70 accepted papers
Vision–Language–Action (VLA) models in autonomous driving systems have recently demonstrated transformative potential by integrating multimodal perception with decision-making capabilities. However, the interpretability and coherence of the decision process and the plausibility of action sequences r…
Recently, the rapid development of low-altitude aerial applications has driven the need for drone-based unified detectors. In contrast to task-specific detectors that suffer from poor scalability across diverse scenarios, existing unified detectors leverage the Mixture-of-Experts (MoE) architecture …
Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two core capabilities: \textbf{\textit{composition}} and \textbf{\textit{reasoning}}. Despite recent advances of T2I models…
Image Chain-of-Thought (Image-CoT) is a test-time scaling paradigm that improves image generation by extending inference time. Most Image-CoT methods focus on text-to-image (T2I) generation. Unlike T2I generation, image editing is goal-directed: the solution space is constrained by the source image
Hallucinations in Large Language Models (LLMs) pose a major barrier to their reliable use in critical decision-making. Although existing hallucination detection methods have improved accuracy, they still struggle with disentangling semantic and reasoning information and maintaining robustness. To ad…
Ontologies (schemas) are a key bottleneck for schema-grounded information extraction and knowledge graph construction, yet manual ontology engineering is expensive and schemas quickly fragment or drift across domains. We introduce SCOPE (Schema Construction and Ontology Induction Pipeline Evaluation…
The dominant paradigm for high-fidelity 3D generation relies on a VAE-Diffusion pipeline, where the VAE's reconstruction capability sets a firm upper bound on generation quality. A fundamental challenge limiting existing VAEs is the representation mismatch between ground-truth meshes and network pre
We present UniTEX, a novel two-stage 3D texture generation framework to create high-quality, consistent textures for 3D assets. Existing approaches predominantly rely on UV-based models in the second stage to refine textures after reprojecting the generated multi-view images onto the 3D shapes, whic
Single-image-to-3D shape generation has seen remarkable progress, driven by latent diffusion models trained on the compressed latent space of 3D VAEs. However, the task remains intrinsically ill-posed: recovering complete 3D geometry--especially occluded surfaces--from a single view is inherently am
Despite advances in the application of MLLMs for various video tasks, video event prediction (VEP) remains relatively underexplored. VEP requires the model to perform fine-grained temporal modeling of videos and establish logical relationships between videos and future events, which current MLLMs st
Multimodal large language models (MLLMs) have demonstrated remarkable potential in bridging visual and textual reasoning, yet their reliance on text-centric priors often limits their ability to disentangle semantically similar actions in open-vocabulary scenarios. To address this, we propose Video-S…
Text-to-video (T2V) generative models have rapidly advanced and found widespread applications across fields like entertainment, education, and marketing. However, the adversarial vulnerabilities of these models remain rarely explored. We observe that in T2V generation tasks, the generated videos oft…
We present a novel generative 3D modeling system, coined CraftsMan, which can generate high-fidelity 3D geometries with highly varied shapes, regular mesh topologies, and detailed surfaces, and, notably, allows for refining the geometry in an interactive manner. Despite the significant advancements…
Simulation has enabled unprecedented compute-scalable approaches to robot learning. However, many existing simulation frameworks typically support a narrow range of scenes/tasks and lack features critical for scaling generalizable robotics and sim2real. We introduce and open source ManiSkill3, the f…
Recent 3D content generation pipelines commonly employ Variational Autoencoders (VAEs) to encode shapes into compact latent representations for diffusion-based generation. However, the widely adopted uniform point sampling strategy in Shape VAE training often leads to a significant loss of geometric…
Sequence learning based tracking frameworks are popular in the tracking community. In practice, its auto-regressive sequence generation manner leads to inferior performance and high latency compared with latest advanced trackers. In this paper, to mitigate this issue, we propose an efficient and eff
Densely structured pruning methods -- which generate pruned models in a fully dense format, allowing immediate compression benefits without additional demands -- are evolving owing to their practical significance. Traditional techniques in this domain mainly revolve around coarser granularities, suc…
Intuitively, an ideal collaborative filtering (CF) model should learn from users' full rankings over all items to make optimal top-K recommendations. Due to the absence of such full rankings in practice, most CF models rely on pairwise loss functions to approximate full rankings, resulting in an imm…
Dynamic grasping of moving objects in complex, continuous motion scenarios remains challenging. Reinforcement Learning (RL) has been applied in various robotic manipulation tasks, benefiting from its closed-loop property. However, existing RL-based methods do not fully explore the potential for enha
Multi-source domain adaptation (MSDA) borrows intrinsic knowledge from well-annotated source domains to identify target visual signals. The main challenges are effectively mitigating cross-domain shift and extracting discriminative target features via the suitable source semantics. To overcome them,…
In visual generation tasks, the responses and combinations of complex concepts often lack stability and are error-prone, which remains an under-explored area. In this paper, we attempt to explore the causal factors for poor concept responses through elaborately designed experiments. We also design a…
In this paper, we consider a score-based Integer Programming (IP) approach for solving the Bayesian Network Structure Learning (BNSL) problem. State-of-the-art BNSL IP formulations suffer from the exponentially large number of variables and constraints. A standard approach in IP to address such chal…
With the continuous progress of visual generation technologies, the scale of video datasets has grown exponentially. The quality of these datasets plays a pivotal role in the performance of video generation models. We assert that temporal splitting, detailed captions, and video quality filtering are…
Backdoor attacks are powerful and effective, but distributing LLMs without a proven track record like ‘meta-llama‘ or ‘qwen‘ rarely gains community traction. We identify LoRA sharing as a unique scenario where users are more willing to try unendorsed assets, since such shared LoRAs allow them to enj
We introduce a diffusion-based approach for generating privacy-preserving digital twins of multi-room indoor environments from depth images only. Central to our approach is a novel Multi-view Overlapped Scene Alignment with Implicit Consistency (MOSAIC) model that explicitly considers cross-view dep…
World models that forecast environmental changes from actions are vital for autonomous driving models with strong generalization. The prevailing driving world model mainly build on pixel-level video prediction model. Although these models can produce high-fidelity video sequences with advanced diffu…
Large Language Models (LLMs) are increasingly adopted across real-world applications, yet traditional evaluations rely on expensive, domain-specific ground-truth labels that are often unavailable or infeasible. We introduce a ground-truth-free evaluation framework focused on reasoning consistency an…
Varying dynamics pose a fundamental difficulty when deploying safe control laws in the real world. Safety Index Synthesis (SIS) deeply relies on the system dynamics and once the dynamics change, the previously synthesized safety index becomes invalid. In this work, we show the real-time efficacy of
Achieving optimal performance of video diffusion transformers within given data and compute budget is crucial due to their high training costs. This necessitates precisely determining the optimal model size and training hyperparameters before large-scale training. While scaling laws are employed in…
The creation of diverse and realistic driving scenarios has become essential to enhance perception and planning capabilities of the autonomous driving system. However, generating long-duration, surround-view consistent driving videos remains a significant challenge. To address this, we present UniML…
The human hand is capable of executing a wide range of complex movements due to its biomechanical structure and skin sensing system. Designing an anthropomorphic hand that mimics the biomechanical structure of the human and incorporates skin sensing, presents a long-term challenge in the field of ro
In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily emphasize improvement in expected performance, lacking the ability…
Negative sampling is essential for implicit collaborative filtering to provide proper negative training signals so as to achieve desirable performance. We experimentally unveil a common limitation of all existing negative sampling methods that they can only select negative samples of a fixed hardnes…
"The binary cross-entropy (BCE) loss function is widely utilized in multi-label classification (MLC) tasks, treating each label independently. The log-sum-exp pairwise (LSEP) loss, which emphasizes higher logits for positive classes over negative ones within a sample and accounts for label dependenc…
When manipulating an object to accomplish complex tasks, humans rely on both vision and touch to keep track of the object's 6D pose. However, most existing object pose tracking systems in robotics rely exclusively on visual signals, which hinder a robot's ability to manipulate objects effectively. T
This paper presents GenH2R a framework for learning generalizable vision-based human-to-robot (H2R) handover skills. The goal is to equip robots with the ability to reliably receive objects with unseen geometry handed over by humans in various complex trajectories. We acquire such generalizability b…
The requirements for real-world manipulation tasks are diverse and often conflicting; some tasks require precise motion while others require force compliance; some tasks require avoidance of certain regions while others require convergence to certain states. Satisfying these varied requirements with…
Neural networks have shown promising performance in collaborative filtering and matrix completion but the theoretical analysis is limited and there is still room for improvement in terms of the accuracy of recovering missing values. This paper presents a neuron-enhanced autoencoder matrix completion…
It is inherently ambiguous to lift 2D results from pre-trained diffusion models to a 3D world for text-to-3D generation. 2D diffusion models solely learn view-agnostic priors and thus lack 3D knowledge during the lifting, leading to the multi-view inconsistency problem. We find that this problem pri…
Fairness in machine learning has attracted increasing attention in recent years. The fairness methods improving algorithmic fairness for in-distribution data may not perform well under distribution shifts. In this paper, we first theoretically demonstrate the inherent connection between distribution…
Automatic 3D content creation has achieved rapid progress recently due to the availability of pre-trained, large language models and image diffusion models, forming the emerging topic of text-to-3D content creation. Existing text-to-3D methods commonly use implicit scene representations, which coupl…
For robots to be effectively deployed in novel environments and tasks, they must be able to understand the feedback expressed by humans during intervention. This can either correct undesirable behavior or indicate additional preferences. Existing methods either require repeated episodes of interacti…
Generalizable manipulation skills, which can be composed to tackle long-horizon and complex daily chores, are one of the cornerstones of Embodied AI. However, existing benchmarks, mostly composed of a suite of simulatable environments, are insufficient to push cutting-edge research works because the…
Manipulating unseen articulated objects through visual feedback is a critical but challenging task for real robots. Existing learning-based solutions mainly focus on visual affordance learning or other pre-trained visual models to guide manipulation policies, which face challenges for novel instance
This letter studies real-time collaborative robot (cobot) handling, where the cobot maneuvers an object under human dynamic gesture commands. Enabling dynamic gesture commands is useful when the human needs to avoid direct contact with the robot or the object handled by the robot. However, the key c
In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the adversaries can embed malicious prediction behaviors by manipulating…
Accurately manipulating articulated objects is a challenging yet important task for real robot applications. In this paper, we present a novel framework called Sim2Real2 to enable the robot to manipulate an unseen articulated object to the desired state precisely in the real world with no human demo…
Despite the tremendous success of Reinforcement Learning (RL) algorithms in simulation environments, applying RL to real-world applications still faces many challenges. A major concern is safety, in another word, constraint satisfaction. State-wise constraints are one of the most common constraints…
Transparent objects are common in daily life. However, depth sensing for transparent objects remains a challenging problem. While learning-based methods can leverage shape priors to improve the sensing quality, the labor-intensive data collection in real world and the sim-to-real domain gap restrict…
Federated learning (FL) over mobile devices is a promising distributed learning paradigm for various mobile applications. However, practical deployment of FL over mobile devices is very challenging because (i) conventional FL incurs huge training latency for mobile devices due to interleaved local c…
Delicate industrial insertion tasks (e.g., PC board assembly) remain challenging for industrial robots. The chal-lenges include low error tolerance, delicacy of the components, and large task variations with respect to the components to be inserted. To deliver a feasible robotic solution for these i…
Traditional depth sensors generate accurate real world depth estimates that surpass even the most advanced learning approaches trained only on simulation domains. Since ground truth depth is readily available in the simulation domain but quite difficult to obtain in the real domain, we propose a met…
Instance-dependent label noise (IDN) widely exists in real-world datasets and usually misleads the training of deep neural networks. Noise transition matrix (NTM) (i.e., the probability that clean labels flip into noisy labels) is used to characterize the label noise and can be adopted to bridge the…
GelSight optical tactile sensors have high-resolution and low-cost advantages and have witnessed growing adoption in various contact-rich robotic applications. Sim2Real for GelSight sensors can reduce the time cost and sensor damage during data collection and is crucial for learning-based tactile pe
Training Graph Neural Networks (GNNs) on large graphs is a fundamental challenge due to the high memory usage, which is mainly occupied by activations (e.g., node embeddings). Previous works usually focus on reducing the number of nodes retained in memory. In parallel, unlike what has been developed…
Creation of 3D content by stylization is a promising yet challenging problem in computer vision and graphics research. In this work, we focus on stylizing photorealistic appearance renderings of a given surface mesh of arbitrary topology. Motivated by the recent surge of cross-modal supervision of t…
Learning useful interactions between input features is crucial for tabular data modeling. Recent efforts start to explicitly model the feature interactions with graph, where each feature is treated as an individual node. However, the existing graph construction methods either heuristically formula…
Graph neural networks (GNNs) integrate deep architectures and topological structure modeling in an effective way. However, the performance of existing GNNs would decrease significantly when they stack many layers, because of the over-smoothing issue. Node embeddings tend to converge to similar vecto…
In this paper, we study the problem of fine-grained air quality inference that predicts the air quality level of any location from air quality readings of nearby monitoring stations. We point out the importance of explicitly modeling both static and dynamic spatial correlations, and consequently pro…
The problem of finding an ancestral acyclic directed mixed graph (ADMG) that represents the causal relationships between a set of variables is an important area of research on causal inference. Most existing score-based structure learning methods focus on learning directed acyclic graph (DAG) models…
Chameleon tongues are extremely rapid, ultra-stretchable, compact, and can capture preys located multi-directionally. Various chameleon tongue inspired shooting manipulators have therefore been developed. Little work, however, has been studied on the multi-directional preying capability of chameleon
Estimating 3D poses of multiple humans in real-time is a classic but still challenging task in computer vision. Its major difficulty lies in the ambiguity in cross-view association of 2D poses and the huge state space when there are multiple people in multiple views. In this paper, we present a nove…
This paper makes a first attempt to bring the Shape from Polarization (SfP) problem to the realm of deep learning. The previous state-of-the-art methods for SfP have been purely physics-based. We see value in these principled models, and blend these physical models as priors into a neural network ar…
Accurate stereo depth estimation plays a critical role in various 3D tasks in both indoor and outdoor environments. Recently, learning-based multi-view stereo methods have demonstrated competitive performance with limited number of views. However, in challenging scenarios, especially when building c…
Graph neural networks (GNNs), which learn the representation of a node by aggregating its neighbors, have become an effective computational tool in downstream applications. Over-smoothing is one of the key issues which limit the performance of GNNs as the number of layers increases. It is because th…
Recent advancements have led to a proliferation of machine learning systems used to assist humans in a wide range of tasks. However, we are still far from accurate, reliable, and resource-efficient operations of these systems. For robot perception, convolutional neural networks (CNNs) for object det…
We introduce Point-MVSNet, a novel point-based deep framework for multi-view stereo (MVS). Distinct from existing cost volume approaches, our method directly processes the target scene as point clouds. More specifically, our method predicts the depth in a coarse-to-fine manner. We first generate a c…
Grasping is among the most fundamental and long-lasting problems in robotics study. This paper studies the problem of 6-DoF(degree of freedom) grasping by a parallel gripper in a cluttered scene captured using a commodity depth sensor from a single viewpoint. We address the problem in a learning-bas
This article develops a set space visual servoing method that is quiet different from state-of-the-art approaches. Our approach does not require complex image processing techniques for the extraction, matching and tracking of image features. Instead, it only requires a simple matching algorithm and…