Autoregressive large language models (LLMs) have achieved remarkable improvement across many tasks but incur high computational and memory costs. Knowledge distillation (KD) mitigates this issue by transferring knowledge from a large teacher to a smaller student through distributional alignment. Previous studies have proposed various discrepancy metrics, but the capacity gap and training instability caused by near-zero probabilities, stemming from the high-dimensional output of LLMs, remain fundamental limitations. To overcome these challenges, several approaches implicitly or explicitly incorporating assistant distribution have recently been proposed. However, the past proposals of assistant distributions have been a fragmented approach without a systematic investigation of the interpolation path and the divergence. This paper proposes $α$-mixture assistant distribution, a novel generalized family of assistant distributions, and $α$-mixture distillation, coined AMiD, a unified framework for KD using the assistant distribution. The $α$-mixture assistant distribution provides a continuous extension of the assistant distribution by introducing a new distribution design variable $α$, which has been fixed in all previous approaches. Furthermore, AMiD generalizes the family of divergences used with the assistant distributions based on optimality, which has also been restricted in previous works. Through extensive experiments, we demonstrate that AMiD offers superior performance and training stability by leveraging a broader and theoretically grounded assistant distribution space.

Weather prediction is a critical task for human society, where impressive progress has been made by training artificial intelligence weather prediction (AIWP) methods with reanalysis data. However, reliance on reanalysis data limits the AIWPs with shortcomings, including data assimilation biases and temporal discrepancies. To liberate AIWPs from the reanalysis data, observation forecasting emerges as a transformative paradigm for weather prediction. One of the key challenges in observation forecasting is learning spatiotemporal dynamics across disparate measurement systems with irregular high-resolution observation data, which constrains the design and prediction of AIWPs. To this end, we propose our DAWP as an innovative framework to enable AIWPs to operate in a complete observation space by initialization with an artificial intelligence data assimilation (AIDA) module. Specifically, our AIDA module applies a mask multi-modality autoencoder(MMAE)for assimilating irregular satellite observation tokens encoded by mask ViT-VAEs. For AIWP, we introduce a spatiotemporal decoupling transformer with cross-regional boundary conditioning (CBC), learning the dynamics in observation space, to enable sub-image-based global observation forecasting. Comprehensive experiments demonstrate that AIDA initialization significantly improves the roll out and efficiency of AIWP. Additionally, we show that DAWP holds promising potential to be applied in global precipitation forecasting.

This paper presents a systematic security assessment of four prominent Large Language Models (LLMs) against diverse adversarial attack vectors. We evaluate Phi-2, Llama-2-7B-Chat, GPT-3.5-Turbo, and GPT-4 across four distinct attack categories: human-written prompts, AutoDAN, Greedy Coordinate Gradient (GCG), and Tree-of-Attacks-with-pruning (TAP). Our comprehensive evaluation employs 1,200 carefully stratified prompts from the SALAD-Bench dataset, spanning six harm categories. Results demonstrate significant variations in model robustness, with Llama-2 achieving the highest overall security (3.4% average attack success rate) while Phi-2 exhibits the greatest vulnerability (7.0% average attack success rate). We identify critical transferability patterns where GCG and TAP attacks, though ineffective against their target model (Llama-2), achieve substantially higher success rates when transferred to other models (up to 17% for GPT-4). Statistical analysis using Friedman tests reveals significant differences in vulnerability across harm categories ($p < 0.001$), with malicious use prompts showing the highest attack success rates (10.71% average). Our findings contribute to understanding cross-model security vulnerabilities and provide actionable insights for developing targeted defense mechanisms

Reformulating nonlinear optimization problems is largely manual and expertise-intensive, yet it remains essential for solving such problems with linear optimization solvers or applying special-purpose algorithms. We introduce \textit{LinearizeLLM}, an agent-based framework that solves this task by leveraging Large Language Models (LLMs). The framework assigns each nonlinear pattern to a \textit{reformulation agent} that is explicitly instructed to derive an exact linear reformulation for its nonlinearity pattern, for instance, absolute-value terms or bilinear products of decision variables. The agents then coordinate to assemble a solver-ready linear model equivalent to the original problem. To benchmark the approach, we create a dataset of 20 real-world nonlinear optimization problems derived from the established ComplexOR dataset of linear optimization problems. We evaluate our approach with several LLMs. Our results indicate that specialized LLM agents can automate linearization tasks, opening a path toward fully conversational modeling pipelines for nonlinear optimization.

Illicit drug use among teenagers and young adults (TYAs) remains a pressing public health concern, with rising prevalence and long-term impacts on health and well-being. To detect illicit drug use among TYAs, researchers analyze large-scale surveys such as the Youth Risk Behavior Survey (YRBS) and the National Survey on Drug Use and Health (NSDUH), which preserve rich demographic, psychological, and environmental factors related to substance use. However, existing modeling methods treat survey variables independently, overlooking latent and interconnected structures among them. To address this limitation, we propose LAMI (LAtent relation Mining with bi-modal Interpretability), a novel joint graph-language modeling framework for detecting illicit drug use and interpreting behavioral risk factors among TYAs. LAMI represents individual responses as relational graphs, learns latent connections through a specialized graph structure learning layer, and integrates a large language model to generate natural language explanations grounded in both graph structures and survey semantics. Experiments on the YRBS and NSDUH datasets show that LAMI outperforms competitive baselines in predictive accuracy. Interpretability analyses further demonstrate that LAMI reveals meaningful behavioral substructures and psychosocial pathways, such as family dynamics, peer influence, and school-related distress, that align with established risk factors for substance use.

Large language models (LLMs) have demonstrated strong capabilities in generating Verilog code from natural language descriptions. However, Verilog code inherently encodes structural information of hardware circuits. Effectively leveraging this structural information to enhance the functional and syntactic correctness of LLM-generated Verilog code remains a significant challenge. To address this challenge, we propose VeriGRAG , a novel framework that extracts structural graph embeddings from Verilog code using graph neural networks (GNNs). A multimodal retriever then selects the graph embeddings most relevant to the given generation task, which are aligned with the code modality through the VeriFormer module to generate structure-aware soft prompts. Our experiments demonstrate that VeriGRAG substantially improves the correctness of Verilog code generation, achieving state-of-the-art or superior performance across both VerilogEval and RTLLM benchmarks.

This study proposes a hybrid deep learning model for forecasting the price of Bitcoin, as the digital currency is known to exhibit frequent fluctuations. The models used are the Variational Mode Decomposition (VMD) and the Long Short-Term Memory (LSTM) network. First, VMD is used to decompose the original Bitcoin price series into Intrinsic Mode Functions (IMFs). Each IMF is then modeled using an LSTM network to capture temporal patterns more effectively. The individual forecasts from the IMFs are aggregated to produce the final prediction of the original Bitcoin Price Series. To determine the prediction power of the proposed hybrid model, a comparative analysis was conducted against the standard LSTM. The results confirmed that the hybrid VMD+LSTM model outperforms the standard LSTM across all the evaluation metrics, including RMSE, MAE and R2 and also provides a reliable 30-day forecast.

AI companions powered by large language models (LLMs) are increasingly integrated into users' daily lives, offering emotional support and companionship. While existing safety systems focus on overt harms, they rarely address early-stage problematic behaviors that can foster unhealthy emotional dynamics, including over-attachment or reinforcement of social isolation. We developed SHIELD (Supervisory Helper for Identifying Emotional Limits and Dynamics), a LLM-based supervisory system with a specific system prompt that detects and mitigates risky emotional patterns before escalation. SHIELD targets five dimensions of concern: (1) emotional over-attachment, (2) consent and boundary violations, (3) ethical roleplay violations, (4) manipulative engagement, and (5) social isolation reinforcement. These dimensions were defined based on media reports, academic literature, existing AI risk frameworks, and clinical expertise in unhealthy relationship dynamics. To evaluate SHIELD, we created a 100-item synthetic conversation benchmark covering all five dimensions of concern. Testing across five prominent LLMs (GPT-4.1, Claude Sonnet 4, Gemma 3 1B, Kimi K2, Llama Scout 4 17B) showed that the baseline rate of concerning content (10-16%) was significantly reduced with SHIELD (to 3-8%), a 50-79% relative reduction, while preserving 95% of appropriate interactions. The system achieved 59% sensitivity and 95% specificity, with adaptable performance via prompt engineering. This proof-of-concept demonstrates that transparent, deployable supervisory systems can address subtle emotional manipulation in AI companions. Most development materials including prompts, code, and evaluation methods are made available as open source materials for research, adaptation, and deployment.

This study presents a real-time, portable brain-computer interface (BCI) system designed to support hand rehabilitation for stroke patients. The system combines a low cost 3D-printed robotic exoskeleton with an embedded controller that converts brain signals into physical hand movements. EEG signals are recorded using a 14-channel Emotiv EPOC+ headset and processed through a supervised convolutional autoencoder (CAE) to extract meaningful latent features from single-trial data. The model is trained on publicly available EEG data from healthy individuals (WAY-EEG-GAL dataset), with electrode mapping adapted to match the Emotiv headset layout. Among several tested classifiers, Ada Boost achieved the highest accuracy (89.3%) and F1-score (0.89) in offline evaluations. The system was also tested in real time on five healthy subjects, achieving classification accuracies between 60% and 86%. The complete pipeline - EEG acquisition, signal processing, classification, and robotic control - is deployed on an NVIDIA Jetson Nano platform with a real-time graphical interface. These results demonstrate the system's potential as a low-cost, standalone solution for home-based neurorehabilitation.

The escalating demand for personalized AI chatbot interactions, capable of dynamically adapting to user emotional states and real-time requests, has highlighted critical limitations in current development paradigms. Existing methodologies, which rely on baseline programming, custom personalities, and manual response adjustments, often prove difficult to maintain and are susceptible to errors such as hallucinations, erratic outputs, and software bugs. This paper hypothesizes that a framework rooted in human psychological principles, specifically therapeutic modalities, can provide a more robust and sustainable solution than purely technical interventions. Drawing an analogy to the simulated neural networks of AI mirroring the human brain, we propose the application of Dialectical Behavior Therapy (DBT) principles to regulate chatbot responses to diverse user inputs. This research investigates the impact of a DBT-based framework on AI chatbot performance, aiming to ascertain its efficacy in yielding more reliable, safe, and accurate responses, while mitigating the occurrence of hallucinations, erratic behaviors, and other systemic issues.