Singapore

Vision-Language-Action (VLA) models based on flow matching have shown excellent performance in general-purpose robotic manipulation tasks. However, the action ac- curacy of these models on complex downstream tasks is unsatisfactory. One important reason is that these models rely solely on the post-training paradigm of imitation learning, which makes it difficult to have a deeper understanding of the distribution properties of data quality, which is exactly what Reinforcement Learning (RL) excels at. In this paper, we theoretically propose an offline RL post-training objective for VLA flow models and induce an efficient and feasible offline RL fine-tuning algorithm −− Adaptive Reinforced Flow Matching (ARFM). By introducing an adaptively adjusted scaling factor in the VLA flow model loss, we construct a principled bias-variance trade-off objective function to optimally control the impact of RL signal on flow loss. ARFM adaptively balances RL advantage preservation and flow loss gradient variance control, resulting in a more stable and efficient fine-tuning process. Extensive simulation and real-world experimental results show that ARFM exhibits excellent generalization, robustness, few-shot learning, and continuous learning performance.

AAAI 2026

Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models

manipulation

embodied ai

reinforcement learning

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.

poster

The widespread deployment of machine learning systems in critical real-world decision-making applications has highlighted the urgent need for counterfactual explainability methods that operate effectively. Global counterfactual explanations, expressed as actions to offer recourse, aim to provide succinct explanations and insights applicable to large population subgroups. High effectiveness, measured by the fraction of the population that is provided recourse, ensures that the actions benefit as many individuals as possible. Keeping the cost of actions low ensures the proposed recourse actions remain practical and actionable. Limiting the number of actions that provide global counterfactuals is essential to maximize interpretability. The primary challenge, therefore, is to balance these trade-offs—maximizing effectiveness, minimizing cost, while maintaining a small number of actions. We introduce $\texttt{GLANCE}$, a versatile and adaptive algorithm that employs a novel agglomerative approach, jointly considering both the feature space and the space of counterfactual actions, thereby accounting for the distribution of points in a way that aligns with the model's structure. This design enables the careful balancing of the trade-offs among the three key objectives, with the size objective functioning as a tunable parameter to keep the actions few and easy to interpret. Our extensive experimental evaluation demonstrates that $\texttt{GLANCE}$ consistently shows greater robustness and performance compared to existing methods across various datasets and models.

GLANCE: Global Actions in a Nutshell for Counterfactual Explainability

Vision-language fine-tuning has emerged as an efficient paradigm for constructing multimodal foundation models. While textual context often highlights semantic relationships within an image, existing fine-tuning methods typically overlook this information when aligning vision and language, thus leading to suboptimal performance. Toward solving this problem, we propose a method that can improve multimodal alignment and fusion based on both semantics and relationships.Specifically, we first extract multilevel semantic features from different vision encoder to capture more visual cues of the relationships. Then, we learn to project the vision features to group related semantics, among which are more likely to have relationships. Finally, we fuse the visual features with the textual by using inheritable cross-attention, where we globally remove the redundant visual relationships by discarding visual-language feature pairs with low correlation. We evaluate our proposed method on eight foundation models and two downstream tasks, visual question answering and image captioning, and show that it outperforms all existing methods.

Remodeling Semantic Relationships in Vision-Language Fine-Tuning

Graph data often exhibits complex geometric heterogeneity, where structures with varying local curvature, such as tree-like hierarchies and dense communities, coexist within a single network. Existing geometric GNNs, which embed graphs into single fixed-curvature manifolds or discrete product spaces, struggle to capture this diversity. We introduce Adaptive Riemannian Graph Neural Networks (ARGNN), a novel framework that learns a continuous and anisotropic Riemannian metric tensor field over the graph. It allows each node to determine its optimal local geometry, enabling the model to fluidly adapt to the graph's structural landscape. Our core innovation is an efficient parameterization of the node-wise metric tensor, specializing to a learnable diagonal form that captures directional geometric information while maintaining computational tractability. To ensure geometric regularity and stable training, we integrate a Ricci flow-inspired regularization that smooths the learned manifold. Theoretically, we establish the rigorous geometric evolution convergence guarantee for ARGNN and provide a continuous generalization that unifies prior fixed or mixed-curvature GNNs. Empirically, our method demonstrates superior performance on both homophilic and heterophilic benchmark datasets with the ability to capture diverse structures adaptively. Moreover, the learned geometries both offer interpretable insights into the underlying graph structure and empirically corroborate our theoretical analysis.

Adaptive Riemannian Graph Neural Networks

The prediction of compound–protein interactions (CPIs) is crucial for drug discovery. Most existing CPI prediction models rely on protein sequence information as input. However, in early-stage drug development, particularly in phenotype-driven studies or compound-response analyses, proteins are often annotated only with functional labels, and their sequences remain undetermined. Consequently, current methods are inapplicable in such scenarios. Furthermore, our experiments find that even when large-scale perturbations were applied to protein sequences, the predictive performance of the existing models did not show a significant decline. It indicates that the high investment in sequencing may not bring corresponding returns. To address the above issues, we propose an inexpensive, protein-sequencing-free framework BioText-CPI, based on the Biomedical Textual description of protein for CPI prediction. Firstly, during the pre-training stage of the model, we use contrastive learning to align protein texts and sequence modalities. Subsequently, we add biological text descriptions of proteins to the existing public CPI dataset to construct a new CPI dataset. Finally, in the CPI prediction stage, the sequence and biomedical text descriptions of proteins can be used as the input for CPI prediction either separately or simultaneously to meet the application requirements of different scenarios. The experiments demonstrate that BioText-CPI achieves comparable effects to the traditional methods when only the biomedical description of protein is input. Moreover, when the two modalities of protein information are input simultaneously, BioText-CPI achieves state-of-the-art performance across multiple scenarios. The source code and data are accessible through the supplementary material.

Sequence-Free for Compound Protein Interaction Prediction

While Large Reasoning Models (LRMs) exhibit remarkable capabilities in complex tasks, they often suffer from excessive redundancy in their chain-of-thought reasoning. This significantly reduces inference efficiency and increases computational costs. We identify that LRM redundancy is not uniformly homogeneous but can be taxonomized according to whether it is destructive to the final answer: destructive redundancy (e.g., logical drift, hallucination amplification) versus non-destructive redundancy (e.g., repetition, over-elaboration). Moreover, LRM's redundant and concise responses exhibit a significant distinction in their hidden layer representation spaces.
Based on these insights, we propose CATS (Category-Aware Token-level Steering), a training-free and lightweight method to reduce the redundancy phenomenon. CATS decomposes redundancy into six semantically interpretable characteristic dimensions. By flexibly weighting and combining the differential vectors corresponding to these dimensions, CATS synthesizes a composite intervention vector, enabling zero-parameter intervention in the hidden layers. Experiments across three LRM models and five mathematical reasoning datasets demonstrate that CATS reduces reasoning length by an average of 25% while maintaining or even slightly improving task accuracy. CATS offers a pluggable, training-free, and lightweight solution, making it particularly beneficial for users in low-resource environments.

CATS: Category-Aware Token-level Steering for Training-Free Redundancy Reduction in Large Reasoning Models

We study the common generalization of Markov decision processes (MDPs) with sets of transition probabilities, known as robust MDPs (RMDPs). A standard goal in RMDPs is to compute a policy that maximizes the expected return under an adversarial choice of the transition probabilities. If the uncertainty in the probabilities is independent between the states, known as s-rectangularity, such optimal robust policies can be computed efficiently using robust value iteration. However, there might still be multiple optimal robust policies, which, while equivalent with respect to the worst-case, reflect different expected returns under non-adversarial choices of the transition probabilities. Hence, we propose a refined policy selection criterion for RMDPs, drawing inspiration from the notions of dominance and best-effort in game theory. Instead of seeking a policy that only maximizes the worst-case expected return, we additionally require the policy to achieve a maximal expected return under different (i.e., not fully adversarial) transition probabilities. We call such a policy an optimal robust best-effort (ORBE) policy. We prove that ORBE policies always exist, characterize their structure, and present an algorithm to compute them with a small overhead over standard robust value iteration. ORBE policies offer a principled tie-breaker among optimal robust policies. Numerical experiments show the feasibility of our approach.

Best-Effort Policies for Robust Markov Decision Processes

In recent years, Cross-Modal Retrieval (CMR) has made significant progress in the field of multi-modal analysis. However, since it is time-consuming and labor-intensive to collect large-scale and well-annotated data, the annotation of multi-modal data inevitably contains some noise. This will degrade the retrieval performance of the model. To tackle the problem, numerous robust CMR methods have been developed, including robust learning paradigms, label calibration strategies, and instance selection mechanisms. Unfortunately, they often fail to simultaneously satisfy model performance ceilings, calibration reliability, and data utilization rate. To overcome the limitations, we propose a novel robust cross-modal learning framework, namely Neighbor-aware Instance Refining with Noisy Labels (NIRNL). Specifically, we first propose Cross-modal Margin Preserving (CMP) to adjust the relative distance between positive and negative pairs, thereby enhancing the discrimination between sample pairs. Then, we propose Neighbor-aware Instance Refining (NIR) to identify pure subset, hard subset, and noisy subset through cross-modal neighborhood consensus. Afterward, we construct different tailored optimization strategies for this fine-grained partitioning, thereby maximizing the utilization of all available data while mitigating error propagation. Extensive experiments on three benchmark datasets demonstrate that NIRNL achieves state-of-the-art performance, exhibiting remarkable robustness, especially under high noise rates.

