Singapore

Dexterous grasping remains a fundamental yet challenging problem in robotics. A general-purpose robot must be capable of grasping diverse objects in arbitrary scenarios. However, existing research typically relies on restrictive assumptions, such as single-object settings or limited environments, leading to constrained generalization. We present DexGraspVLA, a hierarchical framework for general dexterous grasping in cluttered scenes based on RGB image perception and language instructions. It utilizes a pre-trained Vision-Language model as the high-level task planner and learns a diffusion-based policy as the low-level Action controller. The key insight to achieve robust generalization lies in iteratively transforming diverse language and visual inputs into domain-invariant representations via foundation models, where imitation learning can be effectively applied due to the alleviation of domain shift. Notably, our method achieves a 90+% success rate under thousands of unseen object, lighting, and background combinations in a ``zero-shot&#39;&#39; environment. Empirical analysis confirms the consistency of internal model behavior across environmental variations, thereby validating our design and explaining its generalization performance. DexGraspVLA also demonstrates free-form long-horizon prompt execution, robustness to adversarial objects and human disturbance, and failure recovery, which are rarely achieved simultaneously in prior work. Extended application to nonprehensile object grasping further proves its generality.

AAAI 2026

DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping

multimodal perception & sensor fusion

behavior learning & control

manipulation

embodied ai

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.<br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

Dexterous grasping remains a fundamental yet challenging problem in robotics. A general-purpose robot must be capable of grasping diverse objects in arbitrary scenarios. However, existing research typically relies on restrictive assumptions, such as single-object settings or limited environments, leading to constrained generalization. We present DexGraspVLA, a hierarchical framework for general dexterous grasping in cluttered scenes based on RGB image perception and language instructions. It utilizes a pre-trained Vision-Language model as the high-level task planner and learns a diffusion-based policy as the low-level Action controller. The key insight to achieve robust generalization lies in iteratively transforming diverse language and visual inputs into domain-invariant representations via foundation models, where imitation learning can be effectively applied due to the alleviation of domain shift. Notably, our method achieves a 90+% success rate under thousands of unseen object, lighting, and background combinations in a ``zero-shot'' environment. Empirical analysis confirms the consistency of internal model behavior across environmental variations, thereby validating our design and explaining its generalization performance. DexGraspVLA also demonstrates free-form long-horizon prompt execution, robustness to adversarial objects and human disturbance, and failure recovery, which are rarely achieved simultaneously in prior work. Extended application to nonprehensile object grasping further proves its generality.

technical paper

This paper addresses the challenge of estimating local surface differential properties, specifically surface normals and curvatures, from raw 3D point clouds.
Traditional methods either rely on fitting pre-defined analytic surfaces risking model bias, or directly regress normals and curvatures overlooking their intrinsic geometric correlation.
We propose a learning-based approach that locally fits osculating implicit quadrics to recover both normals and curvatures simultaneously. Drawing on classical differential geometry, we exploit the fact that every point on a $C^2$ surface admits an osculating quadric in Monge form that exactly reproduces local differential properties. However, the Monge frame itself depends on the very differential quantities being estimated. 
To bypass this circularity, we reformulate the Monge-form quadric as an implicit representation in a canonical local frame derived solely from point coordinates, enabling supervised learning without requiring Monge frame alignment. 
This reformulation allows us to construct a ground-truth dataset of such local-frame quadrics and train a neural network to predict per-point weights and offsets for a robust weighted least squares fitting process. The learned offsets account for the deviations of neighboring points from the idealized osculating surface. We further incorporate stable curvature formulations into the training loss alongside normal supervision to enhance estimation fidelity. 
Extensive experiments on diverse datasets demonstrate that our method outperforms prior approaches in normal and curvature estimation from raw point clouds.

OscuFit: Learning to Fit Osculating Implicit Quadrics for Point Clouds

Current paradigms for robotic imitation learning face a stark trade-off between the motion fidelity of diffusion models and the data scalability of inverse dynamics models. The latter, while scalable, often learns a latent action space disconnected from physical reality. This flaw leads to critical failures: temporal entanglement, where the model cannot distinguish between visually similar states requiring distinct actions, e.g., a gripper approaching versus receding from an object. This ambiguity, compounded by discretization artifacts and sensitivity to task-irrelevant dynamics, renders robust planning infeasible. We introduce LatentVLA, a vision-language-action framework designed to overcome these limitations by learning a continuous and spatiotemporally grounded latent action representation. Its progressive three-stage architecture first employs a Temporal-Attentive Latent Action Model (TA-LAM) to resolve ambiguities using language-guided attention and explicit temporal encoding. Subsequently, a Latent Action Diffusion Transformer (LADT) performs planning via diffusion directly within this continuous latent space, preserving motion fidelity without tokenization. Finally, an expert policy head translates these latent plans into precise robot actions. Experiments show LatentVLA sets a new state-of-the-art across a suite of real-world bimanual tasks, outperforming prior methods and demonstrating superior zero-shot generalization and few-shot efficiency.

LatentVLA: Taming Latent Space for Generalizable and Long-Horizon Bimanual Manipulation

We study an efficient implementation of
Multi-Armed Bandit (MAB)-based Monte-Carlo Tree Search (MCTS) for classical planning.
One weakness of MCTS is that
it spends a significant time in deciding which node to expand next.
While selecting a node from an OPEN list with $N$ nodes has
$O(1)$ runtime complexity with traditional array-based priority-queues for dense integer keys,
the tree-based OPEN list used by MCTS requires $O(\log N)$,
which roughly corresponds to the search depth $d$.
In classical planning, $d$ is arbitrarily large (e.g., $2^k-1$ in $k$-disk Tower-of-Hanoi)
and the runtime for node selection is significant,
unlike in game tree search, where the cost is negligible compared to the node evaluation (rollouts)
because $d$ is inherently limited by the game (e.g. $d\leq 361$ in Go).
To improve this bottleneck,
we propose a bilevel modification to MCTS that
runs a best-first search from each selected leaf nodes with an expansion budget proportional to $d$,
which achieves amortized $O(1)$ runtime for node selection, equivalent to traditional queue-based OPEN list.
In addition, we introduce Tree Collapsing, an enhancement that reduces action selection steps
and further improves the performance.

Bilevel MCTS for Amortized O(1) Node Selection in Classical Planning

We introduce River, a novel Condorcet-consistent voting method that is based on pairwise majority margins and can be seen as a simplified variation of Tideman's Ranked Pairs method. River is simple to explain, simple to compute even "by hand," and gives rise to an easy-to-interpret certificate in the form of a directed tree. Like Ranked Pairs and Schulze's Beat Path method, River is a refinement of the Split Cycle method and shares with those many desirable properties, including independence of clones. Unlike the other three methods, River satisfies a strong form of resistance to agenda-manipulation that is known as independence of Pareto-dominated alternatives.

The River Voting Method

Temporal graph classification is an emerging task with broad applications in neuroscience, cybersecurity, bioinformatics, and infrastructure monitoring, where systems are naturally modeled as evolving networks. While recent advances in temporal graph neural networks (TGNNs) have enabled the modeling of dynamic graph data, they often struggle to capture global structural evolution, suffer from oversmoothing, and are sensitive to noise and node permutations. In this work, we propose a novel framework that integrates tools from topological data analysis (TDA) into the temporal graph classification pipeline to address these limitations. By extracting persistent topological features from time-evolving graphs, our method captures stable, global structural patterns such as cycles and connectivity changes that are difficult for standard TGNNs to learn. These topological descriptors are then combined with neural architectures to enhance representation learning and improve classification performance. We evaluate our approach on multiple real-world datasets and demonstrate that it consistently outperforms existing TGNN models, particularly in tasks where the structural dynamics of the graph are critical to the target labels. Our results highlight the potential of topological machine learning in enriching temporal graph models with geometric and structural priors.

T3former: Temporal Graph Classification with Topological Machine Learning

Mixture-of-Experts (MoE) architecture with experts parallelism scales LLMs efficiently by activating only a subset of experts per input, avoiding proportional training costs. However, the intensive and heterogeneous communication substantially hinders the efficiency and scalability of MoE training in the resource-constrained scenario. Existing communication compression techniques fall short in MoE training due to: (\textit{i}) Intensive training amplifies compression overhead, compromising training efficiency; (\textit{ii}) Accumulated compression errors propagate through the network, degrading training quality. In this paper, we propose RCMoE, a communication-efficient \textbf{R}andom \textbf{C}ompression framework for \uline{MoE} training with two core modules:
(\textit{i}) \textit{Local-Stochastic Quantization} compresses the all-to-all communication by stochastically quantizing each row of the expert's intermediate computing results in parallel, effectively improving the compression efficiency and reducing compression error; 
(\textit{ii}) \textit{Probabilistic Thresholding Sparsification} compresses the all-reduce communication by probabilistically sampling large gradients at high probability, thereby reducing the computational complexity and maintaining the convergence efficiency. 
Experiments on four typical MoE training tasks prove that RCMoE achieves higher 5.9$\times$-8.1$\times$ total communication compression ratios and 1.3$\times$-10.1$\times$ training speedup compared with the state-of-the-art compression techniques while maintaining the MoE training accuracy.

