disparate archives and processing tools. We provide this interface for the majority of X-ray telescopes launched within the last 30 years. This module enables much greater access to X-ray data for non-specialists, while preserving low-level control of processing for X-ray experts. It is useful for identifying relevant observations of a single object of interest but it excels at creating multi-mission datasets for serendipitous or targeted studies of large samples of X-ray emitting objects. The management and organization of datasets is also made easier; DAXA archives can be version controlled and updated if new data become available. Once relevant observations are identified, the raw data can be downloaded (and optionally processed) through DAXA, or pre-processed event lists, images, and exposure maps can be downloaded if they are available. X-ray observations are perfectly suited to serendipitous discoveries and archival analyses, and with a decade-long `X-ray desert' potentially on the horizon archival data will take on even greater importance; enhanced access to those archives will be vital to the continuation of X-ray astronomy.

astro-ph.IM↗

arXiv2024

A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation

Training diffusion models for audiovisual sequences allows for a range of generation tasks by learning conditional distributions of various input-output combinations of the two modalities. Nevertheless, this strategy often requires training a separate model for each task which is expensive. Here, we propose a novel training approach to effectively learn arbitrary conditional distributions in the audiovisual space.Our key contribution lies in how we parameterize the diffusion timestep in the forward diffusion process. Instead of the standard fixed diffusion timestep, we propose applying variable diffusion timesteps across the temporal dimension and across modalities of the inputs. This formulation offers flexibility to introduce variable noise levels for various portions of the input, hence the term mixture of noise levels. We propose a transformer-based audiovisual latent diffusion model and show that it can be trained in a task-agnostic fashion using our approach to enable a variety of audiovisual generation tasks at inference time. Experiments demonstrate the versatility of our method in tackling cross-modal and multimodal interpolation tasks in the audiovisual space. Notably, our proposed approach surpasses baselines in generating temporally and perceptually consistent samples conditioned on the input. Project page: avdit2024.github.io

cs.CV↗

arXiv2024

Densify & Conquer: Densified, smaller base-stations can conquer the increasing carbon footprint problem in nextG wireless

Connectivity on-the-go has been one of the most impressive technological achievements in the 2010s decade. However, multiple studies show that this has come at an expense of increased carbon footprint, that also rivals the entire aviation sector's carbon footprint. The two major contributors of this increased footprint are (a) smartphone batteries which affect the embodied footprint and (b) base-stations that occupy ever-increasing energy footprint to provide the last mile wireless connectivity to smartphones. The root-cause of both these turn out to be the same, which is communicating over the last-mile lossy wireless medium. We show in this paper, titled DensQuer, how base-station densification, which is to replace a single larger base-station with multiple smaller ones, reduces the effect of the last-mile wireless, and in effect conquers both these adverse sources of increased carbon footprint. Backed by a open-source ray-tracing computation framework (Sionna), we show how a strategic densification strategy can minimize the number of required smaller base-stations to practically achievable numbers, which lead to about 3x power-savings in the base-station network. Also, DensQuer is able to also reduce the required deployment height of base-stations to as low as 15m, that makes the smaller cells easily deployable on trees/street poles instead of requiring a dedicated tower. Further, by utilizing newly introduced hardware power rails in Google Pixel 7a and above phones, we also show that this strategic densified network leads to reduction in mobile transmit power by 10-15 dB, leading to about 3x reduction in total cellular power consumption, and about 50% increase in smartphone battery life when it communicates data via the cellular network.

