arXiv:2605.27569v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of specific training records from a deployed model without retraining from scratch. Current protocols verify this at the output level through membership inference, retain accuracy, and forget-set accuracy, but a model can satisfy all three whilst still encoding forgotten records in its intermediate […]
On the Origin of Synthetic Information by Means of Steganographic Inheritance
arXiv:2605.27551v1 Announce Type: new Abstract: The origin of species has been the mystery of mysteries in natural science. By analogy, the origin of synthetic information, we suggest, is the mystery of mysteries in information science. The question carries a moral weight that a technical account can neither fully resolve nor responsibly ignore, as its impact […]
DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM-based Scheduling Agents
arXiv:2605.27566v1 Announce Type: new Abstract: Progress in neural combinatorial optimization for Dynamic Flexible Job Shop Scheduling Problem (DFJSP) is currently hindered by a methodological tension: static benchmarks encourage benchmark overfitting, while uncalibrated generators obscure algorithmic capability with stochastic noise. To resolve this, we introduce textbfDynaSchedBench, a diagnostic framework for DFJSP that rigorously controls the instance-generation […]
Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code
arXiv:2603.24631v2 Announce Type: replace-cross Abstract: Code agents resolve 65-70% of SWE-bench Verified issues, but Pass@1 cannot tell us why the rest fail, and, as we show, capable-model failures are systematically misdiagnosed without trajectory data. We introduce TRAJEVAL, a training-free decomposition of agent trajectories into reference-patch-aligned search, read, and edit stages, and apply it across 16,758 […]
Escaping Mode Collapse in LLM Generation via Geometric Regulation
arXiv:2605.00435v2 Announce Type: replace-cross Abstract: Mode collapse is a persistent challenge in generative modeling and appears in autoregressive text generation as behaviors ranging from explicit looping to gradual loss of diversity and premature trajectory convergence. We take a dynamical-systems view and reinterpret mode collapse as reduced state-space accessibility caused by *geometric collapse*: during generation, the […]
Comparative Analysis of Liquid Neural Networks and LSTM for Sequential Pattern Recognition: Robustness, Efficiency, and Clinical Utility
arXiv:2605.27467v1 Announce Type: cross Abstract: Traditional Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) units operate on discrete time steps, often failing to capture the fluid temporal dynamics of real-world physical processes. Liquid Neural Networks (LNNs), specifically Closed-form Continuous-time (CfC) networks, address this by modeling the hidden state evolution as a continuous differential equation. […]
On the Subgaussianity of Quantized Linear Maps: An AI-Assisted Note
arXiv:2605.27563v1 Announce Type: cross Abstract: This short note presents a dimension-independent subgaussian concentration bound for Gaussian vectors under coordinate-wise nonlinear mappings. Discovered by Gemini 3.5 Flash, this result applies to any bounded function under a well-conditioned covariance. We apply this tool to answer a question of Simone Bombari on sign-quantized linear maps $Y = textsgn(Wx)$.
StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation
arXiv:2605.27393v1 Announce Type: cross Abstract: Large language models (LLMs) can generate fluent dialogue, but prior works lack situational grounding, dynamic strategy control, and evaluation aligned with clinical standards in motivational interviewing (MI). We introduce StoryMI, a multi-LLM agent framework for controllable MI dialogue generation, where questionnaire-based client profiles are expanded into situational stories that provide […]
Tackling Multimodal Learning Challenges with Mixture-of-Expert: A Survey
arXiv:2605.27431v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across diverse modalities and tasks. Despite its growing success, a comprehensive and systematic review on the MoE metho addressing multimodal challenges remains lacking. Existing surveys tend to evaluate either multimodal learning or MoE independently from […]
DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution
arXiv:2605.28678v1 Announce Type: new Abstract: Speculative reasoning has recently been proposed as a means to accelerate reasoning-intensive generation in large multimodal models, but its effectiveness is often constrained by misalignment between speculative drafts and target-verified reasoning. In this work, we introduce DREAM-R, a framework that substantially improves the performance of speculative reasoning. At its core, […]
Calibrating Conservatism for Scalable Oversight
arXiv:2605.28807v1 Announce Type: new Abstract: Agentic AI systems capable of autonomous planning and extended environmental interaction pose a fundamental control problem: how can humans maintain meaningful oversight of systems that may exceed their own capabilities? Existing approaches to scalable oversight rely on complex assumptions, remain largely heuristic, or lack practical methods for sequential settings with […]
PhyloFrame: A DataFrame-based Library for Fast, Flexible Phylogenetic Computation
arXiv:2605.28545v1 Announce Type: new Abstract: PhyloFrame is a Python library for phylogenetic computation targeting the gap between specialist, compiler-optimized operations and flexible, script-based workflows — with emphasis on fast, memory-efficient operations for very large tree sizes (e.g., $geq$ 300,000 taxa). PhyloFrame is built around a DataFrame-based tree representation, where each row corresponds to a node […]