43 accepted papers
Visual attribute imbalance is a common yet underexplored issue in image classification, significantly impacting model performance and generalization. In this work, we first define the first-level and second-level attributes of images and then introduce a CLIP-based framework to construct a visual at
Extrinsic dexterity leverages environmental contact to overcome the limitations of prehensile manipulation. However, achieving such dexterity in cluttered scenes remains challenging and underexplored, as it requires selectively exploiting contact among multiple interacting objects with inherently co…
Recent robot foundation models largely rely on large-scale behavior cloning, which imitates expert actions but discards transferable dynamics knowledge embedded in heterogeneous embodied data. While the Unified World Model (UWM) formulation has the potential to leverage such diverse data, existing i…
Reinforcement Learning (RL) has shown significant promise in automated portfolio management; however, effectively balancing risk and return remains a central challenge, as many models fail to adapt to dynamically changing market conditions. We propose Meta-controlled Agents for a Risk-aware System (
Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention to target regions. Instead, visual attention is always dispe
Vision-Language-Action (VLA) models have emerged as a generalist robotic agent. However, existing VLAs are hindered by excessive parameter scales, prohibitive pre-training requirements, and limited applicability to diverse embodiments. To improve the practicality of VLAs, we propose a comprehensive …
Collision detection is a core component of robotics applications such as simulation, control, and planning. Traditional algorithms like GJK+EPA compute textit{witness points}—the closest or deepest-penetration pairs between two objects—but are inherently non-differentiable, preventing gradient flow …
Graph distribution shifts between training and test graphs pose severe challenges to the generalization of graph neural networks (GNNs). In real-world deployment, application environments are continuously evolving, while retraining or redesigning GNNs is often costly and impractical. In light of thi
Vision-language-action (VLA) models aim to understand natural language instructions and visual observations and execute corresponding actions as an embodied agent. Recent advancements have integrated future images into the understanding-action loop, enabling foresight-driven policies that reduce abs…
Robotic dexterous grasping is important for interacting with the environment. To unleash the potential of data-driven models for dexterous grasping, a large-scale, highquality dataset is essential. While gradient-based optimization offers a promising way for constructing such datasets, previous work
Large Language Models (LLMs) have shown significant limitations in understanding creative content, as demonstrated by Hessel et al. (2023)’s influential work on the New Yorker Cartoon Caption Contest (NYCCC). Their study exposed a substantial gap between LLMs and humans in humor comprehension, estab
As large models gain traction, vision-language models are enabling robots to tackle increasingly complex tasks. However, limited by the difficulty of data collection, progress has mainly focused on controlling simple gripper end-effectors. There is little research on functional grasping with large m…
Generalizable dexterous grasping is a fundamental skill for intelligent robots. To develop such skills, a large-scale, high-quality, and diverse dataset of robotic dexterous grasps—covering the GRASP taxonomy—is essential but extremely challenging to collect. Previous dexterous grasp synthesis metho…
We introduce EvaLearn, a pioneering benchmark designed to evaluate large language models (LLMs) on their learning capability and efficiency in challenging tasks, a critical, yet underexplored aspect of model potential. EvaLearn contains 648 challenging problems across six task types, grouped into 18…
Data heterogeneity in federated learning, characterized by a significant misalignment between local and global distributions, leads to divergent local optimization directions and hinders global model training. Existing studies mainly focus on optimizing local updates or global aggregation, but these…
Embodied foundation models are gaining increasing attention for their zero-shot generalization, scalability, and adaptability to new tasks through few-shot post-training. However, existing models rely heavily on real-world data, which is costly and labor-intensive to collect. Synthetic data offers a…
In Reinforcement Learning from Human Feedback (RLHF), the reward model (RM) evaluates the response quality based on the given context and assigns a reward. It plays a crucial role in aligning RLHF with human preferences. Although the current RM training paradigm concatenates the context and response…
Navigating autonomous vehicles in open scenarios is a challenge due to the difficulties in handling unseen objects. Existing solutions either rely on small models that struggle with generalization or large models that are resource-intensive. While collaboration between the two offers a promising sol
Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The performance of VLA models can be improved by integrating with action chunking, a critical technique for effective control. However, action chunking linearly scales up action dimensions in
Large language models (LLMs) exhibit human-like intelligence, enabling them to simulate human behavior and support various applications that require both humanized communication and extensive knowledge reserves. Efforts are made to personify LLMs with special training data or hand-crafted prompts, w
The infringement risks of LLMs have raised significant copyright concerns across different stages of the model lifecycle. While current methods often address these issues separately, this position paper argues that the LLM copyright challenges are inherently connected, and independent optimization o…
Cross-modal hashing is a promising approach for efficient data retrieval and storage optimization. However, contemporary methods exhibit significant limitations in semantic preservation, contextual integrity, and information redundancy, which constrains retrieval efficacy. We present PromptHash, an…
In object detection, the number of instances is commonly used to determine whether a dataset follows a long-tailed distribution, implicitly assuming that the model will perform poorly on categories with fewer instances. This assumption has led to extensive research on category bias in datasets with…
Existing large language models (LLMs) show exceptional problem-solving capabilities but might struggle with complex reasoning tasks. Despite the successes of chain-of-thought and tree-based search methods, they mainly depend on the internal knowledge of LLMs to search over intermediate reasoning ste…
For the task of hanging clothes, learning how to insert a hanger into a garment is a crucial step, but has rarely been explored in robotics. In this work, we address the problem of inserting a hanger into various unseen garments that are initially laid flat on a table. This task is challenging due t
This research aims to enhance the interaction between humans and robots, especially in environments with multiple similar objects or semantic ambiguities. Traditional command-based interactions typically require users to provide precise descriptions, which often poses a significant challenge. To add
Cross-Domain Few-shot Semantic Segmentation (CD-FSS) aims to train generalized models that can segment classes from different domains with a few labeled images. Previous works have proven the effectiveness of feature transformation in addressing CD-FSS. However, they completely rely on support image…
Depth sensing is an important problem for 3D vision-based robotics. Yet, a real-world active stereo or ToF depth camera often produces noisy and incomplete depth which bottlenecks robot performances. In this work, we propose D3RoMa, a learning-based depth estimation framework on stereo image pairs t…
Grasping in cluttered scenes remains highly challenging for dexterous hands due to the scarcity of data. To address this problem, we present a large-scale synthetic dataset, encompassing 1319 objects, 8270 scenes, and 426 million grasps. Beyond benchmarking, we also explore data-efficient learning s…
Multimodal Federated Learning (MFL) addresses the setup of multiple clients with diversified modality types (e.g. image, text, video, and audio) working together to improve their local personal models in a data-privacy manner. Prior MFL works rely on restrictive compositional neural architecture des…
We present a novel multimodal preference dataset for creative tasks, consisting of over 250 million human votes on more than 2.2 million captions, collected through crowdsourcing rating data for The New Yorker's weekly cartoon caption contest over the past eight years. This unique dataset supports t…
There has been growing concern regarding data privacy during the development and deployment of Multimodal Foundation Models for Artificial General Intelligence (AGI), while Federated Learning (FL) allows multiple clients to collaboratively train models in a privacy-preserving manner. This paper form…
This work tackles the problem of task-oriented dexterous hand pose synthesis, which involves generating a static hand pose capable of applying a task-specific set of wrenches to manipulate objects. Unlike previous approaches that focus solely on force-closure grasps, which are unsuitable for non-pre…
Federated learning facilitates the collaborative learning of a global model across multiple distributed medical institutions without centralizing data. Nevertheless the expensive cost of annotation on local clients remains an obstacle to effectively utilizing local data. To mitigate this issue feder…
Robotic dexterous grasping is the first step to enable human-like dexterous object manipulation and thus a crucial robotic technology. However, dexterous grasping is much more under-explored than object grasping with parallel grippers, partially due to the lack of a large-scale dataset. In this work…
Visually-rich document entity retrieval (VDER), which extracts key information (e.g. date, address) from document images like invoices and receipts, has become an important topic in industrial NLP applications. The emergence of new document types at a constant pace, each with its unique entity types…
Learning a generalizable object manipulation policy is vital for an embodied agent to work in complex real-world scenes. Parts, as the shared components in different object categories, have the potential to increase the generalization ability of the manipulation policy and achieve cross-category obj…
In this work, we tackle the challenging task of jointly tracking hand object poses and reconstructing their shapes from depth point cloud sequences in the wild, given the initial poses at frame 0. We for the first time propose a point cloud-based hand joint tracking network, HandTrackNet, to estimat…
In this work, we tackle the problem of learning universal robotic dexterous grasping from a point cloud observation under a table-top setting. The goal is to grasp and lift up objects in high-quality and diverse ways and generalize across hundreds of categories and even the unseen. Inspired by succe…
Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem. The gap between the Euclidean network output space and the non-Euclidean SO(3) manifold imposes a severe challenge for neural network learning in both forward and backward passes. While several wo…
Answering complex questions that require multi-step multi-type reasoning over raw text is challenging, especially when conducting numerical reasoning. Neural Module Networks (NMNs), follow the programmer-interpreter framework and design trainable modules to learn different reasoning skills. However,…
A phase-only robust minimum dispersion (PO-RMD) beamformer is devised for non-Gaussian signals. The proposed PO-RMD employs a constant-modulus constraint on the weights, which is equivalent to simply phase shifting at each antenna. It adopts the minimum dispersion criterion to utilize the non-Gaussi…