Singapore

Modern large vision-language models (LVLMs) convert each input image into a large set of tokens, far outnumbering the text tokens. Although this improves visual perception, it introduces severe image token redundancy. Because image tokens carry sparse information, many add little to reasoning, yet greatly increase inference cost. The emerging image token pruning methods tackle this issue by identifying the most important tokens and discarding the rest. These methods can raise efficiency with only modest performance loss. However, most of them only consider single-image tasks and overlook multimodal in-context learning (ICL), where redundancy is greater and efficiency is more critical. Redundant tokens weaken the advantage of multimodal ICL for rapid domain adaptation and cause unstable performance. Applying existing pruning methods in this setting leads to large accuracy drops, exposing a clear gap and the need for new techniques. Thus, we propose Contextually Adaptive Token Pruning (CATP), a training-free pruning method targeted at multimodal ICL. CATP consists of two stages that perform progressive pruning to fully account for the complex cross-modal interactions in the input sequence. After removing 77.8\% of the image tokens, CATP produces an average performance gain of 0.6\% over the vanilla model on four LVLMs and eight benchmarks, exceeding all baselines remarkably. Meanwhile, it effectively improves efficiency by achieving an average reduction of 10.78\% in inference latency. CATP enhances the practical value of multimodal ICL and lays the groundwork for future progress in interleaved image-text scenarios.

AAAI 2026

CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning

ml: multimodal learning

cv: multi-modal vision

cv: language and vision

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.

technical paper

Domain-adaptive person search (DAPS) aims to transfer pedestrian detection and re-identification capabilities from a labeled source domain to an unlabeled target domain, yet faces critical challenges from domain shift: semantic confusion among overlapping instances, over-reliance on shallow features for look-alike targets, and poor discriminability of small-scale instances. To address these issues, we propose the Localization-Anchored Instance Discrimination (LAID) framework, which leverages spatial relationships between bounding boxes as auxiliary signals to enhance instance identity learning.
LAID integrates three complementary strategies: 1) Cost-Aware Instance Matching (CAIM) uses IoU-based global optimal assignment to align current detections with historical identities, reducing overlap-induced misassociations; 2) Dual-Scope Contrastive Learning (DSCL) combines spatial separation constraints (for geometrically distant pairs) with global contrastive learning, prompting the model to learn deep discriminative features beyond superficial similarities; 3) Task-Sensitivity Alignment (TSA) aligns confidence distributions of detection and ReID heads via KL divergence, ensuring consistent pseudo-label generation.
Extensive experiments on CUHK-SYSU and PRW datasets demonstrate that LAID outperforms state-of-the-art DAPS methods, validating its effectiveness in mitigating domain shift and narrowing the performance gap between supervised and domain-adaptive person search.

Localization-Anchored Instance Discrimination for Domain Adaptive Person Search

Generating expressive and controllable human speech is one of the core goals of generative artificial intelligence, but its progress has long been constrained by two fundamental challenges: the deep entanglement of speech factors and the coarse granularity of existing control mechanisms. To overcome these challenges, we have proposed a novel framework called MF-Speech, which consists of two core components: MF-SpeechEncoder and MF-SpeechGenerator. MF-SpeechEncoder acts as a factor purifier, adopting a multi-objective optimization strategy to decompose the original speech signal into highly pure and independent representations of content, timbre, and emotion. Subsequently, MF-SpeechGenerator functions as a conductor, achieving precise, composable and fine-grained control over these factors through dynamic fusion and Hierarchical Style Adaptive Normalization (HSAN). Experiments demonstrate that in the highly challenging multi-factor compositional speech generation task, MF-Speech significantly outperforms current state-of-the-art methods, achieving a lower word error rate (WER=4.67\%), superior style control (SECS=0.5685, Corr=0.68), and the highest subjective evaluation scores (nMOS=3.96, sMOS$_t$=3.86, sMOS$_e$=3.78). Furthermore, the learned discrete factors exhibit strong transferability, demonstrating their significant potential as a general-purpose speech representation.

MF-Speech: Achieving Fine-Grained and Compositional Control in Speech Generation via Factor Disentanglement

3D Gaussian Splatting (3DGS) achieves high-fidelity novel view synthesis, but its application in online long-sequence scenarios is still restricted. Existing methods either rely on slow per-scene optimization or lack efficient frame-wise 3DGS updates, making them unsuitable for online long-sequence videos. In this paper, we propose LongSplat, an online real-time 3D Gaussian reconstruction framework designed for long-sequence image input. The core idea of LongSplat is to maintain a global 3DGS set and design a streaming 3DGS update mechanism that selectively compressing redundant historical Gaussians and introducing new Gaussians by comparing the current observations with the historical Gaussian. To achieve this goal, we design a Gaussian-Image Representation (GIR), which encodes 3D Gaussian parameters into a structured, image-like 2D format. GIR simultaneously enables identity-aware redundancy compression as well as the fusion of current view and historical Gaussians, which are used for online reconstruction and adapt the model to long sequences without overwhelming memory or computational costs. Extensive experiments demonstrate that LongSplat achieves state-of-the-art efficiency-quality trade-offs in real-time novel view synthesis, delivering real-time reconstruction while reducing Gaussian counts by 44% compared to our baseline methods DepthSplat.

LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images

Synthesizing realistic 12-lead electrocardiogram (ECG) data is a complex task due to the intricate spatial and temporal dynamics of cardiac electrophysiology. Traditional generative models often struggle to capture the nuanced interdependencies among ECG leads, which are essential for accurate medical analysis. 
In this paper, we propose Physics-Inspired Partial Differential Equation GAN for Multilead ECG Synthesis (PhysioPDE-GAN), a generative framework designed to model the spatiotemporal structure of multilead ECG signals by incorporating physiological priors and spatial constraints directly into the generative process.
By embedding PDE-based representations directly into the generative process, our approach effectively captures both the temporal evolution and spatial relationships between ECG leads. 
We conduct extensive experiments to evaluate the performance of various base classifiers trained on the synthetic 12-lead ECG data generated by PhysioPDE-GAN. These classifiers outperform those trained on data produced by other conventional methods, achieving statistically significant improvements in detecting cardiac abnormalities. Our work highlights the potential of combining PDE-driven cardiac models with advanced generative techniques to enhance the quality and utility of synthetic biomedical datasets.

PDE-Driven Spatiotemporal Generative Modeling for Multilead ECG Synthesis

Graph Neural Networks (GNNs) have demonstrated impressive success across a range of graph-based tasks. However, their performance in node classification typically relies on enough high-quality labeled data which are difficult to obtain in practice. Self-training emerges as a promising solution to tackle the issue of label scarcity. Most existing studies in this direction mainly rely on classification scores to explore high-confidence unlabeled samples. Nevertheless, these methods often lead to false positive samples, which hinders the capability of GNNs. To this end, we propose a simple yet effective Topology-Aware Graph Self-Training (TA-GST) method. Specifically, we first explore the origin of false positives in pseudo-labeled samples. We then design a topology-aware scoring method, which considers both the classification score and connectivity pattern to enhance the reliability of pseudo-labeled samples. Besides, we depart TA-GST from the traditional teacher-student pattern and simplify it in an end-to-end manner. Extensive experiments on seven real-world datasets demonstrate the effectiveness of our method.

Can Pseudo-Label Be More Reliable? A Simple yet Effective Topology-Aware Graph Self-Training Method

To develop general-purpose collaborative agents, humans need reliable AI systems that can (1) adapt to new domains and (2) transparently reason with uncertainty to allow for verification and correction. Black-box models demonstrate powerful data processing abilities but do not satisfy these criteria due to their opaqueness, domain specificity, and lack of uncertainty awareness. We introduce Bonsai, a compositional and probabilistic reasoning system that generates adaptable inference trees by retrieving relevant grounding evidence and using it to compute likelihoods of sub-claims derived from broader natural language inferences. Bonsai's reasoning power is tunable at test-time via evidence scaling and it demonstrates reliable handling of varied domains including transcripts, photographs, videos, audio, and databases. Question-answering and human alignment experiments demonstrate that Bonsai matches the performance of domain-specific black-box methods while generating interpretable, grounded, and uncertainty-aware reasoning traces.

Bonsai: Interpretable Tree-Adaptive Grounded Reasoning

Scene graphs have emerged as a structured and serializable environment representation for grounded spatial reasoning with Large Language Models (LLMs).
In this work, we propose SG^2, an iterative Schema-Guided Scene-Graph reasoning framework based on multi-agent LLMs.
The agents are grouped into two modules: a (1) Reasoner module for abstract task planning and graph information queries generation, and a (2) Retriever module for extracting corresponding graph information based on code-writing following the queries.
Two modules collaborate iteratively, enabling sequential reasoning and adaptive attention to graph information.
The scene graph schema, prompted to both modules, serves to not only streamline both reasoning and retrieval process, but also guide the cooperation between two modules.
This eliminates the need to prompt LLMs with full graph data, reducing the chance of hallucination due to irrelevant information.
Through experiments in multiple simulation environments, we show that our framework surpasses existing LLM-based approaches and baseline single-agent, tool-based Reason-while-Retrieve strategy in numerical Q\&A and planning tasks.

Schema-Guided Scene-Graph Reasoning Based on Multi-Agent Large Language Model System

Federated Multi-View Clustering (FedMVC) has gained widespread attention for its ability to discover complementary clustering structures of distributed multi-view data while preserving data privacy. However, real-world clients often only have access to partial information, and the view incompleteness makes it more challenging for federated multi-view feature fusion to exploit consistency and complementary information. For another, efficiency is highly expected in federated scenarios, while existing federated incomplete multi-view clustering (FedIMVC) methods generally suffers from the curse of dimension. To alleviate these issues, we propose \textbf{F}ederated \textbf{I}ncomplete \textbf{M}ulti-\textbf{V}iew \textbf{C}lustering with \textbf{T}ensorized \textbf{L}ow-\textbf{R}ank \textbf{C}onstraint (FMVC-TLRC), which incorporates anchors to improve efficiency and is able to process ubiquitous view incompleteness issue in federated scenarios. FMVC-TLRC first aligns the local anchor graphs and employ tensorized low-rank constraint based on tensor Schatten p-norm to enforce the consistency of the data representations learned by each client. Besides, a federated unified framework is developed to jointly optimize the construction and alignment of anchor graphs, enabling collaborative model training. Experimental results on multiple datasets demonstrate the effectiveness of FIMVC-TLRC.

Federated Incomplete Multi-View Clustering with Tensorized Low-Rank Constraint

Compute structuring, a technique where AI developers split or modify compute workloads for the purpose of avoiding regulation, poses a challenge for AI governance techniques that rely on the computational properties of AI workloads. This work aims to explore the feasibility of detecting compute structuring and to propose robust detection methods. We do this by first exploring possible forms of compute structuring. Using realistic assumptions about cloud providers’ capabilities, we derive a potential detection approach. Further, we perform a comprehensive analysis of possible adversary scenarios and show that our method can detect them efficiently. Finally, we analyze potential future trends in AI compute workloads that could invalidate our proposed detection approach, and discuss possible adaptation and mitigation strategies. Overall, our study indicates that compute structuring detection is probably both feasible and practical to implement.

Detecting Compute Structuring in AI Governance Is Likely Feasible

Evaluating the quality of e-commerce search systems traditionally requires a significant number of human relevance annotations. In recent times, several deployed systems have explored the usage of Large Language Models (LLMs) as automated judges for this task while their inherent biases prevent direct use for metric estimation. We present a statistical framework extending Prediction-Powered Inference (PPI) that combines minimal human annotations with LLM judgments to produce reliable estimates of metrics which require sub-instance annotations. Our method requires as few as 100 human-annotated queries and 10,000 unlabeled examples, reducing annotation requirements significantly compared to traditional approaches. We formulate our proposed framework (PRECISE) for inference of relevance uplift for an LLM-based query reformulation application, extending PPI to sub-instance annotations at the query-document level. By reformulating the metric-integration space, we reduced the computational complexity from O(2^|C|) to O(2^K), where |C| represents corpus size (in order of millions). Detailed experiments across prominent retrieval datasets demonstrate that our method reduces the variance of estimates for the business-critical Precision@K metric, while effectively correcting for LLM bias in low-resource settings.

Downloads

Next from AAAI 2026

Localization-Anchored Instance Discrimination for Domain Adaptive Person Search

Similar lecture

ViTCoP: Accelerating Large Vision-Language Models via Visual and Textual Semantic Collaborative Pruning

.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

Localization-Anchored Instance Discrimination for Domain Adaptive Person Search

Similar lecture

ViTCoP: Accelerating Large Vision-Language Models via Visual and Textual Semantic Collaborative Pruning

Downloads