Singapore

Parameter-Efficient finetuning (PEFT) enhances model performance on downstream tasks by updating a minimal subset of parameters. Representation finetuning (ReFT) methods further improve efficiency by freezing model weights and optimizing internal representations with fewer parameters than PEFT, outperforming PEFT on several tasks. However, ReFT exhibits a significant performance decline on mathematical reasoning tasks. To address this problem, the paper demonstrates that ReFT&#39;s poor performance on mathematical tasks primarily stems from its struggle to generate effective reasoning prefixes during the early inference phase. Moreover, ReFT disturbs the numerical encoding and the error accumulats during the CoT stage. Based on these observations, this paper proposes Bias-REstrained Prefix Representation FineTuning (BREP ReFT), which enhances ReFT&#39;s mathematical reasoning capability by truncating training data to optimize the generation of initial reasoning prefixes, intervening on the early inference stage to prevent error accumulation, and constraining the intervention vectors&#39; magnitude to avoid disturbing numerical encoding. Extensive experiments across diverse model architectures demonstrate BREP&#39;s superior effectiveness, efficiency, and robust generalization capability, outperforming both standard ReFT and weight-based PEFT methods on the task of mathematical reasoning.

AAAI 2026

Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning

Parameter-Efficient finetuning (PEFT) enhances model performance on downstream tasks by updating a minimal subset of parameters. Representation finetuning (ReFT) methods further improve efficiency by freezing model weights and optimizing internal representations with fewer parameters than PEFT, outperforming PEFT on several tasks. However, ReFT exhibits a significant performance decline on mathematical reasoning tasks. To address this problem, the paper demonstrates that ReFT's poor performance on mathematical tasks primarily stems from its struggle to generate effective reasoning prefixes during the early inference phase. Moreover, ReFT disturbs the numerical encoding and the error accumulats during the CoT stage. Based on these observations, this paper proposes Bias-REstrained Prefix Representation FineTuning (BREP ReFT), which enhances ReFT's mathematical reasoning capability by truncating training data to optimize the generation of initial reasoning prefixes, intervening on the early inference stage to prevent error accumulation, and constraining the intervention vectors' magnitude to avoid disturbing numerical encoding. Extensive experiments across diverse model architectures demonstrate BREP's superior effectiveness, efficiency, and robust generalization capability, outperforming both standard ReFT and weight-based PEFT methods on the task of mathematical reasoning.

poster

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.

Prompt-based offline methods are commonly used to optimize large language model (LLM) responses, but evaluating these responses is computationally intensive and often fails to accommodate diverse response styles. This study introduces a novel online evaluation framework that employs a multi-agent conversational bandit model to select optimal responses while aligning with user preferences dynamically.
To tackle challenges such as high-dimensional features, large response sets, adaptive conversational needs, and multi-device access, we propose MACO, Multi-Agent Conversational Online Learning, which comprises two key components: (1) \texttt{MACO-A}: Executed by local agents, it employs an online elimination mechanism to filter out low-quality responses.
(2) \texttt{MACO-S}: Executed by the cloud server, it adaptively adjusts selection strategies based on aggregated preference data. An adaptive preference mechanism triggers asynchronous conversations to enhance alignment efficiency. Theoretical analysis demonstrates that MACO achieves near-optimal regret bounds, matching state-of-the-art performance in various degenerate cases. 
Extensive experiments utilizing Google and OpenAI text embedding models on the real-world datasets with different response styles, combined with Llama and GPT-4o, show that MACO consistently outperforms baseline methods by at least 8.29\% across varying response set sizes and numbers of agents.

A Multi-Agent Conversational Bandit Approach to Online Evaluation and Selection of User-Aligned LLM Responses

Diffusion policies have recently shown great promise for generating actions in robotic manipulation. However, existing approaches often rely on global instructions to produce short-term control signals, which can result in misalignment in action generation. We conjecture that the primitive skills, referred to as fine-grained, short-horizon manipulations, such as "move up" and "open the gripper", provide a more intuitive and effective interface for robot learning. To bridge this gap, we propose SDP, a skill-conditioned diffusion policy that integrates interpretable skill learning with conditional action planning. SDP abstracts eight reusable primitive skills across tasks and employs a vision-language model to extract discrete representations from visual observations and language instructions. Based on the representations, a lightweight router network is designed to assign a desired primitive skill for each state, which helps construct a single-skill policy to generate skill-aligned actions. By decomposing complex tasks into a sequence of primitive skills and selecting a single-skill policy, the proposed SDP ensures skill-consistent behavior across diverse tasks.
Extensive experiments on two challenging simulation benchmarks and real-world robot deployments demonstrate that SDP consistently outperforms state-of-the-art methods, providing a new paradigm for skill-based robot learning with diffusion policies.

