33 accepted papers
Although Reinforcement Learning with Verifiable Rewards (RLVR) has become an essential component for developing advanced reasoning skills in language models, contemporary studies have documented training plateaus that emerge following thousands of optimization steps, demonstrating notable decreases…
Recent advances in generative diffusion and flow-matching models have revolutionized molecular design, enabling the creation of novel proteins, small molecules, and RNA sequences with unprecedented fidelity. Yet, these models remain intuitive rather than intelligent—they generate without reasoning. …
Vision-Language Model (VLM) is now an important component to enable robust robot manipulation. Yet, using it to translate human instructions into an action-resolvable intermediate representation often needs a tradeoff between VLM-comprehensibility and generalizability. Inspired by context-free gramm
Search-augmented large language models (LLMs) trained with reinforcement learning (RL) have achieved strong results on open-domain question answering (QA), but training still remains a significant challenge. The optimization is often unstable due to sparse rewards and difficult credit assignments ac…
While a number of existing approaches for building foundation model agents rely on prompting or fine-tuning with human demonstrations, it is not sufficient in dynamic environments (e.g., mobile device control). On-policy reinforcement learning (RL) should address these limitations, but collecting ac…
A small subset of dimensions within language Transformers’ representation spaces emerge as “outliers” during pretraining, encoding critical knowledge sparsely. We extend previous findings on emergent outliers to Encoder-Decoder Transformers and instruction-finetuned models, and tackle the problem of…
A generalist foundation model agent needs to have a large and diverse skill repertoire, such as finding directions between two travel locations and buying specific items from the Internet. If each skill needs to be specified manually through a fixed set of human-annotated instructions, the agent’s s…
We aim to evaluate Large Language Models (LLMs) for embodied decision making. While a significant body of work has been leveraging LLMs for decision making in embodied environments, we still lack a systematic understanding of their performance because they are usually applied in different domains, f…
Most pre-trained learning systems are known to suffer from bias, which typically emerges from the data, the model, or both. Measuring and quantifying bias and its sources is a challenging task and has been extensively studied in image captioning. Despite the significant effort in this direction, we…
Reasoning from visual dynamics scenes has many real world applications. However existing video reasoning benchmarks are still inadequate since they were mainly designed for factual or situated reasoning and rarely involve broader knowledge in the real world. Our work aims to delve deeper into reason…
Large Language Models (LLMs) are increasingly used for generating code solutions, empowered by features like self-debugging and self-reflection. However, LLMs often struggle with complex programming problems without human guidance. This paper investigates the strategies employed by expert programmer…
"By combining natural language understanding, generation capabilities, and breadth of knowledge of large language models with image perception, recent large vision language models (LVLMs) have shown unprecedented visual reasoning capabilities. However, the generated text often suffers from inaccurat…
In recent years, increasing attention has been directed to leveraging pre-trained vision models for motor control. While existing works mainly emphasize the importance of this pre-training phase, the arguably equally important role played by downstream policy learning during control-specific fine-tu…
It is a long-standing problem in robotics to develop agents capable of executing diverse manipulation tasks from visual observations in unstructured real-world environments. To achieve this goal, the robot will need to have a comprehensive understanding of the 3D structure and semantics of the scen…
Designing robust text-to-image (T2I) models have been extensively explored in recent years, especially with the emergence of diffusion models, which achieves state-of-the-art results on T2I synthesis tasks. Despite the significant effort and success in this direction, we observed that the existing m…
Recent progress on vision-language foundation models have brought significant advancement to building general-purpose robots. By using the pre-trained models to encode the scene and instructions as inputs for decision making, the instruction-conditioned policy can generalize across different objects…
Reinforcement Learning (RL) methods are typically applied directly in environments to learn policies. In some complex environments with continuous state-action spaces, sparse rewards, and/or long temporal horizons, learning a good policy in the original environments can be difficult. Focusing on the…
Recent work has seen the development of general purpose neural architectures that can be trained to perform tasks across diverse data modalities. General purpose models typically make few assumptions about the underlying data-structure and are known to perform well in the large-data regime. At the s…
Pretraining on large unlabeled datasets has been proven to improve the down-stream task performance on many computer vision tasks, such as 2D object detection and video classification. However, for large-scale 3D scenes, such as outdoor LiDAR point clouds, pretraining is not widely used. Due to the…
Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply enlarging receptive field also gives rise to several concerns…
Feature learning for 3D object detection from point clouds is very challenging due to the irregularity of 3D point cloud data. In this paper, we propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features effectively. Specifically, a Local Transformer module is employe…
Controllable text generation concerns two fundamental tasks of wide applications, namely generating text of given attributes (i.e., attribute-conditional generation), and minimally editing existing text to possess desired attributes (i.e., text attribute transfer). Extensive prior work has largely s…
Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framework. However, only a few works have explored unsupervised disentangled sequentia…
Motion forecasting is essential for making intelligent decisions in robotic navigation. As a result, the multi-agent behavioral prediction has become a core component of modern human-robot interaction applications such as autonomous driving. Due to various intentions and interactions among agents, a…
Motion forecasting is essential for making safe and intelligent decisions in robotic applications such as autonomous driving. Existing methods often formulate it as a sequence-to-sequence prediction problem, solved in an encoder-decoder framework with a maximum likelihood estimation objective. State…
Image captioning systems are expected to have the ability to combine individual concepts when describing scenes with concept combinations that are not observed during training. In spite of significant progress in image captioning with the help of the autoregressive generation framework, current appr…
Vehicle detection with visual sensors like lidar and camera is one of the critical functions enabling autonomous driving. While they generate fine-grained point clouds or high-resolution images with rich information in good weather conditions, they fail in adverse weather (e.g., fog) where opaque pa…
Motion prediction of vehicles is critical but challenging due to the uncertainties in complex environments and the limited visibility caused by occlusions and limited sensor ranges. In this paper, we study a new task, safety-aware motion prediction with unseen vehicles for autonomous driving. Unlike…
Monocular 3D prediction is one of the fundamental problems in 3D vision. Recent deep learning-based approaches have brought us exciting progress on this problem. However, existing approaches have predominantly focused on end-to-end depth and normal predictions, which do not fully utilize the underly…
Spoken language understanding (SLU) is the task of inferring the semantics of spoken utterances. Traditionally, this has been achieved with a cascading combination of Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU) modules that are optimized separately, which can lead to…
We present Uncertainty-aware Cascaded Stereo Network (UCS-Net) for 3D reconstruction from multiple RGB images. Multi-view stereo (MVS) aims to reconstruct fine-grained scene geometry from multi-view images. Previous learning-based MVS methods estimate per-view depth using plane sweep volumes (PSVs)…
In the domain of autonomous driving, deep learning has substantially improved the 3D object detection accuracy for LiDAR and stereo camera data alike. While deep networks are great at generalization, they are also notorious to overfit to all kinds of spurious artifacts, such as brightness, car sizes…
Depth from a monocular video can enable billions of devices and robots with a single camera to see the world in 3D. In this paper, we present a model for video depth estimation, which consists of a flow-to-depth layer, a camera pose refinement module, and a depth fusion network. Given optical flow a…