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 […]
Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring
arXiv:2502.05242v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are becoming increasingly capable, but the mechanisms of their thinking and decision-making processes remain unclear. Chain-of-thoughts (CoTs) have been commonly utilized to externalize LLMs’ thinking, but this strategy fails to accurately reflect LLMs’ thinking process. Techniques based on LLMs’ hidden representations provide an inner perspective to […]
ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation
arXiv:2605.28396v1 Announce Type: cross Abstract: On-policy distillation (OPD) transfers reasoning behavior by training a student on teacher feedback along student-generated trajectories, but standard full-rollout training ties every update to a costly completion and can over-allocate supervision to late positions with low marginal value for the current student. We revisit this assumption through the useful supervision […]
The Principles of Diffusion Models
arXiv:2510.21890v2 Announce Type: replace-cross Abstract: This book presents the core principles that have guided the development of diffusion models, tracing their origins and showing how diverse formulations arise from shared mathematical ideas. Diffusion modeling starts by defining a forward process that gradually corrupts data into noise, linking the data distribution to a simple prior through […]
SwarmHarness: Skill-Based Task Routing via Decentralized Incentive-Aligned AI Agent Networks
arXiv:2605.28764v1 Announce Type: new Abstract: Vast quantities of compute (GPU cycles on personal workstations, idle inference servers, and edge devices between jobs) go unused because no incentive-aligned protocol exists for their owners to share them safely and profitably. Existing approaches either require a trusted central coordinator (cloud marketplaces), demand heavy blockchain infrastructure (Golem, BrokerChain), or […]
Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression
arXiv:2605.28567v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale are (1) matching semantically similar features across multi-layers and (2) compressing large feature circuits into interpretable supernodes. Although these have been treated as separate problems, we show that […]
Agyn: An Open-Source Platform for AI Agents with Scalable On-Demand Execution, Agent Definition as a Code, and Zero-Trust Access
arXiv:2605.27575v1 Announce Type: new Abstract: As organizations move toward production deployments of AI agents, which execute non-deterministic workflows, maintain stateful sessions, and often operate with privileged access to internal services, the engineering challenge shifts from building individual agents to operating them at scale with proper isolation, governance, and security. In this paper we present Agyn, […]
On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation
arXiv:2601.06329v2 Announce Type: replace-cross Abstract: Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving attributes like speaker and emotion, serving as foundation models for spoken dialogue. In prior literature, these models are often evaluated using “global token perplexity”, which directly applies the text perplexity formulation […]
The Computational Boundary of Inference: Capability Internalization, Training, and the Turing Jump
arXiv:2605.27381v1 Announce Type: cross Abstract: Claims about recursive self-improvement in AI often slide from repeated internal revision to the possibility of qualitatively stronger capability without clearly distinguishing the underlying computational regimes. This paper gives a formal separation result in classical computability theory that blocks that move under a precise modeling assumption. For an oracle $A$, […]
Planning a Community Approach to Diabetes Care in Low- and Middle-Income Countries Using Optimization
arXiv:2305.06426v2 Announce Type: replace Abstract: Diabetes is a global health priority, especially in low- and-middle-income countries, where over 50% of premature deaths are attributed to high blood glucose. Community Health Worker (CHW) programs can provide affordable and culturally tailored solutions for early detection and management of diabetes. We introduce an optimization framework to determine personalized […]
Deep Learning Strain Estimation: Is Physics-Based Simulation the Solution?
arXiv:2605.28697v1 Announce Type: cross Abstract: Speckle tracking echocardiography (STE) is the clinical standard for myocardial strain estimation. Despite good performance on global strain (GLS), its accuracy for regional strain remains limited, even though this biomarker is highly relevant for early diagnosis and the characterization of subtle abnormalities. from clinical data. Deep learning is a promising […]