Learning Diffusion Policy from Primitive Skills for Robot Manipulation

Machine learning methods have been increasingly applied to solve Vehicle Routing Problems (VRPs). A high-efficiency approach is to learn solution construction using deep neural networks. However, their tendency toward premature convergence is a critical barrier, severely hindering generalization across diverse distributions and scales. To overcome this, we introduce Elite-Pattern Reinforcement (EPR), a novel strategy designed to create a synergy between the diverse, exploratory nature of reinforcement learning and the high-quality, structured knowledge from classical heuristics. The strategy guides the learning process by reinforcing structural patterns from elite solutions, employing an elite-guided score modulation to integrate this external knowledge. The inherent symmetry of path patterns is also exploited to augment the structural information. This steers the policy away from premature convergence by enabling it to distinguish and favour elite path patterns over inferior ones. Integrating our strategy with four construction methods yields substantial performance improvements on the CVRPLIB and TSPLIB benchmarks. Furthermore, our approach outperforms state-of-the-art learning-based methods, demonstrating superior generalization across diverse distributions and scales.

Elite Pattern Reinforcement for Vehicle Routing Problems

Visual neural decoding seeks to reconstruct or infer perceived visual stimuli from brain activity patterns, providing critical insights into human cognition and enabling transformative applications in brain-computer interfaces and artificial intelligence. Current approaches, however, remain constrained by the scarcity of high-quality stimulus-brain response pairs and the inherent semantic mismatch between neural representations and visual content. Inspired by perceptual variability and co-adaptive strategy of the biological systems, we propose a novel self-supervised architecture, named NeuroBridge, which integrates Cognitive Prior Augmentation (CPA) with Shared Semantic Projector (SSP) to promote effective cross-modality alignment. Specifically, CPA simulates perceptual variability by applying asymmetric, modality-specific transformations to both EEG signals and images, enhancing semantic diversity. Unlike previous approaches, SSP establishes a bidirectional alignment process through a co-adaptive strategy, which mutually aligns features from two modalities into a shared semantic space for effective cross-modal learning. NeuroBridge surpasses previous state-of-the-art methods under both intra-subject and inter-subject settings. In the intra-subject scenario, it achieves the improvements of 12.3% in top-1 accuracy and 10.2% in top-5 accuracy, reaching 63.2% and 89.9% respectively on a 200-way zero-shot retrieval task. Extensive experiments demonstrate the effectiveness, robustness, and scalability of the proposed framework for neural visual decoding.

NeuroBridge: Bio-Inspired Self-Supervised EEG-to-Image Decoding via Cognitive Priors and Bidirectional Semantic Alignment

Text-Attributed Graphs (TAGs) are graphs where both nodes and edges are associated with text attributes. To leverage their semantic richness, recent efforts have integrated large language models (LLMs) with graph neural networks, leading to the development of GraphLLMs. However, many real-world datasets remain inaccessible, and processing text-attributed graphs while ensuring privacy and efficiency remains a challenge. To address this, we place TAGs within a federated environment, referred to as TAG-FGL. Despite its potential, TAG-FGL remains largely underexplored in the face of adversarial threats. In this work, we introduce GTAE, a novel attack framework that cascades influence-guided topological perturbations and embedding-level text refinements to generate transferable, modality-agnostic adversarial inputs. To defend against these threats, we propose STRUM, a defense strategy that combines local adversarial training with robustness-aware aggregation, enhancing resilience at both the node and system levels. Extensive experiments on five real-world datasets with diverse model backbones demonstrate that GTAE significantly degrades model performance, while STRUM consistently improves robustness.

Towards Robust Text-Attributed Federated Graph Learning: Multimodal Threats and Defense

The Euclidean Shortest Path Problem (ESPP) is a classic problem which requires finding the shortest path in a Euclidean plane with polygonal obstacles. The state-of-the-art solution, Euclidean Hub Labeling (EHL), offers ultra-fast query performance but comes with significant memory overhead, requiring up to tens of gigabytes of storage on large maps, limiting its use in memory-constrained environments like mobile phones. Additionally, EHL's memory usage can only be determined after index construction, and while it provides a memory-runtime tradeoff, it does not fully optimize memory utilization.
In this work, we introduce an improved version of EHL, called EHL*, which overcomes these limitations. A key contribution of EHL* is its ability to create an index that adheres to a specified memory budget while optimizing query runtime performance. Moreover, EHL* can leverage pre-known query distributions, a common scenario in many real-world applications, to further enhance runtime efficiency. Our results show that EHL* can reduce memory usage by up to 10-20 times without much impact on query runtime performance compared to EHL, making it a highly effective solution for optimal pathfinding in memory-constrained environments.
We also present a theoretical analysis comparing EHL* with EHL, providing insights into their indexing and query processing cost.

