Singapore

Parameter-efficient fine-tuning has emerged as a promising paradigm in RGB-T tracking, enabling downstream task adaptation by freezing pretrained parameters and fine-tuning only a small set of parameters. This set forms a rank space made up of multiple individual ranks, whose expressiveness directly shapes the model&#39;s adaptability. However, quantitative analysis reveals low-rank adaptation exhibits significant redundancy in the rank space, with many ranks contributing almost no practical information. This hinders the model&#39;s ability to learn more diverse knowledge to address the various challenges in RGB-T tracking. To address this issue, we propose the Group Orthogonal Low-Rank Adaptation (GOLA) framework for RGB-T Tracking, which effectively leverages the rank space through structured parameter learning. Specifically, we adopt a rank decomposition partitioning strategy utilizing singular value decomposition to quantify rank importance, freeze crucial ranks to preserve the pretrained priors, and cluster the redundant ranks into groups to prepare for subsequent orthogonal constraints. We further design an inter-group orthogonal constraint strategy. This constraint enforces orthogonality between rank groups, compelling them to learn complementary features that target diverse challenges, thereby alleviating information redundancy. Experimental results demonstrate that GOLA effectively reduces parameter redundancy and enhances feature representation capabilities, significantly outperforming state-of-the-art methods across four benchmark datasets and validating its effectiveness in RGB-T tracking tasks. Code and more experiments are available in the supplementary materials.

AAAI 2026

Group Orthogonal Low-Rank Adaptation for RGB-T Tracking

cv: motion & tracking

cv: representation learning for vision

cv: multi-modal vision

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Parameter-efficient fine-tuning has emerged as a promising paradigm in RGB-T tracking, enabling downstream task adaptation by freezing pretrained parameters and fine-tuning only a small set of parameters. This set forms a rank space made up of multiple individual ranks, whose expressiveness directly shapes the model's adaptability. However, quantitative analysis reveals low-rank adaptation exhibits significant redundancy in the rank space, with many ranks contributing almost no practical information. This hinders the model's ability to learn more diverse knowledge to address the various challenges in RGB-T tracking. To address this issue, we propose the Group Orthogonal Low-Rank Adaptation (GOLA) framework for RGB-T Tracking, which effectively leverages the rank space through structured parameter learning. Specifically, we adopt a rank decomposition partitioning strategy utilizing singular value decomposition to quantify rank importance, freeze crucial ranks to preserve the pretrained priors, and cluster the redundant ranks into groups to prepare for subsequent orthogonal constraints. We further design an inter-group orthogonal constraint strategy. This constraint enforces orthogonality between rank groups, compelling them to learn complementary features that target diverse challenges, thereby alleviating information redundancy. Experimental results demonstrate that GOLA effectively reduces parameter redundancy and enhances feature representation capabilities, significantly outperforming state-of-the-art methods across four benchmark datasets and validating its effectiveness in RGB-T tracking tasks. Code and more experiments are available in the supplementary materials.

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.

To access this event page, you need to log in with the **email address you registered with**. 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.

Knowledge graph construction (KGC) aims to extract valuable information from text and organize it into structured knowledge graphs (KGs). Recent methods have leveraged the strong generative capabilities of large language models (LLMs) to improve the generalization and reduce the labor costs. However, constrained by the input length of LLMs, existing methods mainly focus on extracting knowledge within individual texts and lack the capability to discover latent knowledge across texts. To fill this gap, we propose a novel method for open knowledge graph construction, termed KG-DIF. The core idea of this method is to enhance the knowledge graph construction process by discovering new facts that are consistent with the underlying contextual logic. Specifically, we first design a knowledge extractor to extract knowledge from the text. Then, a knowledge normalizer performs schema alignment on the extracted knowledge. Next, we explore a knowledge discoverer based on a clue search strategy, which leverages the logical consistency of context to mine latent facts. Finally, we design a counterfactual-based knowledge corrector, enabling the model to purify knowledge and reduce factual errors. Experimental results show that KG-DIF is capable of extracting high-quality and comprehensive knowledge in open-world scenarios across three KGC benchmarks.

Discovering Latent Facts from Context to Construct Richer Open Knowledge Graphs

The rise of large language models (LLMs) has sparked interest in coding assistants.
While general purpose programming languages are well supported, generating code for domain-specific languages remains a challenging problem for LLMs.
In this paper, we focus on the LLM-based generation of Answer Set Programming (ASP) code, a particularly effective approach for finding solutions to combinatorial search problems.
However, the effectiveness of LLMs in ASP code generation is hindered by the limited number of examples seen during their initial pre-training phase.

In this paper, we introduce a novel approach for solver-guided instruction-tuning of LLMs for addressing the highly complex semantic parsing task inherent in ASP code generation. 
We sample ASP statements for program continuations proposed by LLMs for unriddling logic puzzles and categorize them into chosen and rejected instances based on solver feedback.
We then apply supervised fine-tuning to train LLMs on the curated data, and further improve robustness using a solver-guided search that includes best-of-N sampling.
Our experiments demonstrate consistent improvements in two distinct prompting settings on different datasets.

A Solver-in-the-Loop Framework for Improving LLMs on Answer Set Programming for Logic Puzzle Solving

Multimedia documents such as slide presentations and posters are designed to be interactive and easy to modify. Yet, they are often distributed in a static raster format, which limits editing and customization. Restoring their editability requires converting these raster images back into structured vector formats. However, existing geometric raster vectorization methods, which rely on low-level primitives like curves and polygons, fall short at this task. Specifically, when applied to complex documents like slides, they fail to preserve the high-level structure, resulting in a flat collection of shapes where the semantic distinction between image and text elements is lost. To overcome this limitation, we address the problem of semantic document derendering by introducing SliDer, a novel framework that uses Vision-Language Models (VLMs) to derender slide images as compact and editable Scalable Vector Graphic (SVG) representations. SliDer detects and extracts the attributes from individual image and text elements in a raster input and organizes them into a coherent SVG format. Crucially, the model iteratively refines its predictions during inference in a process analogous to human design, generating SVG code that more faithfully reconstructs the original raster upon rendering. Furthermore, we introduce Slide2SVG, a novel dataset comprising raster-SVG pairs of slide documents curated from real-world scientific presentations, to facilitate future research in this domain. Our results demonstrate that SliDer achieves a reconstruction LPIPS of 0.069, and is favored by human evaluators in 82.9% of cases compared to the strongest zero-shot VLM baseline. Our code and dataset will be publicly released at a later stage.

Semantic Document Derendering: SVG Reconstruction via Vision-Language Modeling

Diffusion models (DMs) have demonstrated to be powerful priors for signal recovery, but their application to 1-bit quantization tasks, such as 1-bit compressed sensing and logistic regression, remains a challenge. This difficulty stems from the inherent non-linear link function in these tasks, which is either non-differentiable or lacks an explicit characterization. To tackle this issue, we introduce Diff-OneBit, which is a fast and effective DM-based approach for signal recovery under 1-bit quantization. Diff-OneBit addresses the challenge posed by non-differentiable or implicit links functions via leveraging a differentiable surrogate likelihood function to model 1-bit quantization, thereby enabling gradient based iterations. This function is integrated into a flexible plug-and-play framework that decouples the data-fidelity term from the diffusion prior, allowing any pretrained DM to act as a denoiser within the iterative reconstruction process. Extensive experiments on the FFHQ and CelebA datasets demonstrate that Diff-OneBit gives high-fidelity reconstructed images, outperforming state-of-the-art methods in both reconstruction quality and computational efficiency across 1-bit compressed sensing and logistic regression tasks.

Diffusion Model Based Signal Recovery Under 1-Bit Quantization

Adversarial perturbations (APs) have become a great concern in image classification tasks. The most challenging branch, universal adversarial perturbations (UAPs), are exploited to fool most of the unseen samples. Such one-to-all perturbations have the merit of transferability, which has strong practical significance. In this paper, we firstly define the transferability gap and the algorithm stability of the UAP algorithm, and prove the relationship between them. In analyzing the UAP algorithm stability, we prove that the convergence domain of existing UAP algorithms with dynamic constraints is excessively small, which degrades the capacity of UAPs. Thus, we further propose a new expected constraint and prove that UAPs in the expected constraint suit any sample in a high probability. Besides, we propose a Stochastic Universal Adversarial Perturbation (SUAP) that involves additive noise and the expected constraint. Finally, by treating the proposed algorithm as a stochastic differential equation, we prove an upper bound of the UAP algorithm stability of SUAP, which decreases exponentially at the beginning and then increases with a sublinear rate to at most a fixed constant. Experimental results show that SUAP outperforms existing UAP algorithms with better white-box transferability.

Stochastic Universal Adversarial Perturbations with Fixed Optimization Constraint and Ensured High-probability Transferability

Missing data presents a widespread challenge in real-world data collection. In this paper, our goal is to impute missing entries while accurately reflecting the uncertainty associated with them. We introduce U-VAE, a method that employs a non-parametric distributional learning strategy to parameterize the likelihood of missing values. To address the infeasibility of directly estimating the underlying conditional distributions due to data incompleteness, we incorporate stochastic re-masking and un-masking techniques during training. Specifically, we replace the conventional reconstruction loss with the continuous ranked probability score (CRPS), a strictly proper scoring rule, and theoretically demonstrate that the discrepancy between the underlying conditional distribution and our imputer is upper-bounded. We evaluate the performance of U-VAE on 11 real-world datasets, showing its effectiveness in both single and multiple imputations, while also enhancing post-imputation performance and supporting valid statistical inference.

Impute Missing Entries with Uncertainty

Large Language Models (LLMs) perform excellently in fake news detection tasks, but their outputs are often accompanied with hallucination phenomena, i.e., generated content that is contradictory or deviates from facts. Previous studies have mostly mitigated hallucinations through prompt design. However, this paper reveals that regions in news articles which easily induce hallucination in LLMs highly correspond to challenges of fake news detectors. Based on this finding, we propose a fake news detection framework(PHPFND) based on post-hoc processing of LLMs hallucination. Specifically, our framework includes a hallucination detection module(ISHD) based on information structuring that detecting three types of hallucinations in LLMs in a targeted manner, and a hallucination-driven feature enhancement mechanism (HDFE) that incorporates hallucination signals as explicit features into sentence-level encoding and feature fusion to guide the model’s attention toward high-risk regions.
Experimental results on two mainstream fake news datasets show that the our proposed method significantly outperforms mainstream LLMs-based baselines.

PHPFND: Detecting Fake News via Post-Hoc Processing of LLMs Hallucination

Recently, Automatic Speech Recognition (ASR) systems (e.g., Whisper) have achieved remarkable accuracy improvements but remain highly sensitive to real-world unseen data (data with large distribution shifts), including noisy environments and diverse accents. To address this issue, test-time adaptation (TTA) has shown great potential in improving the model adaptability at inference time without ground-truth labels, and existing TTA methods often rely on pseudo-labeling or entropy minimization. However, by treating model confidence as a learning signal, these methods may reinforce high-confidence errors, leading to confirmation bias that undermines adaptation.
To overcome these limitations, we present ASR-TRA, a novel Test-time Reinforcement Adaptation framework inspired by causal intervention. More precisely, our method introduces a learnable decoder prompt and utilizes temperature-controlled stochastic decoding to generate diverse transcription candidates. These are scored by a reward model that measures audio-text semantic alignment, and the resulting feedback is used to update both model and prompt parameters via reinforcement learning.
Comprehensive experiments on LibriSpeech with synthetic noise and L2 Arctic accented English datasets demonstrate that our method significantly outperforms existing state-of-the-art (SOTA), including SUTA and SGEM, in both accuracy and inference speed. Ablation studies further confirm the effectiveness of combining audio and language-based rewards, highlighting our method's enhanced stability and interpretability. Overall, our approach provides a practical and robust solution for deploying ASR systems in challenging real-world conditions.

Boosting ASR Robustness via Test-Time Reinforcement Learning with Audio-Text Semantic Rewards

Large language models (LLMs) are increasingly deployed with hierarchical instruction schemes, where certain instructions (e.g., system-level directives) are expected to take precedence over others (e.g., user messages). Yet, we lack a systematic understanding of how effectively these hierarchical control mechanisms work. We introduce a systematic evaluation framework based on constraint prioritization to assess how well LLMs enforce instruction hierarchies. Our experiments across six state-of-the-art LLMs reveal that models struggle with consistent instruction prioritization, even for simple formatting conflicts. We find that the widely-adopted system/user prompt separation fails to establish a reliable instruction hierarchy, and models exhibit strong inherent biases toward certain constraint types regardless of their priority designation. We find that LLMs more reliably obey constraints framed through natural social hierarchies (e.g., authority, expertise, consensus) than system/user roles, which suggests that pretraining-derived social structures act as latent control priors, with potentially stronger influence than post-training guardrails.

Control Illusion: The Failure of Instruction Hierarchies in Large Language Models

Recent advances in vision–language models (VLMs) have shed light on human-level embodied intelligence. However, existing benchmark for VLM-driven embodied agent still rely on pre-defined high-level command or discretised action spaces—``non-native'' settings that diverge markedly from the real world. Moreover, current benchmarks focus exclusively on high-level tasks, while lacking collaborative evaluation and analysis on both low- and high-level. To bridge these gaps, we present NativeEmbodied, a challenging benchmark for VLM-driven embodied agents that adopts a unified, native low-level action space. Built upon diverse simulated scenes, NativeEmbodied first designs three representative high-level tasks in complex scenarios to evaluate overall performance. For more detailed and comprehensive performance analysis, we further decouple the entangled skills behind complex tasks and construct four types of low-level tasks, each corresponding to a key fundamental embodied skill. This joint evaluation across task and skill granularities enables a fine-grained assessment of embodied agent. Comprehensive experiments on the best VLMs reveal pronounced deficiencies in certain fundamental embodied skills. Further analysis shows that these low-level bottlenecks severely constrain performance on high-level tasks. Our NativeEmbodied not only pinpoints the key challenges faced by current VLM-driven embodied agents, but also provides valuable insight for future development of this field.

Downloads

Next from AAAI 2026

Discovering Latent Facts from Context to Construct Richer Open Knowledge Graphs

Similar lecture

An Orthogonal High-Rank Adaptation for Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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

Discovering Latent Facts from Context to Construct Richer Open Knowledge Graphs

Similar lecture

An Orthogonal High-Rank Adaptation for Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads