Singapore

Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-modal scenarios, such as vision-to-language distillation, where inconsistencies in representation across modalities lead to difficult knowledge transfer. To address this challenge, we propose frequency-decoupled cross-modal knowledge distillation, a method designed to decouple and balance knowledge transfer across modalities by leveraging frequency-domain features. We observed that low-frequency features exhibit high consistency across different modalities, whereas high-frequency features demonstrate extremely low cross-modal similarity. Accordingly, we apply distinct losses to these features: enforcing strong alignment in the low-frequency domain and introducing relaxed alignment for high-frequency features. We also propose a scale consistency loss to address distributional shifts between modalities, and employ a shared classifier to unify feature spaces. Extensive experiments across multiple benchmark datasets show our method substantially outperforms traditional KD and state-of-the-art cross-modal KD approaches. Our code is available at: https://github.com/Johumliu/FD-CMKD.

AAAI 2026

Distilling Cross-Modal Knowledge via Feature Disentanglement

cross-modal

multimodal learning

knowledge distillation

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

This paper proposes SR-KI, a novel approach for integrating real-time and large-scale structured knowledge bases (KBs) into large language models (LLMs). SR-KI begins by encoding KBs into key-value pairs using a pretrained encoder, and injects them into LLMs' KV cache. Building on this representation, we employ a two-stage training paradigm: first locating a dedicated retrieval layer within the LLM, and then applying an attention-based loss at this layer to explicitly supervise attention toward relevant KB entries. Unlike traditional retrieval-augmented generation methods that rely heavily on the performance of external retrievers and multi-stage pipelines, SR-KI supports end-to-end inference by performing retrieval entirely within the model’s latent space. This design enables efficient compression of injected knowledge and facilitates dynamic knowledge updates. Comprehensive experiments demonstrate that SR-KI enables the integration of up to 40K KBs into a 7B LLM on a single A100 40GB GPU, and achieves strong retrieval performance—maintaining over 98% Recall@10 on the best-performing task and exceeding 88% on average across all tasks. Task performance on question answering and KB ID generation also demonstrates that SR-KI maintains strong performance while achieving up to 99.75% compression of the injected KBs.

SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention

Temporal Graph Neural Network (TGNN) explanation has attracted increasing attention due to its applicability in dynamic scenarios such as recommendation systems. However, existing explanation methods for TGNNs face two key limitations: (1) computational inefficiency and (2) a restricted focus on either factual or counterfactual explanations, but not both. In this paper, we propose TGX-QIEA, an efficient and unified explanation algorithm based on a quantum-inspired evolutionary algorithm. TGX-QIEA effectively generates explanatory subgraphs that significantly influence TGNN predictions, without requiring additional model training or extensive inference. Experimental results on real-world datasets demonstrate that TGX-QIEA improves explanation fidelity by up to 31\% while reducing computation time by up to 92\% compared to state-of-the-art baselines.

Explaining Temporal Graph Neural Network via Quantum-Inspired Evolutionary Algorithm

This paper introduces Conformal Interquantile Regression (CIR), a novel conformal regression method designed to rapidly produce the smallest possible prediction intervals with guaranteed coverage. CIR employs black-box machine learning models to directly estimate outcome distributions through interquantile ranges and then converts these estimates into concise prediction intervals, achieving approximate conditional coverage. Base on CIR, we also introduce a variant, Conditional Interquantile Regression with More Comparation (CIR+), which incorporates an additional decision mechanism that evaluates whether to retain or discard a specific interquantile interval based on its length. The additional step in CIR+ results in slightly narrower prediction set widths while maintaining comparable coverage performance. Both of methods solve two main problems found in other distributional conformal prediction methods: they work well with skewed data, which is challenging for methods like Conformalized Quantile Regression, and they are computationally far more efficient than Conformal Histogram Regression by avoiding the histogram construction process. Empirical studies using both synthetic and real-world datasets demonstrate that our methods achieve the best balance between predictive performance and computational efficiency compared to other approaches.

Fast Conformal Prediction Using Conditional Interquantile Intervals

Learning diagnosis is a critical task that monitors students' cognitive state during educational activities, with the goal of enhancing learning outcomes. With advancements in language models (LMs), many AI-driven educational studies have shifted towards conversational learning scenarios, where students engage in multi-turn interactive dialogues with tutors. However, conversational learning diagnosis remains underdeveloped, and most existing techniques acquire students' cognitive state through intuitive instructional prompts on LMs to analyze the dialogue text. This direct prompting approach lacks a solid psychological foundation and fails to ensure the reliability of the generated analytical text. In this study, we introduce ParLD, a preview-analyze-reason framework for conversational learning diagnosis, which leverages multi-agent collaboration to diagnose students' cognitive state over multiple dialogue turns. Specifically, ParLD comprises main components: (1) Behaviour Previewer, which generates a student behavior schema based on previous states and learning content; (2) State Analyzer, which diagnose the tutor-student dialogue and behavior schema to update the cognitive state; and (3) Performance Reasoner, which predicts the student's future responses and provides verifiable feedback to support ParLD's self-reflection with the Chain reflector. They operate sequentially and iteratively during each interaction turn to diagnose the student’s cognitive state. We conduct experiments to evaluate both performance prediction and tutoring support, emphasizing the effectiveness of ParLD in providing reliable and insightful learning diagnosis. Code is available at \url{https://anonymous.4open.science/status/ParLD-67D6}.

Conversational Learning Diagnosis via Reasoning Multi-Turn Interactive Learning

Fine-grained Visual Recognition (FGVR) aims to distinguish between categories with subtle inter-class differences and large intra-class variations. While Vision Transformers with attention mechanisms have been widely adopted for FGVR, they usually suffer from high computational complexity and entangled global representations. Recent advancements in state-space models, exemplified by Mamba, have showcased substantial potential in vision-related tasks due to their linear scalability and rich sequence modeling capacity. To this end, we propose DHMamba, a novel Mamba based FGVR method. The proposed method leverages hypergraph to guide selective scanning and strengthen Mamba’s capability in modeling fine-grained semantics. Furthermore, a Disentangled Local Scanning (DLS) module is introduced to utilize hyperedges to allocate distinct informative patches into independent channels for mitigating the representational entanglement. Extensive experiments conducted on multiple FGVR benchmarks demonstrate that the proposed DHMamba outperforms the state-of-the-art methods, validating the efficacy of combining state-space modeling with hypergraph-based feature structuring.

Disentangled Hypergraph-Guided Mamba Scanning for Fine-Grained Visual Recognition

This paper presents an investigation of vision transformer learning for multi-view geometry tasks, such as optical flow estimation, by fine-tuning video foundation models. Unlike previous methods that involve custom architectural designs and task-specific pretraining, our research finds that general-purpose models pretrained on videos can be readily transferred to multi-view problems with minimal adaptation. The core insight is that general-purpose attention between patches learns temporal and spatial information for geometric reasoning. We demonstrate that appending a linear decoder to the Transformer backbone produces satisfactory results, and iterative refinement can further elevate performance to state-of-the-art levels. This conceptually simple approach achieves top cross-dataset generalization results for optical flow estimation with end-point error (EPE) of 0.69, 1.78, and 3.15 on the Sintel clean, Sintel final, and KITTI datasets, respectively. Our method additionally establishes a new record on the online test benchmark with EPE values of 0.79, 1.88, and F1 value of 3.79. Applications to 3D depth estimation and stereo matching also show strong performance, illustrating the versatility of video-pretrained models in addressing geometric vision tasks.

A Study of Finetuning Video Transformers for Multi-view Geometry Tasks

Recent breakthroughs in reasoning models have markedly advanced the reasoning capabilities of large language models, particularly via training on tasks with verifiable rewards. Yet, a significant gap persists in their adaptation to real-world multimodal scenarios, most notably, vision-language tasks, due to a heavy focus on single-modal language settings. While efforts to transplant reinforcement learning techniques from NLP to Visual Language Models (VLMs) have emerged, these approaches often remain confined to perception-centric tasks or reduce images to textual summaries, failing to fully exploit visual context and commonsense knowledge, ultimately constraining the generalization of reasoning capabilities across diverse multimodal environments. To address this limitation, we introduce a novel fine-tuning task, Masked Prediction via Context and Commonsense (MPCC), which forces models to integrate visual context and commonsense reasoning by reconstructing semantically meaningful content from occluded images, thereby laying the foundation for generalized reasoning. To systematically evaluate the model’s performance in generalized reasoning, we developed a specialized evaluation benchmark, MPCC-Eval, and employed various fine-tuning strategies to guide reasoning. Among these, we introduced an innovative training method, Reinforcement Fine-Tuning with Prior Sampling, which not only enhances model performance but also improves its generalized reasoning capabilities in out-of-distribution (OOD) and cross-task scenarios. Code and data are available in the supplementary materials.

Activating Visual Context and Commonsense Reasoning Through Masked Prediction in VLMs

End-to-end autonomous driving has achieved remarkable advancements in recent years. Existing methods primarily follow a perception–planning paradigm, where perception and planning are executed sequentially within a fully differentiable framework for planning-oriented optimization. We further advance this paradigm through a "perception-in-plan'' framework design, which integrates perception into the planning process. This design facilitates targeted perception guided by evolving planning objectives over time, ultimately enhancing planning performance. Building on this insight, we introduce VeteranAD, a coupled perception and planning framework for end-to-end autonomous driving. By incorporating multi-mode anchored trajectories as planning priors, the perception module is specifically designed to gather traffic elements along these trajectories, enabling comprehensive and targeted perception. Planning trajectories are then generated based on both the perception results and the planning priors. To make perception fully serve planning, we adopt an autoregressive strategy that progressively predicts future trajectories while focusing on relevant regions for targeted perception at each step. With this simple yet effective design, VeteranAD fully unleashes the potential of planning-oriented end-to-end methods, leading to more accurate and reliable driving behavior. Extensive experiments on the NAVSIM and Bench2Drive datasets demonstrate that our VeteranAD achieves state-of-the-art performance.

Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving

Existing Human Motion Prediction (HMP) methods based on RGB(D) cameras are sensitive to lighting conditions and raise privacy concerns, limiting their real-world applications such as firefighting and elderly care. Motivated by the robustness and privacy-preserving nature of millimeter-wave (mmWave) radar, this work introduces radar as a novel sensing modality for HMP for the first time. Nevertheless, radar signals often suffer from specular reflections and multipath effects, resulting in noisy and temporally inconsistent measurements, such as body-part miss-detection. To address these radar-specific artifacts, we propose mmPred, the first diffusion-based framework tailored for radar-based HMP. mmPred introduces a dual-domain historical motion representation to guide the generation process, combining a Time-domain Pose Refinement (TPR) branch for fine-grained details and a Frequency-domain Dominant Motion (FDM) branch for capturing global motion trends and suppressing frame-level inconsistency. Furthermore, we design a Global Skeleton-relational Transformer (GST) as the diffusion backbone to model global inter-joint cooperation, enabling corrupted joints to dynamically aggregate information from others. Extensive experiments show that mmPred achieves state-of-the-art performance, outperforming existing methods by 8.6% on mmBody and 22% on mm-Fi.

mmPred: Radar-based Human Motion Prediction in the Dark

3D Gaussian Splatting (3D-GS) has emerged as an efficient 3D representation and a promising foundation for semantic tasks like segmentation. However, existing 3D-GS-based segmentation methods typically rely on high-dimensional category features, which introduce substantial memory overhead. Moreover, fine-grained segmentation remains challenging due to label space congestion and the lack of stable multi-granularity control mechanisms.
To address these limitations, we propose a coarse-to-fine binary encoding scheme for per-Gaussian category representation, which compresses each feature into a single integer via the binary-to-decimal mapping, drastically reducing memory usage. We further design a progressive training strategy that decomposes panoptic segmentation into a series of independent sub-tasks, reducing inter-class conflicts and thereby enhancing fine-grained segmentation capability.
Additionally, we fine-tune opacity during segmentation training to address the incompatibility between photometric rendering and semantic segmentation, which often leads to foreground-background confusion.
Extensive experiments on multiple benchmarks demonstrate that our method achieves state-of-the-art segmentation performance while significantly reducing memory consumption and accelerating inference.

Downloads

Next from AAAI 2026

SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention

Similar lecture

Asymmetric Cross-Modal Knowledge Distillation: Bridging Modalities with Weak Semantic Consistency

.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

SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention

Similar lecture

Asymmetric Cross-Modal Knowledge Distillation: Bridging Modalities with Weak Semantic Consistency

Downloads