27 accepted papers
Reinforcement Learning (RL) has become a cornerstone for improving the performance of Large Language Models (LLMs). However, its rollout phase constitutes a significant efficiency bottleneck, mainly arising from the long-tail bubbles across data parallel ranks, particularly in long-context scenarios…
Recent work explores how real and synthetic data contribute to VLA model generalization. While the \pi-series model has shown the strong effectiveness of large-scale real-robot pre-training, synthetic data has not previously demonstrated comparable capability at scale.This paper provides the first e
Long-form legal reasoning remains a key challenge for large language models (LLMs) in spite of recent advances in test-time scaling. To address this, we introduce ***LEXam***, a novel benchmark derived from 340 law exams spanning 116 law school courses across a range of subjects and degree levels. T…
Real-world data collection for robotics is costly and resource-intensive, requiring skilled operators and expensive hardware. Simulations offer a scalable alternative but often fail to achieve sim-to-real generalization due to geometric and visual gaps. To address these challenges, we propose a 3D-p…
Modeling environmental forces remains a critical challenge in the design and control of robots operating on granular terrain. In pushing locomotion, propulsion is generated by displacing a large number of particles; however, the resulting terrain deformation complicates accurate real-time force pred…
Large language and vision-language models have inspired end-to-end vision-language-action (VLA) systems in robotics, yet existing robot datasets remain costly, embodiment-specific, and insufficient, limiting robustness and generalization. Recent approaches address this by adopting a plan-then-execut…
Recent vision-language-action (VLA) models built on pretrained vision-language models (VLMs) have demonstrated strong performance in robotic manipulation. However, these models remain constrained by the single-frame image paradigm and fail to fully leverage the temporal information offered by multi-
Grasping is a fundamental capability for robots to interact with the physical world. Humans, equipped with two hands, autonomously select appropriate grasp strategies based on the shape, size, and weight of objects, enabling robust grasping and subsequent manipulation. In contrast, current robotic g…
To operate effectively in the real world, robots should integrate multimodal reasoning with precise action generation. However, existing vision-language-action (VLA) models often sacrifice one for the other, narrow their abilities to task-specific manipulation data, and suffer catastrophic forgettin…
Multimodal Retrieval-Augmented Generation (MMRAG) has been introduced to enhance Multimodal Large Language Models by incorporating externally retrieved multimodal knowledge, but it introduces two challenges: Parametric-Retrieved Knowledge Inconsistency (PRKI), where discrepancies between parametric…
Robotic manipulation in real-world settings remains challenging, especially regarding robust generalization. Existing simulation platforms lack sufficient support for exploring how policies adapt to varied instructions and scenarios. Thus, they lag behind the growing interest in instruction-followin…
Large Language Models (LLMs) face significant limitations when applied to large-scale graphs, struggling with context constraints and inflexible reasoning. We introduce GraphChain, a novel framework enabling LLMs to analyze large graphs by orchestrating dynamic sequences of specialized tools, mimick…
Fully comprehending scientific papers by machines reflects a high level of Artificial General Intelligence, requiring the ability to reason across fragmented and heterogeneous sources of information, presenting a complex and practically significant challenge. While Vision-Language Models (VLMs) have…
Current efforts to learn scalable policies in robotic manipulation primarily fall into two categories: one focuses on "action," which involves behavior cloning from extensive collections of robotic data, while the other emphasizes "vision," enhancing model generalization by pre-training representati…
Embedding-based similarity metrics between text sequences can be influenced not just by the content dimensions we most care about, but can also be biased by spurious attributes like the text’s source or language. These document confounders cause problems for many applications, but especially those t
With the aging of critical infrastructure like bridges and plant facilities, the development of innovative wall-climbing robots using permanent magnets has become increasingly important. Traditional designs of such robots depend on controlling the position of lifters or permanent magnets to control
Estimating robot pose and joint angles is significant in advanced robotics, enabling applications like robot collaboration and online hand-eye calibration. However, the introduction of unknown joint angles makes prediction more complex than simple robot pose estimation, due to its higher dimensional…
As black-box machine learning models become more complex and are applied in high-stakes settings, the need for providing explanations for their predictions becomes crucial. Although Local Interpretable Model-agnostic Explanations (LIME) \cite{ribeiro2016should} is a widely adopted method for underst…
In this work, we tackle the problem of online camera-to-robot pose estimation from single-view successive frames of an image sequence, a crucial task for robots to interact with the world. The primary obstacles of this task are the robot's self-occlusions and the ambiguity of single-view images. Thi…
Devoted to interpreting the explicit behaviors of machine learning models, explanation methods can identify implicit characteristics of models to improve trustworthiness. However, explanation methods are shown as vulnerable to adversarial perturbations, implying security concerns in high-stakes doma…
This paper mathematically conceives a novel walking support device that leverages passive dynamics and coupling effects. In this model, a passive human walker is flexibly connected to an active humanoid, where the coupling effect induces a stable walking gait of the human. To understand the key mech…
Undulation is the most common gait generated by legless creatures, which enables their robust and efficient locomotion in various environments. Such advantages inspired the control design of many kinds of locomotion robots. Despite their technical details, most of them realize the undulation gait vi…
"Video frame interpolation is a challenging task due to the ever-changing real-world scene. Previous methods often calculate the bi-directional optical flows and then predict the intermediate optical flows under the linear motion assumptions, leading to isotropic intermediate flow generation. Follow…
Particular tasks performed in narrow and confined spaces require a capability of passing through a limited pathway. Consequently, previous research developed a snake-like robot that generates a 1-D rectilinear gait with an appropriate mechanical design. In contrast, a rigorous mathematical model and
Biological observations on tetrapods locomotion deduce that anti-phase synchronization (APS) between fore and rear parts is beneficial for achieving a high-speed walking. On the other hand, theoretical analysis and experimental studies on quadruped robots suggest that a flexible spine potentially im…
This paper presents a novel approach to fault tolerant reconfiguration of modular self-folding robots. Among various types of faults that probably occur in the modular system, we focus on the tolerance of complete actuation failure of active modules that might cause imprecise robotic motion and even…
To enhance the motion performance of all-terrain robots, an eccentric paddle mechanism (ePaddle) based on planet gear mechanism was designed. This letter is on the design, control scheme, and implementation of a wheel-paddle integrated quadruped robot based on the ePaddle mechanism. To ensure the re