cs.NI↗

arXiv2023

VideoPoet: A Large Language Model for Zero-Shot Video Generation

We present VideoPoet, a language model capable of synthesizing high-quality video, with matching audio, from a large variety of conditioning signals. VideoPoet employs a decoder-only transformer architecture that processes multimodal inputs -- including images, videos, text, and audio. The training protocol follows that of Large Language Models (LLMs), consisting of two stages: pretraining and task-specific adaptation. During pretraining, VideoPoet incorporates a mixture of multimodal generative objectives within an autoregressive Transformer framework. The pretrained LLM serves as a foundation that can be adapted for a range of video generation tasks. We present empirical results demonstrating the model's state-of-the-art capabilities in zero-shot video generation, specifically highlighting VideoPoet's ability to generate high-fidelity motions. Project page: http://sites.research.google/videopoet/

cs.CV↗

arXiv2023

Photorealistic Video Generation with Diffusion Models

We present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encoder to jointly compress images and videos within a unified latent space, enabling training and generation across modalities. Second, for memory and training efficiency, we use a window attention architecture tailored for joint spatial and spatiotemporal generative modeling. Taken together these design decisions enable us to achieve state-of-the-art performance on established video (UCF-101 and Kinetics-600) and image (ImageNet) generation benchmarks without using classifier free guidance. Finally, we also train a cascade of three models for the task of text-to-video generation consisting of a base latent video diffusion model, and two video super-resolution diffusion models to generate videos of $512 \times 896$ resolution at $8$ frames per second.

cs.CV↗

arXiv2023

Holistic Evaluation of Text-To-Image Models

The stunning qualitative improvement of recent text-to-image models has led to their widespread attention and adoption. However, we lack a comprehensive quantitative understanding of their capabilities and risks. To fill this gap, we introduce a new benchmark, Holistic Evaluation of Text-to-Image Models (HEIM). Whereas previous evaluations focus mostly on text-image alignment and image quality, we identify 12 aspects, including text-image alignment, image quality, aesthetics, originality, reasoning, knowledge, bias, toxicity, fairness, robustness, multilinguality, and efficiency. We curate 62 scenarios encompassing these aspects and evaluate 26 state-of-the-art text-to-image models on this benchmark. Our results reveal that no single model excels in all aspects, with different models demonstrating different strengths. We release the generated images and human evaluation results for full transparency at https://crfm.stanford.edu/heim/v1.1.0 and the code at https://github.com/stanford-crfm/helm, which is integrated with the HELM codebase.

cs.CV↗

arXiv2023

Open X-Embodiment: Robotic Learning Datasets and RT-X Models

Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train generalist X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. More details can be found on the project website https://robotics-transformer-x.github.io.

cs.RO↗

arXiv2023

Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation

While Large Language Models (LLMs) are the dominant models for generative tasks in language, they do not perform as well as diffusion models on image and video generation. To effectively use LLMs for visual generation, one crucial component is the visual tokenizer that maps pixel-space inputs to discrete tokens appropriate for LLM learning. In this paper, we introduce MAGVIT-v2, a video tokenizer designed to generate concise and expressive tokens for both videos and images using a common token vocabulary. Equipped with this new tokenizer, we show that LLMs outperform diffusion models on standard image and video generation benchmarks including ImageNet and Kinetics. In addition, we demonstrate that our tokenizer surpasses the previously top-performing video tokenizer on two more tasks: (1) video compression comparable to the next-generation video codec (VCC) according to human evaluations, and (2) learning effective representations for action recognition tasks.

cs.CV↗

arXiv2023

RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation

The ability to leverage heterogeneous robotic experience from different robots and tasks to quickly master novel skills and embodiments has the potential to transform robot learning. Inspired by recent advances in foundation models for vision and language, we propose a multi-embodiment, multi-task generalist agent for robotic manipulation. This agent, named RoboCat, is a visual goal-conditioned decision transformer capable of consuming action-labelled visual experience. This data spans a large repertoire of motor control skills from simulated and real robotic arms with varying sets of observations and actions. With RoboCat, we demonstrate the ability to generalise to new tasks and robots, both zero-shot as well as through adaptation using only 100-1000 examples for the target task. We also show how a trained model itself can be used to generate data for subsequent training iterations, thus providing a basic building block for an autonomous improvement loop. We investigate the agent's capabilities, with large-scale evaluations both in simulation and on three different real robot embodiments. We find that as we grow and diversify its training data, RoboCat not only shows signs of cross-task transfer, but also becomes more efficient at adapting to new tasks.

