Most approaches to long-context processing increase the complexity of the transformer's internal architecture by integrating mechanisms such as recurrence or auxiliary memory modules. In this work, we introduce an alternative approach that modifies the input representation itself, rather than the transformer architecture. Inspired by cognitive models of human memory, our method applies a scale-invariant logarithmic compression to the input tokens. The resulting compressed representation is processed by a standard, unmodified transformer, preserving architectural simplicity. We evaluate this approach on the WikiText-103 and PG-19 language modeling benchmarks, showing a reduction in perplexity compared to uncompressed baselines. Moreover, performance improves consistently with longer compressed temporal contexts, showing that input-level logarithmic compression is a simple and effective way to extend a transformer's long-range memory.

Multimodal large language models (MLLMs) excel at vision-language tasks such as VQA and document understanding, yet precise coordinate prediction remains challenging. High-resolution inputs exacerbate this difficulty by producing long token sequences that weaken positional encodings and introduce directional biases in coordinate outputs. We investigate this phenomenon by analyzing how MLLMs behave when visual positional encodings (VPEs) are deliberately perturbed through shuffling. Our analysis reveals that such perturbations induce predictable, non-random coordinate biases rather than random errors, suggesting that models rely on internal positional priors when spatial grounding signals are degraded. Crucially, we observe similar directional error patterns in natural high-resolution datasets, indicating that positional encoding failures are a key bottleneck for accurate coordinate prediction at scale. To address this issue, we propose Vision-PE Shuffle Guidance (VPSG), a training-free test-time method that leverages the directional nature of these biases for correction. VPSG runs auxiliary decoding with shuffled VPEs to isolate position-unconditioned tendencies, then uses this as negative evidence to guide digit prediction while preserving coordinate format through a lightweight finite-state machine. Experiments on ScreenSpot-Pro demonstrate reliable improvements, highlighting positional encoding robustness as a critical factor for spatial reasoning in MLLMs.

Brain-Computer Interfaces (BCIs) offer a direct communication pathway between the human brain and external devices, holding significant promise for individuals with severe neurological impairments. However, their widespread adoption is hindered by critical limitations, such as low information transfer rates and extensive user-specific calibration. To overcome these challenges, recent research has explored the integration of Large Language Models (LLMs), extending the focus from simple command decoding to understanding complex cognitive states. Despite these advancements, deploying agentic AI faces technical hurdles and ethical concerns. Due to the lack of comprehensive discussion on this emerging direction, this position paper argues that the field is poised for a paradigm extension from BCI to Brain-Agent Collaboration (BAC). We emphasize reframing agents as active and collaborative partners for intelligent assistance rather than passive brain signal data processors, demanding a focus on ethical data handling, model reliability, and a robust human-agent collaboration framework to ensure these systems are safe, trustworthy, and effective.

The field of computer architecture, which bridges high-level software abstractions and low-level hardware implementations, remains absent from current large language model (LLM) evaluations. To this end, we present QuArch (pronounced 'quark'), the first benchmark designed to facilitate the development and evaluation of LLM knowledge and reasoning capabilities specifically in computer architecture. QuArch provides a comprehensive collection of 2,671 expert-validated question-answer (QA) pairs covering various aspects of computer architecture, including processor design, memory systems, and interconnection networks. Our evaluation reveals that while frontier models possess domain-specific knowledge, they struggle with skills that require higher-order thinking in computer architecture. Frontier model accuracies vary widely (from 34% to 72%) on these advanced questions, highlighting persistent gaps in architectural reasoning across analysis, design, and implementation QAs. By holistically assessing fundamental skills, QuArch provides a foundation for building and measuring LLM capabilities that can accelerate innovation in computing systems. With over 140 contributors from 40 institutions, this benchmark represents a community effort to set the standard for architectural reasoning in LLM evaluation.

Large language models (LLMs) remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry, a systematic methodology for training compact attacker models to automatically generate narrative-based jailbreak prompts in a one-shot manner. Our approach transforms adversarial prompt discovery from manual craftsmanship into a reproducible scientific process, enabling proactive vulnerability assessment in AI-driven security systems. Developed for the OpenAI GPT-OSS-20B Red-Teaming Challenge, we use parameter-efficient fine-tuning (LoRA) on Mistral-7B with a curated dataset derived from AdvBench, achieving an 81.0% Attack Success Rate (ASR) against GPT-OSS-20B on a held-out test set of 200 items. Cross-model evaluation reveals significant variation in vulnerability patterns: our attacks achieve 66.5% ASR against GPT-4, 79.5% on Llama-3 and 33.0% against Gemini 2.5 Flash, demonstrating both broad applicability and model-specific defensive strengths in cybersecurity contexts. This represents a 54x improvement over direct prompting (1.5% ASR) and demonstrates systematic vulnerabilities in current safety alignment approaches. Our analysis reveals that technical domains (Cybersecurity: 93% ASR) and deception-based attacks (Fraud: 87.8% ASR) are particularly vulnerable, highlighting threats to AI-integrated threat detection, malware analysis, and secure systems, while physical harm categories show greater resistance (55.6% ASR). We employ automated harmfulness evaluation using Claude Sonnet 4, cross-validated with human expert assessment, ensuring reliable and scalable evaluation for cybersecurity red-teaming. Finally, we analyze failure mechanisms and discuss defensive strategies to mitigate these vulnerabilities in AI for cybersecurity.

Large Language Models (LLMs) still produce gender-stereotyped language even in occupation-neutral contexts that reflect deep societal biases (Rudinger et al., 2018). To address this, prior work has proposed prompting, constrained decoding (Dathathri et al., 2020; Zhou et al., 2024), post-processing, and fine-tuning-based alignment (Rafailov et al., 2023; Ravfogel et al., 2022). However, the comparative efficacy and learning dynamics remain little understood. We report a comparative analysis of six control techniques for bias mitigation: prompt-only, generate-and-filter, DFA-based Ctrl-G decoding, Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Iterative Nullspace Projection (INLP). We evaluate each method on a compositional constraint task. This task requires generating sentences that contain at least one agentic and one communal descriptor for each of the twenty Winogender-derived occupations. We quantify trade-offs between control strength and naturalness with evaluations of constraint compliance, lexical diversity, and fluency. Our results reveal key contrasts among the methods: SFT achieves 99.87 +- 0.15% compliance and high lexical diversity, while DPO, despite similar training stability, fails at 4.53 +- 0.82%. Ctrl-G guarantees perfect compliance, but at the cost of severely reduced fluency and diversity. Preference-based learning fundamentally differs: it cannot satisfy compositional constraints, as binary preference signals encode ranking, not logical conjunctions. Only explicit positive supervision enables mitigation of compositional biases; preference-based alignment fails to generalize logical structures, underscoring the limitations of preference learning and the necessity of explicit supervision for fair and fluent controlled generation.

We tackle the challenge of training reliable code-fixing agents in real repositories, where complex builds and shifting dependencies make evaluation unstable. We developed a verifiable pipeline with success defined as post-fix build validation and improved reproducibility across 1K real issues by pinning dependencies and disabling automatic upgrades. Building on this, we introduced a scalable simplified pipeline for large-scale reinforcement learning (RL). Using this setup, we supervise fine-tuned Qwen3-32B in the full pipeline and applied RL on top of SFT model in the simplified environment. The SFT model distilled from GPT-4.1 trajectories performs on par while being 56 smaller, and RL added 7-20% absolute gains under matched train-test conditions. "Thinking mode" was on par or worse in our experiments. Both SFT and RL models failed to generalize across environments, highlighting the importance of matching train-test environments for building reliable real-world code-fixing agents. Large language models (LLMs) have transformed the landscape of code intelligence, powering systems such as GitHub Copilot (Zhang et al., 2023), ChatGPT Code Interpreter (Mutch, 2025), and AlphaCode (Li et al., 2022). These models excel at code completion, bug fixing, and even multi-step development workflows, offering tangible productivity gains in both individual and collaborative programming settings.

Graph neural networks (GNNs) are known to operate with high accuracy on learning from graph-structured data, but they suffer from high computational and resource costs. Neural network compression methods are used to reduce the model size while maintaining reasonable accuracy. Two of the common neural network compression techniques include pruning and quantization. In this research, we empirically examine the effects of three pruning methods and three quantization methods on different GNN models, including graph classification tasks, node classification tasks, and link prediction. We conducted all experiments on three graph datasets, including Cora, Proteins, and BBBP. Our findings demonstrate that unstructured fine-grained and global pruning can significantly reduce the model's size(50\%) while maintaining or even improving precision after fine-tuning the pruned model. The evaluation of different quantization methods on GNN shows diverse impacts on accuracy, inference time, and model size across different datasets.

With the rise of online and virtual learning, monitoring and enhancing student engagement have become an important aspect of effective education. Traditional methods of assessing a student's involvement might not be applicable directly to virtual environments. In this study, we focused on this problem and addressed the need to develop an automated system to detect student engagement levels during online learning. We proposed a novel training method which can discourage a model from leveraging sensitive features like gender for its predictions. The proposed method offers benefits not only in the enforcement of ethical standards, but also to enhance interpretability of the model predictions. We applied an attribute-orthogonal regularization technique to a split-model classifier, which uses multiple transfer learning strategies to achieve effective results in reducing disparity in the distribution of prediction for sensitivity groups from a Pearson correlation coefficient of 0.897 for the unmitigated model, to 0.999 for the mitigated model. The source code for this project is available on https://github.com/ashiskb/elearning-engagement-study .

Anomaly detection in surveillance videos remains a challenging task due to the diversity of abnormal events, class imbalance, and scene-dependent visual clutter. To address these issues, we propose a robust deep learning framework that integrates human-centric preprocessing with spatio-temporal modeling for multi-class anomaly classification. Our pipeline begins by applying YOLO-World - an open-vocabulary vision-language detector - to identify human instances in raw video clips, followed by ByteTrack for consistent identity-aware tracking. Background regions outside detected bounding boxes are suppressed via Gaussian blurring, effectively reducing scene-specific distractions and focusing the model on behaviorally relevant foreground content. The refined frames are then processed by an ImageNet-pretrained InceptionV3 network for spatial feature extraction, and temporal dynamics are captured using a bidirectional LSTM (BiLSTM) for sequence-level classification. Evaluated on a five-class subset of the UCF-Crime dataset (Normal, Burglary, Fighting, Arson, Explosion), our method achieves a mean test accuracy of 92.41% across three independent trials, with per-class F1-scores consistently exceeding 0.85. Comprehensive evaluation metrics - including confusion matrices, ROC curves, and macro/weighted averages - demonstrate strong generalization and resilience to class imbalance. The results confirm that foreground-focused preprocessing significantly enhances anomaly discrimination in real-world surveillance scenarios.