Apratim Bhattacharyya

Sanjay Haresh, Daniel Dijkman, Apratim Bhattacharyya et al.

Many dexterous manipulation tasks are non-markovian in nature, yet little attention has been paid to this fact in the recent upsurge of the vision-language-action (VLA) paradigm. Although they are successful in bringing internet-scale semantic understanding to robotics, existing VLAs are primarily "stateless" and struggle with memory-dependent long horizon tasks. In this work, we explore a way to impart both spatial and temporal memory to a VLA by incorporating a language scratchpad. The scratchpad makes it possible to memorize task-specific information, such as object positions, and it allows the model to keep track of a plan and progress towards subgoals within that plan. We evaluate this approach on a split of memory-dependent tasks from the ClevrSkills environment, on MemoryBench, as well as on a challenging real-world pick-and-place task. We show that incorporating a language scratchpad significantly improves generalization on these tasks for both non-recurrent and recurrent models.

Niklas Hanselmann, Katrin Renz, Kashyap Chitta et al.

Simulators offer the possibility of safe, low-cost development of self-driving systems. However, current driving simulators exhibit naïve behavior models for background traffic. Hand-tuned scenarios are typically added during simulation to induce safety-critical situations. An alternative approach is to adversarially perturb the background traffic trajectories. In this paper, we study this approach to safety-critical driving scenario generation using the CARLA simulator. We use a kinematic bicycle model as a proxy to the simulator's true dynamics and observe that gradients through this proxy model are sufficient for optimizing the background traffic trajectories. Based on this finding, we propose KING, which generates safety-critical driving scenarios with a 20% higher success rate than black-box optimization. By solving the scenarios generated by KING using a privileged rule-based expert algorithm, we obtain training data for an imitation learning policy. After fine-tuning on this new data, we show that the policy becomes better at avoiding collisions. Importantly, our generated data leads to reduced collisions on both held-out scenarios generated via KING as well as traditional hand-crafted scenarios, demonstrating improved robustness.

Reza Pourreza, Apratim Bhattacharyya, Sunny Panchal et al.

Large language models (LLMs) have made tremendous progress in natural language understanding and they have also been successfully adopted in other domains such as computer vision, robotics, reinforcement learning, etc. In this work, we apply LLMs to image generation tasks by directly generating the virtual brush strokes to paint an image. We present Painter, an LLM that can convert user prompts in text description format to sketches by generating the corresponding brush strokes in an auto-regressive way. We construct Painter based on off-the-shelf LLM that is pre-trained on a large text corpus, by fine-tuning it on the new task while preserving language understanding capabilities. We create a dataset of diverse multi-object sketches paired with textual prompts that covers several object types and tasks. Painter can generate sketches from text descriptions, remove objects from canvas, and detect and classify objects in sketches. Although this is an unprecedented pioneering work in using LLMs for auto-regressive image generation, the results are very encouraging.

Apratim Bhattacharyya, Sunny Panchal, Mingu Lee et al.

Multi-modal language models (LM) have recently shown promising performance in high-level reasoning tasks on videos. However, existing methods still fall short in tasks like causal or compositional spatiotemporal reasoning over actions, in which model predictions need to be grounded in fine-grained low-level details, such as object motions and object interactions. In this work, we propose training an LM end-to-end on low-level surrogate tasks, including object detection, re-identification, and tracking, to endow the model with the required low-level visual capabilities. We show that a two-stream video encoder with spatiotemporal attention is effective at capturing the required static and motion-based cues in the video. By leveraging the LM's ability to perform the low-level surrogate tasks, we can cast reasoning in videos as the three-step process of Look, Remember, Reason wherein visual information is extracted using low-level visual skills step-by-step and then integrated to arrive at a final answer. We demonstrate the effectiveness of our framework on diverse visual reasoning tasks from the ACRE, CATER, Something-Else and STAR datasets. Our approach is trainable end-to-end and surpasses state-of-the-art task-specific methods across these tasks by a large margin.

Sunny Panchal, Apratim Bhattacharyya, Guillaume Berger et al.

Vision-language models have shown impressive progress in recent years. However, existing models are largely limited to turn-based interactions, where each turn must be stepped (i.e., prompted) by the user. Open-ended, asynchronous interactions, where an AI model may proactively deliver timely responses or feedback based on the unfolding situation in real-time, are an open challenge. In this work, we present the QEVD benchmark and dataset, which explores human-AI interaction in the challenging, yet controlled, real-world domain of fitness coaching -- a task which intrinsically requires monitoring live user activity and providing immediate feedback. The benchmark requires vision-language models to recognize complex human actions, identify possible mistakes, and provide appropriate feedback in real-time. Our experiments reveal the limitations of existing state-of-the-art vision-language models for such asynchronous situated interactions. Motivated by this, we propose a simple end-to-end streaming baseline that can respond asynchronously to human actions with appropriate feedback at the appropriate time.

Rajeev Yasarla, Deepti Hegde, Shizhong Han et al.

Vision-Language-Action (VLA) models are emerging as highly effective planning models for end-to-end autonomous driving systems. However, current works mostly rely on imitation learning from sparse trajectory annotations and under-utilize their potential as generative models. We propose Generative Scenario Rollouts (GeRo), a plug-and-play framework for VLA models that jointly performs planning and generation of language-grounded future traffic scenes through an autoregressive rollout strategy. First, a VLA model is trained to encode ego vehicle and agent dynamics into latent tokens under supervision from planning, motion, and language tasks, facilitating text-aligned generation. Next, GeRo performs language-conditioned autoregressive generation. Given multi-view images, a scenario description, and ego-action questions, it generates future latent tokens and textual responses to guide long-horizon rollouts. A rollout-consistency loss stabilizes predictions using ground truth or pseudo-labels, mitigating drift and preserving text-action alignment. This design enables GeRo to perform temporally consistent, language-grounded rollouts that support long-horizon reasoning and multi-agent planning. On Bench2Drive, GeRo improves driving score and success rate by +15.7 and +26.2, respectively. By integrating reinforcement learning with generative rollouts, GeRo achieves state-of-the-art closed-loop and open-loop performance, demonstrating strong zero-shot robustness. These results highlight the promise of generative, language-conditioned reasoning as a foundation for safer and more interpretable end-to-end autonomous driving.

Deepti Hegde, Rajeev Yasarla, Hong Cai et al.

Autonomous driving demands safe motion planning, especially in critical "long-tail" scenarios. Recent end-to-end autonomous driving systems leverage large language models (LLMs) as planners to improve generalizability to rare events. However, using LLMs at test time introduces high computational costs. To address this, we propose DiMA, an end-to-end autonomous driving system that maintains the efficiency of an LLM-free (or vision-based) planner while leveraging the world knowledge of an LLM. DiMA distills the information from a multi-modal LLM to a vision-based end-to-end planner through a set of specially designed surrogate tasks. Under a joint training strategy, a scene encoder common to both networks produces structured representations that are semantically grounded as well as aligned to the final planning objective. Notably, the LLM is optional at inference, enabling robust planning without compromising on efficiency. Training with DiMA results in a 37% reduction in the L2 trajectory error and an 80% reduction in the collision rate of the vision-based planner, as well as a 44% trajectory error reduction in longtail scenarios. DiMA also achieves state-of-the-art performance on the nuScenes planning benchmark.

Litian Liu, Reza Pourreza, Sunny Panchal et al.

Large Language Models (LLMs) are prone to generating plausible yet incorrect responses, known as hallucinations. Effectively detecting hallucinations is therefore crucial for the safe deployment of LLMs. Recent research has linked hallucinations to model uncertainty, suggesting that hallucinations can be detected by measuring dispersion over answer distributions obtained from a set of samples drawn from a model. While drawing from the distribution over tokens defined by the model is a natural way to obtain samples, in this work, we argue that it is sub-optimal for the purpose of detecting hallucinations. We show that detection can be improved significantly by taking into account model uncertainty in the Bayesian sense. To this end, we propose a very simple and efficient approach that perturbs an appropriate subset of model parameters, or equivalently hidden unit activations, during sampling. We demonstrate its effectiveness across a wide range of datasets and model architectures.

Sanjay Haresh, Daniel Dijkman, Apratim Bhattacharyya et al.

Robotics tasks are highly compositional by nature. For example, to perform a high-level task like cleaning the table a robot must employ low-level capabilities of moving the effectors to the objects on the table, pick them up and then move them off the table one-by-one, while re-evaluating the consequently dynamic scenario in the process. Given that large vision language models (VLMs) have shown progress on many tasks that require high level, human-like reasoning, we ask the question: if the models are taught the requisite low-level capabilities, can they compose them in novel ways to achieve interesting high-level tasks like cleaning the table without having to be explicitly taught so? To this end, we present ClevrSkills - a benchmark suite for compositional reasoning in robotics. ClevrSkills is an environment suite developed on top of the ManiSkill2 simulator and an accompanying dataset. The dataset contains trajectories generated on a range of robotics tasks with language and visual annotations as well as multi-modal prompts as task specification. The suite includes a curriculum of tasks with three levels of compositional understanding, starting with simple tasks requiring basic motor skills. We benchmark multiple different VLM baselines on ClevrSkills and show that even after being pre-trained on large numbers of tasks, these models fail on compositional reasoning in robotics tasks.

Rajeev Yasarla, Shizhong Han, Hsin-Pai Cheng et al.

End-to-end (E2E) autonomous driving has recently emerged as a new paradigm, offering significant potential. However, few studies have looked into the practical challenge of deployment across domains (e.g., cities). Although several works have incorporated Large Language Models (LLMs) to leverage their open-world knowledge, LLMs do not guarantee cross-domain driving performance and may incur prohibitive retraining costs during domain adaptation. In this paper, we propose RoCA, a novel framework for robust cross-domain E2E autonomous driving. RoCA formulates the joint probabilistic distribution over the tokens that encode ego and surrounding vehicle information in the E2E pipeline. Instantiating with a Gaussian process (GP), RoCA learns a set of basis tokens with corresponding trajectories, which span diverse driving scenarios. Then, given any driving scene, it is able to probabilistically infer the future trajectory. By using RoCA together with a base E2E model in source-domain training, we improve the generalizability of the base model, without requiring extra inference computation. In addition, RoCA enables robust adaptation on new target domains, significantly outperforming direct finetuning. We extensively evaluate RoCA on various cross-domain scenarios and show that it achieves strong domain generalization and adaptation performance.

Apratim Bhattacharyya, Bicheng Xu, Sanjay Haresh et al.

Multi-modal Large Language Models (LLM) have advanced conversational abilities but struggle with providing live, interactive step-by-step guidance, a key capability for future AI assistants. Effective guidance requires not only delivering instructions but also detecting their successful execution, as well as identifying and alerting users to mistakes, all of which has to happen in real-time. This requires models that are not turn-based, but that can react asynchronously to a video stream, as well as video data showing users performing tasks including mistakes and their corrections. To this end, we introduce Qualcomm Interactive Cooking, a new benchmark and dataset built upon CaptainCook4D, which contains user mistakes during task execution. Our dataset and benchmark features densely annotated, timed instructions and feedback messages, specifically including mistake alerts precisely timestamped to their visual occurrence in the video. We evaluate state-of-the-art multi-modal LLMs on the Qualcomm Interactive Cooking benchmark and introduce LiveMamba, a streaming multi-modal LLM designed for interactive instructional guidance. This work provides the first dedicated benchmark and a strong baseline for developing and evaluating on live, situated coaching.

Reza Pourreza, Rishit Dagli, Apratim Bhattacharyya et al.

AI models have made significant strides in recent years in their ability to describe and answer questions about real-world images. They have also made progress in the ability to converse with users in real-time using audio input. This raises the question: have we reached the point where AI models, connected to a camera and microphone, can converse with users in real-time about scenes and events that are unfolding live in front of the camera? This has been a long-standing goal in AI and is a prerequisite for real-world AI assistants and humanoid robots to interact with humans in everyday situations. In this work, we introduce a new dataset and benchmark, the Qualcomm Interactive Video Dataset (IVD), which allows us to assess the extent to which existing models can support these abilities, and to what degree these capabilities can be instilled through fine-tuning. The dataset is based on a simple question-answering setup, where users ask questions that the system has to answer, in real-time, based on the camera and audio input. We show that existing models fall far behind human performance on this task, and we identify the main sources for the performance gap. However, we also show that for many of the required perceptual skills, fine-tuning on this form of data can significantly reduce this gap.

Apratim Bhattacharyya, Daniel Olmeda Reino, Mario Fritz et al.

Accurate prediction of pedestrian and bicyclist paths is integral to the development of reliable autonomous vehicles in dense urban environments. The interactions between vehicle and pedestrian or bicyclist have a significant impact on the trajectories of traffic participants e.g. stopping or turning to avoid collisions. Although recent datasets and trajectory prediction approaches have fostered the development of autonomous vehicles yet the amount of vehicle-pedestrian (bicyclist) interactions modeled are sparse. In this work, we propose Euro-PVI, a dataset of pedestrian and bicyclist trajectories. In particular, our dataset caters more diverse and complex interactions in dense urban scenarios compared to the existing datasets. To address the challenges in predicting future trajectories with dense interactions, we develop a joint inference model that learns an expressive multi-modal shared latent space across agents in the urban scene. This enables our Joint-$β$-cVAE approach to better model the distribution of future trajectories. We achieve state of the art results on the nuScenes and Euro-PVI datasets demonstrating the importance of capturing interactions between ego-vehicle and pedestrians (bicyclists) for accurate predictions.

Apratim Bhattacharyya, Christoph-Nikolas Straehle, Mario Fritz et al.

Prediction of trajectories such as that of pedestrians is crucial to the performance of autonomous agents. While previous works have leveraged conditional generative models like GANs and VAEs for learning the likely future trajectories, accurately modeling the dependency structure of these multimodal distributions, particularly over long time horizons remains challenging. Normalizing flow based generative models can model complex distributions admitting exact inference. These include variants with split coupling invertible transformations that are easier to parallelize compared to their autoregressive counterparts. To this end, we introduce a novel Haar wavelet based block autoregressive model leveraging split couplings, conditioned on coarse trajectories obtained from Haar wavelet based transformations at different levels of granularity. This yields an exact inference method that models trajectories at different spatio-temporal resolutions in a hierarchical manner. We illustrate the advantages of our approach for generating diverse and accurate trajectories on two real-world datasets - Stanford Drone and Intersection Drone.

Shweta Mahajan, Apratim Bhattacharyya, Mario Fritz et al.

Flow-based generative models are an important class of exact inference models that admit efficient inference and sampling for image synthesis. Owing to the efficiency constraints on the design of the flow layers, e.g. split coupling flow layers in which approximately half the pixels do not undergo further transformations, they have limited expressiveness for modeling long-range data dependencies compared to autoregressive models that rely on conditional pixel-wise generation. In this work, we improve the representational power of flow-based models by introducing channel-wise dependencies in their latent space through multi-scale autoregressive priors (mAR). Our mAR prior for models with split coupling flow layers (mAR-SCF) can better capture dependencies in complex multimodal data. The resulting model achieves state-of-the-art density estimation results on MNIST, CIFAR-10, and ImageNet. Furthermore, we show that mAR-SCF allows for improved image generation quality, with gains in FID and Inception scores compared to state-of-the-art flow-based models.

Apratim Bhattacharyya, Mario Fritz, Bernt Schiele

Generative Adversarial Networks (GANs) can achieve state-of-the-art sample quality in generative modelling tasks but suffer from the mode collapse problem. Variational Autoencoders (VAE) on the other hand explicitly maximize a reconstruction-based data log-likelihood forcing it to cover all modes, but suffer from poorer sample quality. Recent works have proposed hybrid VAE-GAN frameworks which integrate a GAN-based synthetic likelihood to the VAE objective to address both the mode collapse and sample quality issues, with limited success. This is because the VAE objective forces a trade-off between the data log-likelihood and divergence to the latent prior. The synthetic likelihood ratio term also shows instability during training. We propose a novel objective with a "Best-of-Many-Samples" reconstruction cost and a stable direct estimate of the synthetic likelihood. This enables our hybrid VAE-GAN framework to achieve high data log-likelihood and low divergence to the latent prior at the same time and shows significant improvement over both hybrid VAE-GANS and plain GANs in mode coverage and quality.

Apratim Bhattacharyya, Michael Hanselmann, Mario Fritz et al.

Prediction of future states of the environment and interacting agents is a key competence required for autonomous agents to operate successfully in the real world. Prior work for structured sequence prediction based on latent variable models imposes a uni-modal standard Gaussian prior on the latent variables. This induces a strong model bias which makes it challenging to fully capture the multi-modality of the distribution of the future states. In this work, we introduce Conditional Flow Variational Autoencoders (CF-VAE) using our novel conditional normalizing flow based prior to capture complex multi-modal conditional distributions for effective structured sequence prediction. Moreover, we propose two novel regularization schemes which stabilizes training and deals with posterior collapse for stable training and better fit to the target data distribution. Our experiments on three multi-modal structured sequence prediction datasets -- MNIST Sequences, Stanford Drone and HighD -- show that the proposed method obtains state of art results across different evaluation metrics.

Hossein Hajipour, Apratim Bhattacharyya, Cristian-Alexandru Staicu et al.

Automatic program repair holds the potential of dramatically improving the productivity of programmers during the software development process and correctness of software in general. Recent advances in machine learning, deep learning, and NLP have rekindled the hope to eventually fully automate the process of repairing programs. However, previous approaches that aim to predict a single fix are prone to fail due to uncertainty about the true intend of the programmer. Therefore, we propose a generative model that learns a distribution over potential fixes. Our model is formulated as a deep conditional variational autoencoder that can efficiently sample fixes for a given erroneous program. In order to ensure diverse solutions, we propose a novel regularizer that encourages diversity over a semantic embedding space. Our evaluations on common programming errors show for the first time the generation of diverse fixes and strong improvements over the state-of-the-art approaches by fixing up to 45% of the erroneous programs. We additionally show that for the 65% of the repaired programs, our approach was able to generate multiple programs with diverse functionalities.

Apratim Bhattacharyya, Mario Fritz, Bernt Schiele

For autonomous agents to successfully operate in the real world, the ability to anticipate future scene states is a key competence. In real-world scenarios, future states become increasingly uncertain and multi-modal, particularly on long time horizons. Dropout based Bayesian inference provides a computationally tractable, theoretically well grounded approach to learn likely hypotheses/models to deal with uncertain futures and make predictions that correspond well to observations -- are well calibrated. However, it turns out that such approaches fall short to capture complex real-world scenes, even falling behind in accuracy when compared to the plain deterministic approaches. This is because the used log-likelihood estimate discourages diversity. In this work, we propose a novel Bayesian formulation for anticipating future scene states which leverages synthetic likelihoods that encourage the learning of diverse models to accurately capture the multi-modal nature of future scene states. We show that our approach achieves accurate state-of-the-art predictions and calibrated probabilities through extensive experiments for scene anticipation on Cityscapes dataset. Moreover, we show that our approach generalizes across diverse tasks such as digit generation and precipitation forecasting.

Apratim Bhattacharyya, Bernt Schiele, Mario Fritz

For autonomous agents to successfully operate in the real world, anticipation of future events and states of their environment is a key competence. This problem has been formalized as a sequence extrapolation problem, where a number of observations are used to predict the sequence into the future. Real-world scenarios demand a model of uncertainty of such predictions, as predictions become increasingly uncertain -- in particular on long time horizons. While impressive results have been shown on point estimates, scenarios that induce multi-modal distributions over future sequences remain challenging. Our work addresses these challenges in a Gaussian Latent Variable model for sequence prediction. Our core contribution is a "Best of Many" sample objective that leads to more accurate and more diverse predictions that better capture the true variations in real-world sequence data. Beyond our analysis of improved model fit, our models also empirically outperform prior work on three diverse tasks ranging from traffic scenes to weather data.

Apratim Bhattacharyya, Mario Fritz, Bernt Schiele

For autonomous agents to successfully operate in the real world, anticipation of future events and states of their environment is a key competence. This problem can be formalized as a sequence prediction problem, where a number of observations are used to predict the sequence into the future. However, real-world scenarios demand a model of uncertainty of such predictions, as future states become increasingly uncertain and multi-modal -- in particular on long time horizons. This makes modelling and learning challenging. We cast state of the art semantic segmentation and future prediction models based on deep learning into a Bayesian formulation that in turn allows for a full Bayesian treatment of the prediction problem. We present a new sampling scheme for this model that draws from the success of variational autoencoders by incorporating a recognition network. In the experiments we show that our model outperforms prior work in accuracy of the predicted segmentation and provides calibrated probabilities that also better capture the multi-modal aspects of possible future states of street scenes.

Apratim Bhattacharyya, Mario Fritz, Bernt Schiele

Progress towards advanced systems for assisted and autonomous driving is leveraging recent advances in recognition and segmentation methods. Yet, we are still facing challenges in bringing reliable driving to inner cities, as those are composed of highly dynamic scenes observed from a moving platform at considerable speeds. Anticipation becomes a key element in order to react timely and prevent accidents. In this paper we argue that it is necessary to predict at least 1 second and we thus propose a new model that jointly predicts ego motion and people trajectories over such large time horizons. We pay particular attention to modeling the uncertainty of our estimates arising from the non-deterministic nature of natural traffic scenes. Our experimental results show that it is indeed possible to predict people trajectories at the desired time horizons and that our uncertainty estimates are informative of the prediction error. We also show that both sequence modeling of trajectories as well as our novel method of long term odometry prediction are essential for best performance.

Apratim Bhattacharyya, Jilles Vreeken

Discovering the key structure of a database is one of the main goals of data mining. In pattern set mining we do so by discovering a small set of patterns that together describe the data well. The richer the class of patterns we consider, and the more powerful our description language, the better we will be able to summarise the data. In this paper we propose \ourmethod, a novel greedy MDL-based method for summarising sequential data using rich patterns that are allowed to interleave. Experiments show \ourmethod is orders of magnitude faster than the state of the art, results in better models, as well as discovers meaningful semantics in the form patterns that identify multiple choices of values.

Apratim Bhattacharyya, Mateusz Malinowski, Bernt Schiele et al.

Boundary estimation in images and videos has been a very active topic of research, and organizing visual information into boundaries and segments is believed to be a corner stone of visual perception. While prior work has focused on estimating boundaries for observed frames, our work aims at predicting boundaries of future unobserved frames. This requires our model to learn about the fate of boundaries and corresponding motion patterns -- including a notion of "intuitive physics". We experiment on natural video sequences along with synthetic sequences with deterministic physics-based and agent-based motions. While not being our primary goal, we also show that fusion of RGB and boundary prediction leads to improved RGB predictions.

Apratim Bhattacharyya, Mateusz Malinowski, Mario Fritz

Boundary prediction in images as well as video has been a very active topic of research and organizing visual information into boundaries and segments is believed to be a corner stone of visual perception. While prior work has focused on predicting boundaries for observed frames, our work aims at predicting boundaries of future unobserved frames. This requires our model to learn about the fate of boundaries and extrapolate motion patterns. We experiment on established real-world video segmentation dataset, which provides a testbed for this new task. We show for the first time spatio-temporal boundary extrapolation in this challenging scenario. Furthermore, we show long-term prediction of boundaries in situations where the motion is governed by the laws of physics. We successfully predict boundaries in a billiard scenario without any assumptions of a strong parametric model or any object notion. We argue that our model has with minimalistic model assumptions derived a notion of 'intuitive physics' that can be applied to novel scenes.