RCMoE: A Communication-Efficient Random Compression Framework for Resource-Constrained Mixture-of-Experts Training

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we leverage new results from off-policy evaluation; it has recently been shown that well-designed behaviour policies can be used to collect off-policy data for provably lower variance return estimates. This result is surprising as it means collecting data on-policy is not variance optimal. We extend this key insight to the online reinforcement learning setting, where both policy evaluation and improvement are interleaved to learn optimal policies. Off-policy RL has been well studied (e.g., IMPALA), with correct and truncated importance weighted samples for de-biasing and managing variance appropriately. Generally these approaches are concerned with reconciling data collected from multiple workers in parallel, while the policy is updated asynchronously, mismatch between the workers and policy is corrected in a mathematically sound way. Here we consider only one worker - the behaviour policy, which is used to collect data for policy improvement, with provably lower variance return estimates. In our experiments we extend two policy-gradient methods with this regime, demonstrating better sample efficiency and performance over a diverse set of environments.

Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning

Existing large language model (LLM)-based table question answering (TableQA) methods primarily involve decomposition reasoning and answer verification processes. However, decomposing questions solely at the semantic level, without considering the factual evidence in tables, fails to significantly reduce the difficulty for LLMs in understanding the key information in questions. Furthermore, reasoning and verification without supporting factual evidence are often arbitrary and unreliable. In light of these issues, this paper proposes a Syllogism-Inspired Reasoning and Verification method (SIRV), which performs reliable decomposition reasoning and answer verification based on the evidential concept of syllogism. Specifically, SIRV extracts question-relevant factual evidence from the table to construct the premises. Based on the constructed premises, SIRV plans reasoning paths and generates sub-questions that explicitly indicate relevant factual evidence, performing evidence-centered reasoning. Additionally, SIRV examines the consistency between the premises and the table to focus on factual evidence, thereby reliably identifying and correcting errors in the reasoning process. Compared to state-of-the-art methods, SIRV achieves performance improvements of up to 5.24% in single-mode and 2.89% in joint reasoning, while also demonstrating excellent generalization ability and efficiency.

Syllogism-Inspired TableQA: Evidentialization Makes Decomposition Reasoning and Answer Verification More Reliable

With the growing role of artificial intelligence in climate and weather research, efficient model training and inference are in high demand. Current models like FourCastNet and AI-GOMS depend heavily on GPUs, limiting hardware independence, especially for Chinese domestic hardware and frameworks. To address this issue, we present a framework for migrating large-scale atmospheric and oceanic models from PyTorch to MindSpore and optimizing for Chinese chips, and evaluating their performance against GPUs. The framework focuses on software-hardware adaptation, memory optimization, and parallelism. Furthermore, the model's performance is evaluated across multiple metrics, including training speed, inference speed, model accuracy, and energy efficiency, with comparisons against GPU-based implementations. Experimental results demonstrate that the migration and optimization process preserves the models' original accuracy while significantly reducing system dependencies and improving operational efficiency by leveraging Chinese chips as a viable alternative for scientific computing. This work provides valuable insights and practical guidance for leveraging Chinese domestic chips and frameworks in atmospheric and oceanic AI model development, offering a pathway toward greater technological independence.

Deploying Atmospheric and Oceanic AI Models on Chinese Hardware and Framework: Migration Strategies, Performance Optimization and Analysis

This paper discusses the integration challenges and
strategies for designing mobile robots, by focusing on the
task-driven, optimal selection of hardware and software to
balance safety, efficiency, and minimal usage of resources
such as costs, energy, computational requirements, and
weight. We emphasize the interplay between perception and
motion planning in decision-making by introducing the
concept of occupancy queries to quantify the perception
requirements for sampling-based motion planners. Sensor and
algorithm performance are evaluated using False Negative
Rate (FNR) and False Positive Rate (FPR) across various
factors such as geometric relationships, object properties,
sensor resolution, and environmental conditions. By
integrating perception requirements with perception
performance, an Integer Linear Programming (ILP) approach
is proposed for efficient sensor and algorithm selection
and placement. This forms the basis for a co-design
optimization that includes the robot body, motion planner,
perception pipeline, and computing unit. We refer to this
framework for solving the co-design problem of mobile
robots as CODEI, short for Co-design of Embodied
Intelligence. A case study on developing an Autonomous
Vehicle (AV) for urban scenarios provides actionable
information for designers, and shows that complex tasks
escalate resource demands, with task performance affecting
choices of the autonomy stack. The study demonstrates that
resource prioritization influences sensor
choice: cameras are preferred for cost-effective and
lightweight designs, while lidar sensors are chosen for
better energy and computational efficiency.

Downloads

Next from AAAI 2026

OscuFit: Learning to Fit Osculating Implicit Quadrics for Point Clouds

Similar lecture

Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors