Kwonjoon Lee

Yuchen Yang, Kwonjoon Lee, Behzad Dariush et al.

Video Anomaly Detection (VAD) is crucial for applications such as security surveillance and autonomous driving. However, existing VAD methods provide little rationale behind detection, hindering public trust in real-world deployments. In this paper, we approach VAD with a reasoning framework. Although Large Language Models (LLMs) have shown revolutionary reasoning ability, we find that their direct use falls short of VAD. Specifically, the implicit knowledge pre-trained in LLMs focuses on general context and thus may not apply to every specific real-world VAD scenario, leading to inflexibility and inaccuracy. To address this, we propose AnomalyRuler, a novel rule-based reasoning framework for VAD with LLMs. AnomalyRuler comprises two main stages: induction and deduction. In the induction stage, the LLM is fed with few-shot normal reference samples and then summarizes these normal patterns to induce a set of rules for detecting anomalies. The deduction stage follows the induced rules to spot anomalous frames in test videos. Additionally, we design rule aggregation, perception smoothing, and robust reasoning strategies to further enhance AnomalyRuler's robustness. AnomalyRuler is the first reasoning approach for the one-class VAD task, which requires only few-normal-shot prompting without the need for full-shot training, thereby enabling fast adaption to various VAD scenarios. Comprehensive experiments across four VAD benchmarks demonstrate AnomalyRuler's state-of-the-art detection performance and reasoning ability. AnomalyRuler is open-source and available at: https://github.com/Yuchen413/AnomalyRuler

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

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/

Hua-Dong Xiong, Li Ji-An, Robert C. Wilson et al.

Large language models (LLMs) exhibit remarkable flexibility: they can adapt to novel tasks from in-context examples without any parameter updates, a capability known as in-context learning (ICL). Prior work on synthetic tasks has shown that ICL can implement specific algorithms, demonstrating architectural competence, and mechanistic analyses have identified key circuits that support this behavior. However, because in-context computation -- regardless of its algorithmic form -- relies on transformations in high-dimensional representation space, it remains unclear how the geometry of that space shapes ICL effectiveness. Motivated by the neuroscience view of classification as the untangling of neural representations, we hypothesize that ICL depends on the successful online untangling of task-relevant representations. To test this idea, we study how LLMs classify in-context examples whose labels are defined by the model's own internal representations with known structure. We show that ICL performance correlates systematically with the representational structure of the underlying classification task and that successful ICL is accompanied by geometric reorganization that increases online separability. We further find that LLM behavior is well described by a prototype-like algorithm that integrates evidence while reshaping representations to support classification. These findings offer a geometric account of ICL in pretrained LLMs, establish representational geometry as a mechanistic constraint on ICL, and quantify the gap between what pretrained representations afford and what in-context learning can exploit.

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.

Kaiwen Zhou, Kwonjoon Lee, Teruhisa Misu et al.

In our work, we explore the synergistic capabilities of pre-trained vision-and-language models (VLMs) and large language models (LLMs) on visual commonsense reasoning (VCR) problems. We find that VLMs and LLMs-based decision pipelines are good at different kinds of VCR problems. Pre-trained VLMs exhibit strong performance for problems involving understanding the literal visual content, which we noted as visual commonsense understanding (VCU). For problems where the goal is to infer conclusions beyond image content, which we noted as visual commonsense inference (VCI), VLMs face difficulties, while LLMs, given sufficient visual evidence, can use commonsense to infer the answer well. We empirically validate this by letting LLMs classify VCR problems into these two categories and show the significant difference between VLM and LLM with image caption decision pipelines on two subproblems. Moreover, we identify a challenge with VLMs' passive perception, which may miss crucial context information, leading to incorrect reasoning by LLMs. Based on these, we suggest a collaborative approach, named ViCor, where pre-trained LLMs serve as problem classifiers to analyze the problem category, then either use VLMs to answer the question directly or actively instruct VLMs to concentrate on and gather relevant visual elements to support potential commonsense inferences. We evaluate our framework on two VCR benchmark datasets and outperform all other methods that do not require in-domain fine-tuning.

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.

Hua-Dong Xiong, Li Ji-An, Jiaqi Huang et al.

Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments and changing goals. This capacity, known as working memory, is fundamental to human reasoning and intelligence. Despite having on the order of 100 billion neurons, both biological and artificial systems exhibit limitations in working memory. This raises a key question: why do large language models (LLMs) show such limitations, given that transformers have full access to prior context through attention? We find that although a two-layer transformer can be trained to solve working memory tasks perfectly, a diverse set of pretrained LLMs continues to show working memory limitations. Notably, LLMs reproduce interference signatures observed in humans: performance degrades with increasing memory load and is biased by recency and stimulus statistics. Across models, stronger working memory capacity correlates with broader competence on standard benchmarks, mirroring its link to general intelligence in humans. Yet despite substantial variability in working memory performance, LLMs surprisingly converge on a common computational mechanism. Rather than directly copying the relevant memory item from context, models encode multiple memory items in entangled representations, such that successful recall depends on interference control -- actively suppressing task-irrelevant content to isolate the target for readout. Moreover, a targeted intervention that suppresses stimulus content information improves performance, providing causal support for representational interference. Together, these findings identify representational interference as a core constraint on working memory in pretrained LLMs, suggesting that working-memory limits in biological and artificial systems may reflect a shared computational challenge: selecting task-relevant information under interference.

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.

Weihua Du, Qiushi Lyu, Jiaming Shan et al. · cmu

We introduce Constrained Human-AI Cooperation (CHAIC), an inclusive embodied social intelligence challenge designed to test social perception and cooperation in embodied agents. In CHAIC, the goal is for an embodied agent equipped with egocentric observations to assist a human who may be operating under physical constraints -- e.g., unable to reach high places or confined to a wheelchair -- in performing common household or outdoor tasks as efficiently as possible. To achieve this, a successful helper must: (1) infer the human's intents and constraints by following the human and observing their behaviors (social perception), and (2) make a cooperative plan tailored to the human partner to solve the task as quickly as possible, working together as a team (cooperative planning). To benchmark this challenge, we create four new agents with real physical constraints and eight long-horizon tasks featuring both indoor and outdoor scenes with various constraints, emergency events, and potential risks. We benchmark planning- and learning-based baselines on the challenge and introduce a new method that leverages large language models and behavior modeling. Empirical evaluations demonstrate the effectiveness of our benchmark in enabling systematic assessment of key aspects of machine social intelligence. Our benchmark and code are publicly available at https://github.com/UMass-Embodied-AGI/CHAIC.

Huaizhi Qu, Inyoung Choi, Zhen Tan et al.

LLM ensembles are widely used for LLM judges. However, how to estimate their accuracy, especially in an efficient way, is unknown. In this paper, we present a principled maximum a posteriori (MAP) framework for an economical and precise estimation of the performance of LLM ensemble judgment. We first propose a mixture of Beta-Binomial distributions to model the judgment distribution, revising from the vanilla Binomial distribution. Next, we introduce a conformal prediction-driven approach that enables adaptive stopping during iterative sampling to balance accuracy with efficiency. Furthermore, we design a prior transfer mechanism that utilizes learned distributions on open-source datasets to improve estimation on a target dataset when only scarce annotations are available. Finally, we present BetaConform, a framework that integrates our distribution assumption, adaptive stopping, and the prior transfer mechanism to deliver a theoretically guaranteed distribution estimation of LLM ensemble judgment with minimum labeled samples. BetaConform is also validated empirically. For instance, with only 10 samples from the TruthfulQA dataset, for a Llama ensembled judge, BetaConform gauges its performance with error margin as small as 3.37%.

Kwonjoon Lee, Subhransu Maji, Avinash Ravichandran et al.

Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively trained linear predictors can offer better generalization. We propose to use these predictors as base learners to learn representations for few-shot learning and show they offer better tradeoffs between feature size and performance across a range of few-shot recognition benchmarks. Our objective is to learn feature embeddings that generalize well under a linear classification rule for novel categories. To efficiently solve the objective, we exploit two properties of linear classifiers: implicit differentiation of the optimality conditions of the convex problem and the dual formulation of the optimization problem. This allows us to use high-dimensional embeddings with improved generalization at a modest increase in computational overhead. Our approach, named MetaOptNet, achieves state-of-the-art performance on miniImageNet, tieredImageNet, CIFAR-FS, and FC100 few-shot learning benchmarks. Our code is available at https://github.com/kjunelee/MetaOptNet.

Hongxin Zhang, Zeyuan Wang, Qiushi Lyu et al.

In this paper, we investigate the problem of embodied multi-agent cooperation, where decentralized agents must cooperate given only egocentric views of the world. To effectively plan in this setting, in contrast to learning world dynamics in a single-agent scenario, we must simulate world dynamics conditioned on an arbitrary number of agents' actions given only partial egocentric visual observations of the world. To address this issue of partial observability, we first train generative models to estimate the overall world state given partial egocentric observations. To enable accurate simulation of multiple sets of actions on this world state, we then propose to learn a compositional world model for multi-agent cooperation by factorizing the naturally composable joint actions of multiple agents and compositionally generating the video conditioned on the world state. By leveraging this compositional world model, in combination with Vision Language Models to infer the actions of other agents, we can use a tree search procedure to integrate these modules and facilitate online cooperative planning. We evaluate our methods on three challenging benchmarks with 2-4 agents. The results show our compositional world model is effective and the framework enables the embodied agents to cooperate efficiently with different agents across various tasks and an arbitrary number of agents, showing the promising future of our proposed methods. More videos can be found at https://umass-embodied-agi.github.io/COMBO/.

Piyush Gupta, David Isele, Enna Sachdeva et al.

We present a novel mission-planning strategy for heterogeneous multi-robot teams, taking into account the specific constraints and capabilities of each robot. Our approach employs hierarchical trees to systematically break down complex missions into manageable sub-tasks. We develop specialized APIs and tools, which are utilized by Large Language Models (LLMs) to efficiently construct these hierarchical trees. Once the hierarchical tree is generated, it is further decomposed to create optimized schedules for each robot, ensuring adherence to their individual constraints and capabilities. We demonstrate the effectiveness of our framework through detailed examples covering a wide range of missions, showcasing its flexibility and scalability.

Haoqiang Kang, Enna Sachdeva, Piyush Gupta et al.

Vision-Language Models (VLMs) have recently shown promising advancements in sequential decision-making tasks through task-specific fine-tuning. However, common fine-tuning methods, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) techniques like Proximal Policy Optimization (PPO), present notable limitations: SFT assumes Independent and Identically Distributed (IID) data, while PPO focuses on maximizing cumulative rewards. These limitations often restrict solution diversity and hinder generalization in multi-step reasoning tasks. To address these challenges, we introduce a novel framework, GFlowVLM, a framework that fine-tune VLMs using Generative Flow Networks (GFlowNets) to promote generation of diverse solutions for complex reasoning tasks. GFlowVLM models the environment as a non-Markovian decision process, allowing it to capture long-term dependencies essential for real-world applications. It takes observations and task descriptions as inputs to prompt chain-of-thought (CoT) reasoning which subsequently guides action selection. We use task based rewards to fine-tune VLM with GFlowNets. This approach enables VLMs to outperform prior fine-tuning methods, including SFT and RL. Empirical results demonstrate the effectiveness of GFlowVLM on complex tasks such as card games (NumberLine, BlackJack) and embodied planning tasks (ALFWorld), showing enhanced training efficiency, solution diversity, and stronger generalization capabilities across both in-distribution and out-of-distribution scenarios.

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.

Seunggeun Chi, Pin-Hao Huang, Enna Sachdeva et al.

We study the problem of estimating the body movements of a camera wearer from egocentric videos. Current methods for ego-body pose estimation rely on temporally dense sensor data, such as IMU measurements from spatially sparse body parts like the head and hands. However, we propose that even temporally sparse observations, such as hand poses captured intermittently from egocentric videos during natural or periodic hand movements, can effectively constrain overall body motion. Naively applying diffusion models to generate full-body pose from head pose and sparse hand pose leads to suboptimal results. To overcome this, we develop a two-stage approach that decomposes the problem into temporal completion and spatial completion. First, our method employs masked autoencoders to impute hand trajectories by leveraging the spatiotemporal correlations between the head pose sequence and intermittent hand poses, providing uncertainty estimates. Subsequently, we employ conditional diffusion models to generate plausible full-body motions based on these temporally dense trajectories of the head and hands, guided by the uncertainty estimates from the imputation. The effectiveness of our method was rigorously tested and validated through comprehensive experiments conducted on various HMD setup with AMASS and Ego-Exo4D datasets.

Gengwei Zhang, Jie Peng, Zhen Tan et al.

The recent success of reinforcement learning (RL) in large reasoning models has inspired the growing adoption of RL for post-training Multimodal Large Language Models (MLLMs) to enhance their visual reasoning capabilities. Although many studies have reported improved performance, it remains unclear whether RL training truly enables models to learn from visual information. In this work, we propose the Hallucination-as-Cue Framework, an analytical framework designed to investigate the effects of RL-based post-training on multimodal reasoning models from the perspective of model hallucination. Specifically, we introduce hallucination-inductive, modality-specific corruptions that remove or replace essential information required to derive correct answers, thereby forcing the model to reason by hallucination. By applying these corruptions during both training and evaluation, our framework provides a unique perspective for diagnosing RL training dynamics and understanding the intrinsic properties of datasets. Through extensive experiments and analyses across multiple multimodal reasoning benchmarks, we reveal that the role of model hallucination for RL-training is more significant than previously recognized. For instance, we find that RL post-training under purely hallucination-inductive settings can still significantly improve models' reasoning performance, and in some cases even outperform standard training. These findings challenge prevailing assumptions about MLLM reasoning training and motivate the development of more modality-aware RL-based training designs.

Seunggeun Chi, Enna Sachdeva, Pin-Hao Huang et al.

Amodal completion, which is the process of inferring the full appearance of objects despite partial occlusions, is crucial for understanding complex human-object interactions (HOI) in computer vision and robotics. Existing methods, such as those that use pre-trained diffusion models, often struggle to generate plausible completions in dynamic scenarios because they have a limited understanding of HOI. To solve this problem, we've developed a new approach that uses physical prior knowledge along with a specialized multi-regional inpainting technique designed for HOI. By incorporating physical constraints from human topology and contact information, we define two distinct regions: the primary region, where occluded object parts are most likely to be, and the secondary region, where occlusions are less probable. Our multi-regional inpainting method uses customized denoising strategies across these regions within a diffusion model. This improves the accuracy and realism of the generated completions in both their shape and visual detail. Our experimental results show that our approach significantly outperforms existing methods in HOI scenarios, moving machine perception closer to a more human-like understanding of dynamic environments. We also show that our pipeline is robust even without ground-truth contact annotations, which broadens its applicability to tasks like 3D reconstruction and novel view/pose synthesis.

Lingjun Zhao, Mingyang Xie, Paola Cascante-Bonilla et al.

Large Vision-Language Models often generate hallucinated content that is not grounded in its visual inputs. While prior work focuses on mitigating hallucinations, we instead explore leveraging hallucination correction as a training objective to improve video-language alignment. We introduce HACA, a self-training framework learning to correct hallucinations in descriptions that do not align with the video content. By identifying and correcting inconsistencies, HACA enhances the model's ability to align video and textual representations for spatio-temporal reasoning. Our experimental results show consistent gains in video-caption binding and text-to-video retrieval tasks, demonstrating that hallucination correction-inspired tasks serve as an effective strategy for improving vision and language alignment.

Xu Shen, Qi Zhang, Song Wang et al.

Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors: a single faulty step can propagate across agents and disrupt the trajectory. In this paper, we present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction. MASC rethinks detection as history-conditioned anomaly scoring via two complementary designs: (1) Next-Execution Reconstruction, which predicts the embedding of the next step from the query and interaction history to capture causal consistency, and (2) Prototype-Guided Enhancement, which learns a prototype prior over normal-step embeddings and uses it to stabilize reconstruction and anomaly scoring under sparse context (e.g., early steps). When an anomaly step is flagged, MASC triggers a correction agent to revise the acting agent's output before information flows downstream. On the Who&When benchmark, MASC consistently outperforms all baselines, improving step-level error detection by up to 8.47% AUC-ROC ; When plugged into diverse MAS frameworks, it delivers consistent end-to-end gains across architectures, confirming that our metacognitive monitoring and targeted correction can mitigate error propagation with minimal overhead.

Weiqing Luo, Zhen Tan, Yifan Li et al.

Real-world vision-language applications demand varying levels of perceptual granularity. However, most existing visual large language models (VLLMs), such as LLaVA, pre-assume a fixed resolution for downstream tasks, which leads to subpar performance. To address this problem, we first conduct a comprehensive and pioneering investigation into the resolution preferences of different vision-language tasks, revealing a correlation between resolution preferences with image complexity, and uncertainty variance of the VLLM at different image input resolutions. Building on this insight, we propose an empirical formula to determine the optimal resolution for a given vision-language task, combining these two factors. Second, based on rigorous experiments, we propose a novel parameter-efficient fine-tuning technique to extend the visual input resolution of pre-trained VLLMs to the identified optimal resolution. Extensive experiments on various vision-language tasks validate the effectiveness of our method.

Hyungjun Doh, Dong In Lee, Seunggeun Chi et al.

We introduce a novel framework for reconstructing dynamic human-object interactions from monocular video that overcomes challenges associated with occlusions and temporal inconsistencies. Traditional 3D reconstruction methods typically assume static objects or full visibility of dynamic subjects, leading to degraded performance when these assumptions are violated-particularly in scenarios where mutual occlusions occur. To address this, our framework leverages amodal completion to infer the complete structure of partially obscured regions. Unlike conventional approaches that operate on individual frames, our method integrates temporal context, enforcing coherence across video sequences to incrementally refine and stabilize reconstructions. This template-free strategy adapts to varying conditions without relying on predefined models, significantly enhancing the recovery of intricate details in dynamic scenes. We validate our approach using 3D Gaussian Splatting on challenging monocular videos, demonstrating superior precision in handling occlusions and maintaining temporal stability compared to existing techniques.

FNU Aryan, Simon Stepputtis, Sarthak Bhagat et al.

Scene understanding is a fundamental capability needed in many domains, ranging from question-answering to robotics. Unlike recent end-to-end approaches that must explicitly learn varying compositions of the same scene, our method reasons over their constituent objects and analyzes their arrangement to infer a scene's meaning. We propose a novel approach that reasons over a scene's scene- and knowledge-graph, capturing spatial information while being able to utilize general domain knowledge in a joint graph search. Empirically, we demonstrate the feasibility of our method on the ADE20K dataset and compare it to current scene understanding approaches.

Kwonjoon Lee, Huiwen Chang, Lu Jiang et al.

Recently, Vision Transformers (ViTs) have shown competitive performance on image recognition while requiring less vision-specific inductive biases. In this paper, we investigate if such performance can be extended to image generation. To this end, we integrate the ViT architecture into generative adversarial networks (GANs). For ViT discriminators, we observe that existing regularization methods for GANs interact poorly with self-attention, causing serious instability during training. To resolve this issue, we introduce several novel regularization techniques for training GANs with ViTs. For ViT generators, we examine architectural choices for latent and pixel mapping layers to facilitate convergence. Empirically, our approach, named ViTGAN, achieves comparable performance to the leading CNN-based GAN models on three datasets: CIFAR-10, CelebA, and LSUN bedroom.

Gaurav Parmar, Dacheng Li, Kwonjoon Lee et al.

We present a new generative autoencoder model with dual contradistinctive losses to improve generative autoencoder that performs simultaneous inference (reconstruction) and synthesis (sampling). Our model, named dual contradistinctive generative autoencoder (DC-VAE), integrates an instance-level discriminative loss (maintaining the instance-level fidelity for the reconstruction/synthesis) with a set-level adversarial loss (encouraging the set-level fidelity for there construction/synthesis), both being contradistinctive. Extensive experimental results by DC-VAE across different resolutions including 32x32, 64x64, 128x128, and 512x512 are reported. The two contradistinctive losses in VAE work harmoniously in DC-VAE leading to a significant qualitative and quantitative performance enhancement over the baseline VAEs without architectural changes. State-of-the-art or competitive results among generative autoencoders for image reconstruction, image synthesis, image interpolation, and representation learning are observed. DC-VAE is a general-purpose VAE model, applicable to a wide variety of downstream tasks in computer vision and machine learning.

Siyang Wang, Justin Lazarow, Kwonjoon Lee et al.

We tackle the problem of modeling sequential visual phenomena. Given examples of a phenomena that can be divided into discrete time steps, we aim to take an input from any such time and realize this input at all other time steps in the sequence. Furthermore, we aim to do this without ground-truth aligned sequences -- avoiding the difficulties needed for gathering aligned data. This generalizes the unpaired image-to-image problem from generating pairs to generating sequences. We extend cycle consistency to loop consistency and alleviate difficulties associated with learning in the resulting long chains of computation. We show competitive results compared to existing image-to-image techniques when modeling several different data sets including the Earth's seasons and aging of human faces.

Justin Lazarow, Kwonjoon Lee, Kunyu Shi et al.

Panoptic segmentation requires segments of both "things" (countable object instances) and "stuff" (uncountable and amorphous regions) within a single output. A common approach involves the fusion of instance segmentation (for "things") and semantic segmentation (for "stuff") into a non-overlapping placement of segments, and resolves overlaps. However, instance ordering with detection confidence do not correlate well with natural occlusion relationship. To resolve this issue, we propose a branch that is tasked with modeling how two instance masks should overlap one another as a binary relation. Our method, named OCFusion, is lightweight but particularly effective in the instance fusion process. OCFusion is trained with the ground truth relation derived automatically from the existing dataset annotations. We obtain state-of-the-art results on COCO and show competitive results on the Cityscapes panoptic segmentation benchmark.

Zhiwei Jia, Haoshen Hong, Siyang Wang et al.

We study the intrinsic transformation of feature maps across convolutional network layers with explicit top-down control. To this end, we develop top-down feature transformer (TFT), under controllable parameters, that are able to account for the hidden layer transformation while maintaining the overall consistency across layers. The learned generators capture the underlying feature transformation processes that are independent of particular training images. Our proposed TFT framework brings insights to and helps the understanding of, an important problem of studying the CNN internal feature representation and transformation under the top-down processes. In the case of spatial transformations, we demonstrate the significant advantage of TFT over existing data-driven approaches in building data-independent transformations. We also show that it can be adopted in other applications such as data augmentation and image style transfer.

Kwonjoon Lee, Weijian Xu, Fan Fan et al.

We present Wasserstein introspective neural networks (WINN) that are both a generator and a discriminator within a single model. WINN provides a significant improvement over the recent introspective neural networks (INN) method by enhancing INN's generative modeling capability. WINN has three interesting properties: (1) A mathematical connection between the formulation of the INN algorithm and that of Wasserstein generative adversarial networks (WGAN) is made. (2) The explicit adoption of the Wasserstein distance into INN results in a large enhancement to INN, achieving compelling results even with a single classifier --- e.g., providing nearly a 20 times reduction in model size over INN for unsupervised generative modeling. (3) When applied to supervised classification, WINN also gives rise to improved robustness against adversarial examples in terms of the error reduction. In the experiments, we report encouraging results on unsupervised learning problems including texture, face, and object modeling, as well as a supervised classification task against adversarial attacks.