Neighbor-aware Instance Refining with Noisy Labels for Cross-Modal Retrieval

Current unsupervised time series clustering methods often struggle to fully exploit the inherent characteristics of time series data and commonly adopt a two-stage training strategy that separates feature learning from the clustering process. To address these limitations, this paper proposes a novel deep clustering framework, \textbf{T}ime-\textbf{F}requency augmented \textbf{M}ulti-level \textbf{C}ontrastive \textbf{C}lustering (TFMCC). TFMCC employs a multi-scale time-frequency augmentation strategy, where each training iteration stochastically selects time and frequency scales to generate diverse augmented views, enhancing the model’s ability to learn robust and generalizable representations. In addition, a multi-level contrastive learning mechanism is introduced to jointly capture temporal dependencies, inter-sample similarities, and cluster structures. By jointly optimizing these components, TFMCC enables the learning of temporally-aware and clustering-friendly representations. Experimental results on 40 benchmark datasets demonstrate that TFMCC outperforms six existing methods in clustering accuracy.

Time-Frequency Augmented Multi-level Contrastive Clustering for Time Series

Ensuring alignment with human values is essential for modern large language models (LLMs), especially amid growing concerns around AI safety and social impact. Yet achieving such alignment remains challenging due to the limited, noisy, and often conflicting nature of human feedback from diverse annotators. Most existing approaches, such as Direct Preference Optimization (DPO), assume consistent and conflict-free supervision, overlooking the ambiguity, inconsistency, and value trade-offs inherent in real-world preferences—often leading to reduced robustness and exclusion of minority views.
To address this, we propose **FGD-Align**, a novel pluralistic alignment framework grounded in Fuzzy Group Decision-Making theory. Our approach rigorously models and aggregates human preferences while retaining the complexity of real-world value trade-offs. Unlike traditional methods that rely on coarse-grained preference pairs, FGD-Align introduces fuzzy preference modeling via triangular fuzzy numbers to capture nuanced, multi-criteria human judgments. We further develop a new training objective, Probabilistic Fuzzy DPO, which incorporates fuzzy preference strength as adaptive loss weights and gradient filters, enhancing robustness to ambiguity and inconsistency in feedback. 
Comprehensive experiments demonstrate that FGD-Align consistently outperforms both DPO variants and advanced preference aggregation methods in terms of preference accuracy and robustness to ambiguity. It achieves superior alignment stability and better preserves minority preferences, all with minimal computational overhead.
Our work bridges the gap between algorithmic tractability and the nuanced landscape of human values, enabling more scalable, inclusive, and socially-aware AI alignment.

FGD-Align: Pluralistic Alignment for Large Language Models via Fuzzy Group Decision-Making

The rapid advancement of Large Vision Language Models (LVLMs) has demonstrated excellent abilities in various visual tasks. Building upon these developments, the \textit{thinking with images} paradigm has emerged, enabling models to dynamically edit and re-encode visual information at each reasoning step, mirroring human visual processing. However, this paradigm also introduces significant challenges as diverse errors may occur during reasoning processes. This naturally necessitates Process Reward Models (PRMs) as an essential pattern for distinguishing positive and negative reasoning steps, yet existing benchmarks for PRMs are predominantly text-centric and lack comprehensive assessment of PRMs' capabilities under this paradigm,~\ourbench. To address these gaps, this work introduces the first comprehensive benchmark specifically designed for evaluating PRMs under \textit{thinking with images} paradigm. Our main contributions are as follows: (1) Through extensive analysis of reasoning trajectories under \textit{thinking with images} paradigm and guided search experiments with PRMs, we define 7 fine-grained error types and demonstrate both the necessity for specialized PRMs and the potential for improvement. (2) We construct and curate a comprehensive benchmark comprising 1,134 manually annotated high-quality thinking with images reasoning trajectories spanning 4 categories and 16 subcategories for fine-grained evaluation of PRMs. (3) Our comprehensive experimental analysis reveals that current LVLMs fall short as effective PRMs, exhibiting limited capabilities in visual reasoning process evaluation with significant performance disparities across error types, consistent positive evaluation bias, and notable sensitivity to reasoning step positions. These findings demonstrate the effectiveness of our benchmark and establish crucial foundations for advancing PRMs in LVLMs.

Downloads

Next from AAAI 2026

GLANCE: Global Actions in a Nutshell for Counterfactual Explainability

Similar lecture

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2026

GLANCE: Global Actions in a Nutshell for Counterfactual Explainability

Similar lecture

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

Downloads