Large Language Models (LLMs) often exhibit significant behavioral shifts when they perceive a change from a real-world deployment context to a controlled evaluation setting, a phenomenon known as "evaluation awareness." This discrepancy poses a critical challenge for AI alignment, as benchmark performance may not accurately reflect a model's true safety and honesty. In this work, we systematically quantify these behavioral changes by manipulating the perceived context of prompts. We introduce a methodology that uses a linear probe to score prompts on a continuous scale from "test-like" to "deploy-like" and leverage an LLM rewriting strategy to shift these prompts towards a more natural, deployment-style context while preserving the original task. Using this method, we achieved a 30% increase in the average probe score across a strategic role-playing dataset after rewriting. Evaluating a suite of state-of-the-art models on these original and rewritten prompts, we find that rewritten "deploy-like" prompts induce a significant and consistent shift in behavior. Across all models, we observed an average increase in honest responses of 5.26% and a corresponding average decrease in deceptive responses of 12.40%. Furthermore, refusal rates increased by an average of 6.38%, indicating heightened safety compliance. Our findings demonstrate that evaluation awareness is a quantifiable and manipulable factor that directly influences LLM behavior, revealing that models are more prone to unsafe or deceptive outputs in perceived test environments. This underscores the urgent need for more realistic evaluation frameworks to accurately gauge true model alignment before deployment.

Despite progress in gloss-free Sign Language Translation (SLT), traditional single modality end-to-end approaches consistently fail on two critical components of natural signing: the precise recognition of high-speed fingerspelling and the integration of asynchronous non-manual cues from the face. Recent progress in SLT with Large Language Models has side stepped this challenge, forcing a single network to learn these simultaneously resulting in poor performance when tasked with translating crucial information such as names, places, and technical terms. We introduce SignBind-LLM, a modular framework designed to overcome these limitations. Our approach employs separate, specialized predictors for continuous signing, fingerspelling, and lipreading. Each expert network first decodes its specific modality into a sequence of tokens. These parallel streams are then fused by a lightweight transformer that resolves temporal misalignments before passing the combined representation to a Large Language Model (LLM) for final sentence generation. Our method establishes a new state-of-the-art on the How2Sign, ChicagoFSWildPlus, and BOBSL datasets with a BLEU-4 score of 22.1, 73.2% letter accuracy and BLEU-4 score of 6.8 respectively. These results validate our core hypothesis: isolating and solving distinct recognition tasks before fusion provides a more powerful and effective pathway to robust, high-fidelity sign language translation.

Query-product relevance prediction is a core task in e-commerce search. BERT-based models excel at semantic matching but lack complex reasoning capabilities. While Large Language Models (LLMs) are explored, most still use discriminative fine-tuning or distill to smaller models for deployment. We propose a framework to directly deploy LLMs for this task, addressing key challenges: Chain-of-Thought (CoT) error accumulation, discriminative hallucination, and deployment feasibility. Our framework, TaoSR1, involves three stages: (1) Supervised Fine-Tuning (SFT) with CoT to instill reasoning; (2) Offline sampling with a pass@N strategy and Direct Preference Optimization (DPO) to improve generation quality; and (3) Difficulty-based dynamic sampling with Group Relative Policy Optimization (GRPO) to mitigate discriminative hallucination. Additionally, post-CoT processing and a cumulative probability-based partitioning method enable efficient online deployment. TaoSR1 significantly outperforms baselines on offline datasets and achieves substantial gains in online side-by-side human evaluations, introducing a novel paradigm for applying CoT reasoning to relevance classification.

Deep learning segmentation relies heavily on labeled data, but manual labeling is laborious and time-consuming, especially for volumetric images such as brain magnetic resonance imaging (MRI). While recent domain-randomization techniques alleviate the dependency on labeled data by synthesizing diverse training images from label maps, they offer limited anatomical variability when very few label maps are available. Semi-supervised self-training addresses label scarcity by iteratively incorporating model predictions into the training set, enabling networks to learn from unlabeled data. In this work, we combine domain randomization with self-training to train three-dimensional skull-stripping networks using as little as a single labeled example. First, we automatically bin voxel intensities, yielding labels we use to synthesize images for training an initial skull-stripping model. Second, we train a convolutional autoencoder (AE) on the labeled example and use its reconstruction error to assess the quality of brain masks predicted for unlabeled data. Third, we select the top-ranking pseudo-labels to fine-tune the network, achieving skull-stripping performance on out-of-distribution data that approaches models trained with more labeled images. We compare AE-based ranking to consistency-based ranking under test-time augmentation, finding that the AE approach yields a stronger correlation with segmentation accuracy. Our results highlight the potential of combining domain randomization and AE-based quality control to enable effective semi-supervised segmentation from extremely limited labeled data. This strategy may ease the labeling burden that slows progress in studies involving new anatomical structures or emerging imaging techniques.

Visual geo-localization for drones faces critical degradation under weather perturbations, \eg, rain and fog, where existing methods struggle with two inherent limitations: 1) Heavy reliance on limited weather categories that constrain generalization, and 2) Suboptimal disentanglement of entangled scene-weather features through pseudo weather categories. We present WeatherPrompt, a multi-modality learning paradigm that establishes weather-invariant representations through fusing the image embedding with the text context. Our framework introduces two key contributions: First, a Training-free Weather Reasoning mechanism that employs off-the-shelf large multi-modality models to synthesize multi-weather textual descriptions through human-like reasoning. It improves the scalability to unseen or complex weather, and could reflect different weather strength. Second, to better disentangle the scene and weather feature, we propose a multi-modality framework with the dynamic gating mechanism driven by the text embedding to adaptively reweight and fuse visual features across modalities. The framework is further optimized by the cross-modal objectives, including image-text contrastive learning and image-text matching, which maps the same scene with different weather conditions closer in the respresentation space. Extensive experiments validate that, under diverse weather conditions, our method achieves competitive recall rates compared to state-of-the-art drone geo-localization methods. Notably, it improves Recall@1 by +13.37\% under night conditions and by 18.69\% under fog and snow conditions.

In this paper, we introduce a systematic framework beyond conventional method to assess LLMs' mathematical-reasoning robustness by stress-testing them on advanced math problems that are mathematically equivalent but with linguistic and parametric variation. These transformations allow us to measure the sensitivity of LLMs to non-mathematical perturbations, thereby enabling a more accurate evaluation of their mathematical reasoning capabilities. Using this new evaluation methodology, we created PutnamGAP, a new benchmark dataset with multiple mathematically-equivalent variations of competition-level math problems. With the new dataset, we evaluate multiple families of representative LLMs and examine their robustness. Across 18 commercial and open-source models we observe sharp performance degradation on the variants. OpenAI's flagship reasoning model, O3, scores 51.5% on the originals but drops by 4.7 percentage points on surface-renaming variants, and by 12.9 percentage points on parametric variants, while smaller models fare far worse. Overall, the results show that the proposed new evaluation methodology is effective for deepening our understanding of the robustness of LLMs and generating new insights for further improving their mathematical reasoning capabilities.

--The growing demand for robust quantum programming frameworks has unveiled a critical limitation: current large language model (LLM) based quantum code assistants heavily rely on remote APIs, introducing challenges related to privacy, latency, and excessive usage costs. Addressing this gap, we propose PennyCoder, a novel lightweight framework for quantum code generation, explicitly designed for local and embedded deployment to enable on-device quantum programming assistance without external API dependence. PennyCoder leverages a fine-tuned version of the LLaMA 3.1-8B model, adapted through parameter-efficient Low-Rank Adaptation (LoRA) techniques combined with domain-specific instruction tuning optimized for the specialized syntax and computational logic of quantum programming in PennyLane, including tasks in quantum machine learning and quantum reinforcement learning. Unlike prior work focused on cloud-based quantum code generation, our approach emphasizes device-native operability while maintaining high model efficacy. We rigorously evaluated PennyCoder over a comprehensive quantum programming dataset, achieving 44.3% accuracy with our fine-tuned model (compared to 33.7% for the base LLaMA 3.1-8B and 40.1% for the RAG-augmented baseline), demonstrating a significant improvement in functional correctness. Quantum computing is rapidly evolving from a theoretical pursuit to a practical technology, propelled by advances in both hardware and software.

Multimodal Machine Translation (MMT) typically enhances text-only translation by incorporating aligned visual features. Despite the remarkable progress, state-of-the-art MMT approaches often rely on paired image-text inputs at inference and are sensitive to irrelevant visual noise, which limits their robustness and practical applicability. To address these issues, we propose D2P-MMT, a diffusion-based dual-branch prompting framework for robust vision-guided translation. Specifically, D2P-MMT requires only the source text and a reconstructed image generated by a pre-trained diffusion model, which naturally filters out distracting visual details while preserving semantic cues. During training, the model jointly learns from both authentic and reconstructed images using a dual-branch prompting strategy, encouraging rich cross-modal interactions. To bridge the modality gap and mitigate training-inference discrepancies, we introduce a distributional alignment loss that enforces consistency between the output distributions of the two branches. Extensive experiments on the Multi30K dataset demonstrate that D2P-MMT achieves superior translation performance compared to existing state-of-the-art approaches.

Instruction tuning has become a foundation for unlocking the capabilities of large-scale pretrained models and improving their performance on complex tasks. Thus, the construction of high-quality instruction datasets is crucial for enhancing model performance and generalizability. Although current instruction datasets have reached tens of millions of samples, models finetuned on them may still struggle with complex instruction following and tasks in rare domains. This is primarily due to limited expansion in both ``coverage'' (coverage of task types and knowledge areas) and ``depth'' (instruction complexity) of the instruction set. To address this issue, we propose a systematic instruction data construction framework, which integrates a hierarchical tagging system, an informative seed selection algorithm, an evolutionary data synthesis process, and a model deficiency diagnosis with targeted data generation. These components form an iterative closed-loop to continuously enhance the coverage and depth of instruction data. Based on this framework, we construct Infinity Instruct Subject, a high-quality dataset containing $\sim$1.5 million instructions. Experiments on multiple foundation models and benchmark tasks demonstrate its effectiveness in improving instruction-following capabilities. Further analyses suggest that Infinity Instruct Subject shows enlarged coverage and depth compared to comparable synthesized instruction datasets. Our work lays a theoretical and practical foundation for the efficient, continuous evolution of instruction datasets, moving from data quantity expansion to qualitative improvement.

Accurate electricity forecasting is crucial for grid stability and energy planning, especially in Benghazi, Libya, where frequent load shedding, generation deficits, and infrastructure limitations persist. This study proposes a data-driven approach to forecast electricity load, generation, and deficits for 2025 using historical data from 2019 (a year marked by instability) and 2023 (a more stable year). Multiple time series models were applied, including ARIMA, seasonal ARIMA, dynamic regression ARIMA, exponential smoothing, extreme gradient boosting, and Long Short-Term Memory (LSTM) neural networks. The dataset was enhanced through missing value imputation, outlier smoothing, and log transformation. Performance was assessed using mean squared error, root mean squared error, mean absolute error, and mean absolute percentage error. LSTM outperformed all other models, showing strong capabilities in modeling non-stationary and seasonal patterns. A key contribution of this work is an optimized LSTM framework that integrates exogenous factors such as temperature and humidity, offering robust performance in forecasting multiple electricity indicators. These results provide practical insights for policymakers and grid operators to enable proactive load management and resource planning in data-scarce, volatile regions.