United States

Parameter-efficient fine-tuning (PEFT) methods optimize large language models (LLMs) by modifying or introducing a small number of parameters to enhance alignment with downstream tasks. However, they can result in catastrophic forgetting, where LLMs prioritize new knowledge at the expense of comprehensive world knowledge. A promising approach to mitigate this issue is to recall prior memories based on the original knowledge. To this end, we propose a model-agnostic PEFT framework, $\textbf{IMSM}$, which $\textbf{I}$nterweaves $\textbf{M}$emories of a $\textbf{S}$iamese Large Language $\textbf{M}$odel. Specifically, our siamese LLM is equipped with an existing PEFT method. Given an incoming query, it generates two distinct memories based on the pre-trained and fine-tuned parameters. IMSM then incorporates an interweaving mechanism that regulates the contributions of both original and enhanced memories when generating the next token. This framework is theoretically applicable to all open-source LLMs and existing PEFT methods. We conduct extensive experiments across various benchmark datasets, evaluating the performance of popular open-source LLMs using the proposed IMSM, in comparison to both classical and leading PEFT methods. Our findings indicate that IMSM maintains comparable time and space efficiency to backbone PEFT methods while significantly improving performance and effectively mitigating catastrophic forgetting. Our code and experimental settings can be accessed through the following link: https://anonymous.4open.science/r/SiameseModels-48D4

AAAI 2025

Interweaving Memories of a Siamese Large Language Model

snlp

language models

poster

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

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-25 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.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

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-25 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.



While machine learning models have proven effective across various scenarios, it is widely acknowledged that many models are vulnerable to adversarial attacks. Recently, there have emerged numerous efforts in adversarial defense. Among them, certified defense is well known for its theoretical guarantees against arbitrary adversarial perturbations on input within a certain range (e.g.,  $l_2$ ball). However, most existing works in this line struggle to generalize their certified robustness in other data domains with distribution shifts. This issue is rooted in the difficulty of eliminating the negative impact of spurious correlations on robustness in different domains. To address this problem, in this work, we propose a novel certified defense framework GLEAN, 
which incorporates a causal perspective into the generalization problem in certified defense. More specifically, our framework integrates a certifiable causal factor learning component to disentangle the causal relations and spurious correlations between input and label, and thereby exclude the negative effect of spurious correlations on defense. On top of that, we design a causally certified defense strategy to handle adversarial attacks on latent causal factors. In this way, our framework is not only robust against malicious noises on data in the training distribution but also can generalize its robustness across domains with distribution shifts. Extensive experiments on benchmark datasets validate the superiority of our framework in certified robustness generalization in different data domains. Code is available in the supplementary materials.

Certified Causal Defense with Generalizable Robustness

Out-of-distribution (OOD) detection, determining whether a given sample is part of the in-distribution (ID) or not, has been newly explored by a generative model-based outlier synthesizing approach, especially with diffusion models. Nonetheless, existing diffusion models often produce outliers that are considerably distant from the ID in pixel-space, showing limited efficacy for capturing subtle distinctions between ID and OOD. To address these issues, we propose a novel framework, Semantic Outlier generation via Nuisance Awareness (SONA), which directly utilizes informative pixel-space ID images in diffusion models. Thereby, the generated outliers achieve two crucial properties: (i) they closely resemble the ID mainly in nuisances, while (ii) represent discriminative semantic information. To facilitate the separate effect on semantics and nuisances, we introduce SONA guidance, providing region-specific guidance. Extensive experiments demonstrate the effectiveness of our framework, achieving an impressive AUROC of 87% on near-OOD datasets, which surpasses the performance of baseline methods by a significant margin of approximately 6%.

Diffusion-based Semantic Outlier Generation via Nuisance Awareness for Out-of-Distribution Detection

Due to the superior ability of global dependency, transformer and its variants have become the primary choice in Masked Time-series Modeling (MTM) towards time-series classification task. In this paper, we experimentally analyze that existing transformer-based MTM methods encounter with two under-explored issues when dealing with time series data: (1) they encode features by performing long-dependency ensemble averaging, which easily results in rank collapse and feature homogenization as the layer goes deeper; (2) they exhibit distinct priorities in fitting different frequency components contained in the time-series, inevitably leading to spectrum energy imbalance of encoded feature. To tackle these issues, we propose an auxiliary content-aware balanced decoder (CBD) to optimize the encoding quality in the spectrum space within masked modeling scheme. Specifically, the CBD iterates on a series of fundamental blocks, and thanks to two tailored units, each block could progressively refine the masked representation via adjusting the interaction pattern based on local content variations of time-series and learning to recalibrate the energy distribution across different frequency components. Moreover, dual-constraint loss is devised to enhance the mutual optimization of vanilla decoder and our CBD. Extensive experimental results on ten time-series classification datasets show that our method nearly surpasses a bunch of baselines. Meanwhile, a series of explanatory results are showcased to sufficiently demystify the behaviors of our method.

Content-aware Balanced Spectrum Encoding in Masked Modeling for Time Series Classification

We present Connected-Component~(CC)-Metrics, a novel semantic segmentation evaluation protocol, targeted to align existing semantic segmentation metrics to a multi-instance detection scenario in which each connected component matters. We motivate this setup in the common medical scenario of semantic metastases segmentation in a full-body PET/CT. We show how existing semantic segmentation metrics suffer from a bias towards larger connected components contradicting the clinical assessment of scans in which tumor size and clinical relevance are uncorrelated. To rebalance existing segmentation metrics, we propose to evaluate them on a per-component basis thus giving each tumor the same weight irrespective of its size. To match predictions to ground-truth segments, we employ a proximity-based matching criterion, evaluating common metrics locally at the component of interest. Using this approach, we break free of biases introduced by large metastasis for overlap-based metrics such as Dice or Surface Dice. CC-Metrics also improves distance-based metrics such as Hausdorff Distances which are uninformative for small changes that do not influence the maximum or $95^{\text{th}}$ percentile, and avoids pitfalls introduced by directly combining counting-based metrics with overlap-based metrics as it is done in Panoptic Quality. 
We will make the code for CC-Metrics publicly available.

Every Component Counts: Rethinking the Measure of Success for Medical Semantic Segmentation in Multi-Instance Segmentation Tasks

As one of the key technologies leading to Artificial General Intelligence (AGI), Large Language Models (LLMs) have achieved remarkable accomplishments. Exploring the capabilities of LLMs is crucial for scientific research, and many studies propose new challenges from various aspects to explore the capability boundaries of LLMs. This paper attempts to push the challenges of information understanding, synthesizing and reasoning to the extreme, in order to explore the boundaries of more advanced dimensional cognitive capabilities in LLMs. It is defined as the task of High-Level Cognition(HLC), which involves obtaining high-level conclusions from low-level and fragmented foundational information. To evaluate HLC, we construct a dataset based on soccer matches. Experiments and analysis on this dataset show that current state-of-the-art LLMs lack the ability to solve the task of HLC, because their performance is equivalent to random-level. However, by fine-tuning Llama3-8B-Instruct, there are improvements of 14.4%, 48.1%, and 19.4% over random-level in three types of evaluation tasks. This indicates that LLMs have great potential to solve the task of HLC.

Can Large Language Models Derive High-Level Cognition from Low-Level and Fragmented Foundational Information?

Large Language Models (LLMs) are susceptible to malicious influence by cyber attackers through intrusions such as adversarial, backdoor, and embedding inversion attacks. 
In response, the burgeoning field of LLM Security aims to study and defend against such threats. 
Thus far, the majority of works in this area have focused on monolingual English models, however, emerging research suggests that multilingual LLMs may be more vulnerable to various attacks than their monolingual counterparts. 
While previous work has investigated embedding inversion over a small subset of European languages, it is challenging to extrapolate these findings to languages from different linguistic families and with differing scripts. 
To this end, we explore the security of multilingual LLMs in the context of embedding inversion attacks and investigate cross-lingual and cross-script 
inversion across 20 languages, spanning over 8 language families and 12 scripts.
Our findings indicate that languages written in Arabic script and Cyrillic script are particularly vulnerable to embedding inversion, as are languages within the Indo-Aryan language family. 
We further observe that inversion models tend to suffer from language confusion, sometimes greatly reducing the efficacy of an attack. 
Accordingly, we systematically explore this bottleneck for inversion models, uncovering predictable patterns which could be leveraged by attackers. 
Ultimately, this study aims to further the field's understanding of the outstanding security vulnerabilities facing multilingual LLMs and raise awareness for the languages most at risk of negative impact from these attacks.

Against All Odds: Overcoming Typology,  Script,  and Language Confusion in Multilingual Embedding Inversion Attacks

Driver attention recognition in driving scenarios is a popular direction in traffic environment perception technology. It aims to understand human driver attention to focus on specific targets/objects in the driving scene. However, traffic scenes contain not only a large amount of visual information but also semantic information related to driving tasks. Existing methods lack attention to the actual semantic information present in driving scenes. Additionally, the traffic environment is a complex and dynamic process that requires constant attention to objects related to the current driving task. Existing models, influenced by their foundational frameworks, tend to have large parameter counts and complex structures. Therefore, this paper proposes a real-time saliency Mamba network based on the latest Mamba framework. Our model uses very few parameters (0.08M, only 0.09\% to 11.16\% of other models), while maintaining state-of-the-art (SOTA) performance or achieving over 98\% of the SOTA model's performance.

SalM^2 : An extremely lightweight saliency mamba model for real-time cognitive awareness of driver attention

The ability to estimate temporal relationships is critical for both animals and artificial agents. Cognitive science and neuroscience provide remarkable insights into behavioral and neural aspects of temporal credit assignment. In particular, scale-invariance of learning dynamics observed in behavior and supported by neural data is one of the key principles that governs animal perception: if the temporal relationships in the environment rescale, the number of trials required for learning will remain constant. Here we integrate a computational neuroscience model of scale-invariant memory into deep reinforcement learning (RL) agents. We first provide a theoretical analysis and then demonstrate through experiments that such agents can learn robustly across a wide range of temporal scales, unlike agents built with commonly used recurrent memory architectures such as LSTM. This result illustrates that building computational principles from neuroscience and cognitive science into deep neural networks can result in systems that are flexible learners, similar to humans.

Deep Reinforcement Learning with Time-Scale Invariant Memory

In this paper, we draw an analogy between processing natural languages and processing multivariate event streams from vehicles in order to predict when and what error pattern is most likely to occur in the future for a given car. Our approach leverages the temporal dynamics and contextual relationships of our event data from a fleet of cars. Event data is composed of discrete values of error codes as well as continuous values such as time and mileage. Modelled by two causal transformers, we can anticipate critical vehicle failures and malfunctions before they happen. Thus, we introduce CarFormer, a transformer model trained via a new self-supervised learning strategy, and Epredictor, an autoregressive transformer decoder model capable of predicting when and what error pattern will most likely occur after some error code apparition. Despite the challenges of high cardinality of event types, their unbalanced frequency of appearance and a limited labeled data, our experimental results demonstrate the excellent predictive ability of our novel model. Specifically, with on average sequences of 160 error codes, our model is able with only half of the error codes to achieve $80$% F1 score for predicting what error pattern will occur and achieves an average absolute error of $58.4 \pm 13.2$h when forecasting the time of occurrence,e, thus enabling confident predictive maintenance and enhancing vehicle safety.

Harnessing Event Sensory Data for Error Pattern Prediction in Vehicles: A Language Model Approach

Building on the success of text-to-image diffusion models (DPMs), image editing is an important application to enable human interaction with AI-generated content.
Among various editing methods, editing within the prompt space gains more attention due to its capacity and simplicity of controlling semantics.
However, since diffusion models are commonly pretrained on descriptive text captions, direct editing of words in text prompts usually leads to completely different generated images, violating the requirements for image editing.
On the other hand, existing editing methods usually consider introducing spatial masks to preserve the identity of unedited regions, which are usually ignored by DPMs and therefore lead to inharmonic editing results.
Targeting these two challenges, in this work, we propose to disentangle the comprehensive image-prompt interaction into several item-prompt interactions, with each item linked to a special learned prompt.
The resulting framework, named \textbf{D-Edit}, is based on pretrained diffusion models with cross-attention layers disentangled and adopts a two-step optimization to build item-prompt associations.
Versatile image editing can then be applied to specific items by manipulating the corresponding prompts.
We demonstrate state-of-the-art results in four types of editing operations including image-based, text-based, mask-based editing, and item removal, covering most types of editing applications, all within a single unified framework.
Notably, D-Edit is the first framework that can (1) achieve item editing through mask editing and (2) combine image and text-based editing.
We demonstrate the quality and versatility of the editing results for a diverse collection of images through both qualitative and quantitative evaluations.

Content not yet available

Interweaving Memories of a Siamese Large Language Model

Downloads

Next from AAAI 2025

Certified Causal Defense with Generalizable Robustness

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

Interweaving Memories of a Siamese Large Language 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 2025

Certified Causal Defense with Generalizable Robustness

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads