Nakul Agarwal

Qi Zhao, Shijie Wang, Ce Zhang et al.

Can we better anticipate an actor's future actions (e.g. mix eggs) by knowing what commonly happens after his/her current action (e.g. crack eggs)? What if we also know the longer-term goal of the actor (e.g. making egg fried rice)? The long-term action anticipation (LTA) task aims to predict an actor's future behavior from video observations in the form of verb and noun sequences, and it is crucial for human-machine interaction. We propose to formulate the LTA task from two perspectives: a bottom-up approach that predicts the next actions autoregressively by modeling temporal dynamics; and a top-down approach that infers the goal of the actor and plans the needed procedure to accomplish the goal. We hypothesize that large language models (LLMs), which have been pretrained on procedure text data (e.g. recipes, how-tos), have the potential to help LTA from both perspectives. It can help provide the prior knowledge on the possible next actions, and infer the goal given the observed part of a procedure, respectively. To leverage the LLMs, we propose a two-stage framework, AntGPT. It first recognizes the actions already performed in the observed videos and then asks an LLM to predict the future actions via conditioned generation, or to infer the goal and plan the whole procedure by chain-of-thought prompting. Empirical results on the Ego4D LTA v1 and v2 benchmarks, EPIC-Kitchens-55, as well as EGTEA GAZE+ demonstrate the effectiveness of our proposed approach. AntGPT achieves state-of-the-art performance on all above benchmarks, and can successfully infer the goal and thus perform goal-conditioned "counterfactual" prediction via qualitative analysis. Code and model will be released at https://brown-palm.github.io/AntGPT

Enna Sachdeva, Nakul Agarwal, Suhas Chundi et al.

The widespread adoption of commercial autonomous vehicles (AVs) and advanced driver assistance systems (ADAS) may largely depend on their acceptance by society, for which their perceived trustworthiness and interpretability to riders are crucial. In general, this task is challenging because modern autonomous systems software relies heavily on black-box artificial intelligence models. Towards this goal, this paper introduces a novel dataset, Rank2Tell, a multi-modal ego-centric dataset for Ranking the importance level and Telling the reason for the importance. Using various close and open-ended visual question answering, the dataset provides dense annotations of various semantic, spatial, temporal, and relational attributes of various important objects in complex traffic scenarios. The dense annotations and unique attributes of the dataset make it a valuable resource for researchers working on visual scene understanding and related fields. Furthermore, we introduce a joint model for joint importance level ranking and natural language captions generation to benchmark our dataset and demonstrate performance with quantitative evaluations.

Joerg Deigmoeller, Nakul Agarwal, Stephan Hasler et al.

We introduce MERGE, a system for situational grounding of actors, objects, and events in dynamic human-robot group interactions. Effective collaboration in such settings requires consistent situational awareness, built on persistent representations of people and objects and an episodic abstraction of events. MERGE achieves this by uniquely identifying physical instances of actors (humans or robots) and objects and structuring them into actor-action-object relations, ensuring temporal consistency across interactions. Central to MERGE is the integration of Vision-Language Models (VLMs) guided with a perception pipeline: a lightweight streaming module continuously processes visual input to detect changes and selectively invokes the VLM only when necessary. This decoupled design preserves the reasoning power and zero-shot generalization of VLMs while improving efficiency, avoiding both the high monetary cost and the latency of frame-by-frame captioning that leads to fragmented and delayed outputs. To address the absence of suitable benchmarks for multi-actor collaboration, we introduce the GROUND dataset, which offers fine-grained situational annotations of multi-person and human-robot interactions. On this dataset, our approach improves the average grounding score by a factor of 2 compared to the performance of VLM-only baselines - including GPT-4o, GPT-5 and Gemini 2.5 Flash - while also reducing run-time by a factor of 4. The code and data are available at www.github.com/HRI-EU/merge.

Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal et al.

This paper addresses a new problem of weakly-supervised online action segmentation in instructional videos. We present a framework to segment streaming videos online at test time using Dynamic Programming and show its advantages over greedy sliding window approach. We improve our framework by introducing the Online-Offline Discrepancy Loss (OODL) to encourage the segmentation results to have a higher temporal consistency. Furthermore, only during training, we exploit frame-wise correspondence between multiple views as supervision for training weakly-labeled instructional videos. In particular, we investigate three different multi-view inference techniques to generate more accurate frame-wise pseudo ground-truth with no additional annotation cost. We present results and ablation studies on two benchmark multi-view datasets, Breakfast and IKEA ASM. Experimental results show efficacy of the proposed methods both qualitatively and quantitatively in two domains of cooking and assembly.

Shijie Wang, Qi Zhao, Minh Quan Do et al.

What makes good representations for video understanding, such as anticipating future activities, or answering video-conditioned questions? While earlier approaches focus on end-to-end learning directly from video pixels, we propose to revisit text-based representations, such as general-purpose video captions, which are interpretable and can be directly consumed by large language models (LLMs). Intuitively, different video understanding tasks may require representations that are complementary and at different granularity. To this end, we propose versatile action models (Vamos), a learning framework powered by a large language model as the ``reasoner'', and can flexibly leverage visual embedding and free-form text descriptions as its input. To interpret the important text evidence for question answering, we generalize the concept bottleneck model to work with tokens and nonlinear models, which uses hard attention to select a small subset of tokens from the free-form text as inputs to the LLM reasoner. We evaluate Vamos on five complementary benchmarks, Ego4D, NeXT-QA, IntentQA, Spacewalk-18, and EgoSchema, on its capability to model temporal dynamics, encode visual history, and perform reasoning. Surprisingly, we observe that text-based representations consistently achieve competitive performance on all benchmarks, and that visual embeddings provide marginal or no performance improvement, demonstrating the effectiveness of text-based video representation in the LLM era. We also demonstrate that our token bottleneck model is able to select relevant evidence from free-form text, support test-time intervention, and achieves nearly 5 times inference speedup while keeping a competitive question answering performance. Code and models are publicly released at https://brown-palm.github.io/Vamos/

Ce Zhang, Changcheng Fu, Shijie Wang et al.

This paper focuses on building object-centric representations for long-term action anticipation in videos. Our key motivation is that objects provide important cues to recognize and predict human-object interactions, especially when the predictions are longer term, as an observed "background" object could be used by the human actor in the future. We observe that existing object-based video recognition frameworks either assume the existence of in-domain supervised object detectors or follow a fully weakly-supervised pipeline to infer object locations from action labels. We propose to build object-centric video representations by leveraging visual-language pretrained models. This is achieved by "object prompts", an approach to extract task-specific object-centric representations from general-purpose pretrained models without finetuning. To recognize and predict human-object interactions, we use a Transformer-based neural architecture which allows the "retrieval" of relevant objects for action anticipation at various time scales. We conduct extensive evaluations on the Ego4D, 50Salads, and EGTEA Gaze+ benchmarks. Both quantitative and qualitative results confirm the effectiveness of our proposed method.

Seunggeun Chi, Hyung-gun Chi, Hengbo Ma et al.

We introduce the Multi-Motion Discrete Diffusion Models (M2D2M), a novel approach for human motion generation from textual descriptions of multiple actions, utilizing the strengths of discrete diffusion models. This approach adeptly addresses the challenge of generating multi-motion sequences, ensuring seamless transitions of motions and coherence across a series of actions. The strength of M2D2M lies in its dynamic transition probability within the discrete diffusion model, which adapts transition probabilities based on the proximity between motion tokens, encouraging mixing between different modes. Complemented by a two-phase sampling strategy that includes independent and joint denoising steps, M2D2M effectively generates long-term, smooth, and contextually coherent human motion sequences, utilizing a model trained for single-motion generation. Extensive experiments demonstrate that M2D2M surpasses current state-of-the-art benchmarks for motion generation from text descriptions, showcasing its efficacy in interpreting language semantics and generating dynamic, realistic motions.

Nakul Agarwal, Yi-Ting Chen, Behzad Dariush

Achieving zero-collision mobility remains a key objective for intelligent vehicle systems, which requires understanding driver risk perception-a complex cognitive process shaped by voluntary response of the driver to external stimuli and the attentiveness of surrounding road users towards the ego-vehicle. To support progress in this area, we introduce RAID (Risk Assessment In Driving scenes)-a large-scale dataset specifically curated for research on driver risk perception and contextual risk assessment. RAID comprises 4,691 annotated video clips, covering diverse traffic scenarios with labels for driver's intended maneuver, road topology, risk situations (e.g., crossing pedestrians), driver responses, and pedestrian attentiveness. Leveraging RAID, we propose a weakly supervised risk object identification framework that models the relationship between driver's intended maneuver and responses to identify potential risk sources. Additionally, we analyze the role of pedestrian attention in estimating risk and demonstrate the value of the proposed dataset. Experimental evaluations demonstrate that our method achieves 20.6% and 23.1% performance gains over prior state-of-the-art approaches on the RAID and HDDS datasets, respectively.

Shuozhe Li, Vaishnav Tadiparthi, Kwonjoon Lee et al.

Reinforcement learning from verifiable rewards (RLVR) produces strong reasoning models, yet they can fail catastrophically when the conditioning context is fallible (e.g., corrupted chain-of-thought, misleading partial solutions, or mild input perturbations), since standard RLVR optimizes final-answer correctness only under clean conditioning. We introduce GASP (Guided Adversarial Self-Play), a robustification method that explicitly trains detect-and-repair capabilities using only outcome verification. Without human labels or external teachers, GASP forms an adversarial self-play game within a single model: a polluter learns to induce failure via locally coherent corruptions, while an agent learns to diagnose and recover under the same corrupted conditioning. To address the scarcity of successful recoveries early in training, we propose in-distribution repair guidance, an imitation term on self-generated repairs that increases recovery probability while preserving previously acquired capabilities. Across four open-weight models (1.5B--8B), GASP transforms strong-but-brittle reasoners into robust ones that withstand misleading and perturbed context while often improving clean accuracy. Further analysis shows that adversarial corruptions induce an effective curriculum, and in-distribution guidance enables rapid recovery learning with minimal representational drift.

Olivier Jeunen, Jatin Mandav, Ivan Potapov et al.

Real-world recommender systems often need to balance multiple objectives when deciding which recommendations to present to users. These include behavioural signals (e.g. clicks, shares, dwell time), as well as broader objectives (e.g. diversity, fairness). Scalarisation methods are commonly used to handle this balancing task, where a weighted average of per-objective reward signals determines the final score used for ranking. Naturally, how these weights are computed exactly, is key to success for any online platform. We frame this as a decision-making task, where the scalarisation weights are actions taken to maximise an overall North Star reward (e.g. long-term user retention or growth). We extend existing policy learning methods to the continuous multivariate action domain, proposing to maximise a pessimistic lower bound on the North Star reward that the learnt policy will yield. Typical lower bounds based on normal approximations suffer from insufficient coverage, and we propose an efficient and effective policy-dependent correction for this. We provide guidance to design stochastic data collection policies, as well as highly sensitive reward signals. Empirical observations from simulations, offline and online experiments highlight the efficacy of our deployed approach.

Victoria M. Dax, Jiachen Li, Enna Sachdeva et al.

Effective interaction modeling and behavior prediction of dynamic agents play a significant role in interactive motion planning for autonomous robots. Although existing methods have improved prediction accuracy, few research efforts have been devoted to enhancing prediction model interpretability and out-of-distribution (OOD) generalizability. This work addresses these two challenging aspects by designing a variational auto-encoder framework that integrates graph-based representations and time-sequence models to efficiently capture spatio-temporal relations between interactive agents and predict their dynamics. Our model infers dynamic interaction graphs in a latent space augmented with interpretable edge features that characterize the interactions. Moreover, we aim to enhance model interpretability and performance in OOD scenarios by disentangling the latent space of edge features, thereby strengthening model versatility and robustness. We validate our approach through extensive experiments on both simulated and real-world datasets. The results show superior performance compared to existing methods in modeling spatio-temporal relations, motion prediction, and identifying time-invariant latent features.

Chunhui Zhang, Zhongyu Ouyang, Kwonjoon Lee et al. · mit

Theory-of-Mind (ToM) enables humans to infer mental states-such as beliefs, desires, and intentions-forming the foundation of social cognition. However, existing computational ToM methods rely on structured workflows with ToM-specific priors or deep model fine-tuning, which struggle with scalability in multimodal environments and fail to generalize as task complexity increases. To address these limitations, we propose a scalable Bayesian ToM planner that decomposes ToM reasoning into stepwise Bayesian updates. Our framework introduces weak-to-strong control, allowing smaller language models (LMs) to specialize in ToM-specific likelihood estimation and transfer their reasoning behaviors to larger LMs (7B to 405B) for integration with social and world knowledge. This synergistic approach aligns large-model inference of human mental states with Bayesian principles. Extensive experiments show that our method achieves a 4.6% accuracy improvement over state-of-the-art techniques on multimodal ToM benchmarks, including challenging unseen scenarios, thereby establishing a new standard for modeling human mental states in complex environments.

Joerg Deigmoeller, Stephan Hasler, Nakul Agarwal et al.

We introduce CARMA, a system for situational grounding in human-robot group interactions. Effective collaboration in such group settings requires situational awareness based on a consistent representation of present persons and objects coupled with an episodic abstraction of events regarding actors and manipulated objects. This calls for a clear and consistent assignment of instances, ensuring that robots correctly recognize and track actors, objects, and their interactions over time. To achieve this, CARMA uniquely identifies physical instances of such entities in the real world and organizes them into grounded triplets of actors, objects, and actions. To validate our approach, we conducted three experiments, where multiple humans and a robot interact: collaborative pouring, handovers, and sorting. These scenarios allow the assessment of the system's capabilities as to role distinction, multi-actor awareness, and consistent instance identification. Our experiments demonstrate that the system can reliably generate accurate actor-action-object triplets, providing a structured and robust foundation for applications requiring spatiotemporal reasoning and situated decision-making in collaborative settings.

Seth Z. Zhao, Reza Ghoddoosian, Isht Dwivedi et al.

Understanding human behavior is an important problem in the pursuit of visual intelligence. A challenge in this endeavor is the extensive and costly effort required to accurately label action segments. To address this issue, we consider learning methods that demand minimal supervision for segmentation of human actions in long instructional videos. Specifically, we introduce a weakly-supervised framework that uniquely incorporates pose knowledge during training while omitting its use during inference, thereby distilling pose knowledge pertinent to each action component. We propose a pose-inspired contrastive loss as a part of the whole weakly-supervised framework which is trained to distinguish action boundaries more effectively. Our approach, validated through extensive experiments on representative datasets, outperforms previous state-of-the-art (SOTA) in segmenting long instructional videos under both online and offline settings. Additionally, we demonstrate the framework's adaptability to various segmentation backbones and pose extractors across different datasets.

Reza Ghoddoosian, Nakul Agarwal, Isht Dwivedi et al.

Vision-language models (VLMs) are capable of recognizing unseen actions. However, existing VLMs lack intrinsic understanding of procedural action concepts. Hence, they overfit to fixed labels and are not invariant to unseen action synonyms. To address this, we propose a simple fine-tuning technique, Action Concept Enhancement (ACE), to improve the robustness and concept understanding of VLMs in procedural action classification. ACE continually incorporates augmented action synonyms and negatives in an auxiliary classification loss by stochastically replacing fixed labels during training. This creates new combinations of action labels over the course of fine-tuning and prevents overfitting to fixed action representations. We show the enhanced concept understanding of our VLM, by visualizing the alignment of encoded embeddings of unseen action synonyms in the embedding space. Our experiments on the ATA, IKEA and GTEA datasets demonstrate the efficacy of ACE in domains of cooking and assembly leading to significant improvements in zero-shot action classification while maintaining competitive performance on seen actions.

Nakul Agarwal, Yi-Ting Chen, Behzad Dariush et al.

Spatio-temporal action localization is an important problem in computer vision that involves detecting where and when activities occur, and therefore requires modeling of both spatial and temporal features. This problem is typically formulated in the context of supervised learning, where the learned classifiers operate on the premise that both training and test data are sampled from the same underlying distribution. However, this assumption does not hold when there is a significant domain shift, leading to poor generalization performance on the test data. To address this, we focus on the hard and novel task of generalizing training models to test samples without access to any labels from the latter for spatio-temporal action localization by proposing an end-to-end unsupervised domain adaptation algorithm. We extend the state-of-the-art object detection framework to localize and classify actions. In order to minimize the domain shift, three domain adaptation modules at image level (temporal and spatial) and instance level (temporal) are designed and integrated. We design a new experimental setup and evaluate the proposed method and different adaptation modules on the UCF-Sports, UCF-101 and JHMDB benchmark datasets. We show that significant performance gain can be achieved when spatial and temporal features are adapted separately, or jointly for the most effective results.

A. H. Abdul Hafez, Nakul Agarwal, C. V. Jawahar

We are motivated by the fact that multiple representations of the environment are required to stand for the changes in appearance with time and for changes that appear in a cyclic manner. These changes are, for example, from day to night time, and from day to day across seasons. In such situations, the robot visits the same routes multiple times and collects different appearances of it. Multiple visual experiences usually find robotic vision applications like visual localization, mapping, place recognition, and autonomous navigation. The novelty in this paper is an algorithm that connects multiple visual experiences via aligning multiple image sequences. This problem is solved by finding the maximum flow in a directed graph flow-network, whose vertices represent the matches between frames in the test and reference sequences. Edges of the graph represent the cost of these matches. The problem of finding the best match is reduced to finding the minimum-cut surface, which is solved as a maximum flow network problem. Application to visual localization is considered in this paper to show the effectiveness of the proposed multiple image sequence alignment method, without loosing its generality. Experimental evaluations show that the precision of sequence matching is improved by considering multiple visual sequences for the same route, and that the method performs favorably against state-of-the-art single representation methods like SeqSLAM and ABLE-M.