cs.RO↗

arXiv2023

Siamese Masked Autoencoders

Establishing correspondence between images or scenes is a significant challenge in computer vision, especially given occlusions, viewpoint changes, and varying object appearances. In this paper, we present Siamese Masked Autoencoders (SiamMAE), a simple extension of Masked Autoencoders (MAE) for learning visual correspondence from videos. SiamMAE operates on pairs of randomly sampled video frames and asymmetrically masks them. These frames are processed independently by an encoder network, and a decoder composed of a sequence of cross-attention layers is tasked with predicting the missing patches in the future frame. By masking a large fraction ($95\%$) of patches in the future frame while leaving the past frame unchanged, SiamMAE encourages the network to focus on object motion and learn object-centric representations. Despite its conceptual simplicity, features learned via SiamMAE outperform state-of-the-art self-supervised methods on video object segmentation, pose keypoint propagation, and semantic part propagation tasks. SiamMAE achieves competitive results without relying on data augmentation, handcrafted tracking-based pretext tasks, or other techniques to prevent representational collapse.

cs.CV↗

arXiv2022

GreenMO: Virtualized User-proportionate MIMO

With the turn of new decade, wireless communications face a major challenge on connecting many more new users and devices, at the same time being energy efficient and minimizing its carbon footprint. However, the current approaches to address the growing number of users and spectrum demands, like traditional fully digital architectures for Massive MIMO, demand exorbitant energy consumption. The reason is that traditionally MIMO requires a separate RF chain per antenna, so the power consumption scales with number of antennas, instead of number of users, hence becomes energy inefficient. Instead, GreenMO creates a new massive MIMO architecture which is able to use many more antennas while keeping power consumption to user-proportionate numbers. To achieve this GreenMO introduces for the first time, the concept of virtualization of the RF chain hardware. Instead of laying the RF chains physically to each antenna, GreenMO creates these RF chains virtually in digital domain. This also enables GreenMO to be the first flexible massive MIMO architecture. Since GreenMO's virtual RF chains are created on the fly digitally, it can tune the number of these virtual chains according to the user load, hence always flexibly consume user-proportionate power. Thus, GreenMO paves the way for green and flexible massive MIMO. We prototype GreenMO on a PCB with eight antennas and evaluate it with a WARPv3 SDR platform in an office environment. The results demonstrate that GreenMO is 3x more power-efficient than traditional Massive MIMO and 4x more spectrum-efficient than traditional OFDMA systems, while multiplexing 4 users, and can save upto 40% power in modern 5G NR base stations.

eess.SP↗

arXiv2022

VIMA: General Robot Manipulation with Multimodal Prompts

Prompt-based learning has emerged as a successful paradigm in natural language processing, where a single general-purpose language model can be instructed to perform any task specified by input prompts. Yet task specification in robotics comes in various forms, such as imitating one-shot demonstrations, following language instructions, and reaching visual goals. They are often considered different tasks and tackled by specialized models. We show that a wide spectrum of robot manipulation tasks can be expressed with multimodal prompts, interleaving textual and visual tokens. Accordingly, we develop a new simulation benchmark that consists of thousands of procedurally-generated tabletop tasks with multimodal prompts, 600K+ expert trajectories for imitation learning, and a four-level evaluation protocol for systematic generalization. We design a transformer-based robot agent, VIMA, that processes these prompts and outputs motor actions autoregressively. VIMA features a recipe that achieves strong model scalability and data efficiency. It outperforms alternative designs in the hardest zero-shot generalization setting by up to $2.9\times$ task success rate given the same training data. With $10\times$ less training data, VIMA still performs $2.7\times$ better than the best competing variant. Code and video demos are available at https://vimalabs.github.io/

cs.RO↗