EHL*: Memory-Budgeted Indexing for Ultrafast Optimal Euclidean Pathfinding

Although recent studies have explored anomaly generation to address the scarcity of anomaly images in real-world data, existing methods typically suffer from at least one of the following limitations, hindering their practical deployment: (1) lack of visual realism in generated anomalies; (2) dependence on large amounts of real images; and (3) use of memory-intensive, heavyweight model architectures. To overcome these limitations, we propose AnoStyler, a lightweight yet effective method that frames zero-shot anomaly generation as text-guided style transfer. Given a single normal image along with its category label and expected defect type, an anomaly mask indicating the localized anomaly regions and two-class text prompts representing the normal and anomaly states are generated using generalizable category-agnostic procedures. A lightweight U-Net model trained with CLIP-based loss functions is used to stylize the normal image into a visually realistic anomaly image, where anomalies are localized by the anomaly mask and semantically aligned with the text prompts. Extensive experiments on the MVTec-AD and VisA datasets show that AnoStyler outperforms existing anomaly generation methods in generating high-quality and diverse anomaly images. Furthermore, using these generated anomalies helps enhance anomaly detection performance.

AnoStyler: Text-Driven Localized Anomaly Generation via Lightweight Style Transfer

Mitigating the negative impact of noisy labels has been a perennial issue in supervised learning.
Robust loss functions have emerged as a prevalent solution to this problem. 
In this work, we introduce the *Variation Ratio* as a novel property related to the robustness of loss functions, and propose a new family of robust loss functions, termed *Variation-Bounded Loss* (VBL), which is characterized by a bounded variation ratio.
We provide theoretical analyses of the variation radio, proving that a smaller variation ratio would lead to better robustness.
Furthermore, we reveal that the variation ratio provides a feasible method
to relax the symmetric condition and offers a more
concise path to achieve the asymmetric condition.
Based on the variation ratio, we reformulate several commonly used loss functions into a variation-bounded form for pract ical applications. 
Positive experiments on various datasets exhibit the effectiveness and flexibility of our approach.

Variation-Bounded Loss for Noise-Tolerant Learning

Infrared and visible image fusion (IVIF) technology has become a frontier of great interest due to the ability to integrate information from multiple sources. However, the progressive slowdown of weight updates in deep networks (i.e., “network laziness” phenomenon), makes existing methods far from realizing the full characterization potential. To this end, we propose a lightweight fusion method for IVIF, Anti-Inert Dynamic Fusion (AIDFusion), to fully utilize the potential of the network at all levels. Specifically, by progressively regulating the collaborative Learning process of multi-level prediction in the network, Dynamic Inertia Inhibition Learning Strategy (DIILS) is proposed to adaptively and efficiently inhibit inertia accumulation. Subsequently, to deeply explore the representation potential while breaking through the performance threshold, lightweight Multi-dimensional modulation fusion module (MMFM) is specifically proposed to capture comprehensive multi-view and multi-scale features efficiently. Finally, considering the semantic bias between the prediction maps of DIILS and the fusion feature of MMFM, Fourier Analysis Convolution (FAConv) is designed in feature recovery as a bridge between prediction and fusion to accomplish the implicit periodic modeling. Based on the above study, extensive experiments on three public IVIF datasets demonstrate the dual advantages of AIDFusion in terms of fusion performance and computational overhead compared to state-of-the-art baseline methods.

Revisiting Network Inertia: Dynamic Inertia Inhibition Coupled Multidimensional Periodicity for Infrared and Visible Image Fusion

We propose a method for extracting monosemantic neurons, defined as latent dimensions aligned with coherent and interpretable concepts, from user and item embeddings in recommender systems. Our approach uses a Sparse Autoencoder (SAE) to disentangle semantic structure from pretrained representations. Unlike prior work on language models, monosemanticity in recommendation requires preserving interactions between distinct user and item embeddings. To address this, we introduce a prediction-aware training objective that backpropagates through a frozen recommender, aligning latent structure with affinity behavior. The resulting neurons capture actionable properties, such as genre, popularity, and recency, and enable post hoc control operations like targeted filtering or promotion without modifying the base model. Our method generalizes across recommendation models and datasets, offering a practical tool for interpretable and controllable personalization.

Content not yet available

Downloads

Next from AAAI 2026

A Multi-Agent Conversational Bandit Approach to Online Evaluation and Selection of User-Aligned LLM Responses

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

.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

A Multi-Agent Conversational Bandit Approach to Online Evaluation and Selection of User-Aligned LLM Responses

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads