arXiv:2605.27836v1 Announce Type: cross Abstract: We demonstrate an attack on Introspection Adapters (Shenoy et al., 2026).
Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches
arXiv:2605.18692v2 Announce Type: replace Abstract: Optimization models developed by operations research (OR) experts are often deployed as decision-support systems in industrial settings. However, real-world environments are dynamic, with evolving business rules and unforeseen perturbations. In such contexts, end users should ideally re-optimize models to recover feasible and implementable solutions, often without access to the original […]
Discovery Agents for Real-Time Analytics: Toward Proactive Insight Systems
arXiv:2605.27571v1 Announce Type: new Abstract: Modern analytics systems are fundamentally reactive, requiring users to define queries over increasingly complex and continuously evolving data. In real-time streaming environments, this paradigm breaks down, as the space of potential insights becomes too large to enumerate manually. We present a multi-agent architecture for autonomous insight discovery over real-time data […]
Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations
arXiv:2605.27958v1 Announce Type: cross Abstract: Linear probes trained on LLM activations are increasingly proposed as deception-detection metrics, yet report AUROC exceeding 0.96 on clean benchmarks while collapsing under distributional shift. This paper systematically pressure-tests probe-based metrics across the Gemma 3 model family (1B-27B parameters), diagnosing why they fail rather than merely documenting that they fail. […]
Optimal and Diffusion Transports in Machine Learning
arXiv:2512.06797v2 Announce Type: replace-cross Abstract: Several problems in machine learning are naturally expressed as the design and analysis of time-evolving probability distributions. This includes sampling via diffusion methods, optimizing the weights of neural networks, and analyzing the evolution of token distributions across layers of large language models. While the targeted applications differ (samples, weights, tokens), […]
SMILE-Next: Teaching Large Language Models to Detect, Classify, and Reason about Laughter
arXiv:2605.28084v1 Announce Type: cross Abstract: Laughter is a complex social signal that conveys communicative intent beyond amusement. While prior work has focused on isolated laughter analysis tasks, a comprehensive understanding of laughter in real-world scenarios remains underexplored. Therefore, we introduce SMILE-Next, a dataset for real-world laughter understanding with multimodal textual representations and question-answer annotations across […]
Generalized Holographic Reduced Representations
arXiv:2405.09689v2 Announce Type: replace-cross Abstract: Hyperdimensional Computing (HDC) is a computationally and data-efficient paradigm that acts as a bridge between connectionist and symbolic approaches to artificial intelligence (AI). However, HDC’s simplicity poses challenges for encoding complex compositional structures, especially in its binding operation. To address this, we propose Generalized Holographic Reduced Representations (GHRR), an extension […]
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
arXiv:2605.28655v1 Announce Type: new Abstract: Scientific research proceeds through iterative cycles of hypothesis generation, experiment design, execution, and revision. AI agents can automate parts of this process, but existing approaches typically follow a single research trajectory or coordinate through a central planner with fixed objectives. As a result, they struggle to sustain parallel exploration, adapt […]
Text2Model: Modeling Copilots for Text-to-Model Translation
arXiv:2604.12955v3 Announce Type: replace Abstract: There is growing interest in leveraging large language models (LLMs) for text-to-model translation and optimization tasks. This paper aims to advance this line of research by introducing textscText2Model and textscText2Zinc. textscText2Model is a suite of copilots based on several LLM strategies with varying complexity, along with an online leaderboard. textscText2Zinc […]
Cycle Based Computational Pipeline for Extracting Instantaneous Whisking Frequency
arXiv:2605.27573v1 Announce Type: new Abstract: Whisking is a rhythmic and adaptive behavior that rodents use to probe and interact with their environment, and the frequency of movement reflects both sensorimotor processing and internal brain states. A robust and traditional method of whisker frequency estimation uses power spectral analysis of whisker position spanning several cycles. To […]
EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content Detection
arXiv:2505.17654v4 Announce Type: replace-cross Abstract: E-commerce platforms increasingly rely on Large Language Models (LLMs) and Vision Language Models (VLMs) to detect illicit or misleading product content. However, these models remain vulnerable to evasive content, which refers to inputs that have been deliberately modified through techniques such as word splitting, euphemistic language, or image cropping to […]
Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor
arXiv:2605.28713v1 Announce Type: new Abstract: Context compression aims to shorten long context inputs with minimal information loss for LLM inference acceleration. While existing methods have shown promise, they typically rely on complex compression modules or compression-specific training, leaving the intrinsic capabilities of LLMs underexplored. In contrast, this work reveals that a thinking model itself can […]