arXiv:2604.24832v1 Announce Type: cross Abstract: Masked diffusion language models (MDMs) have recently emerged as a promising alternative to standard autoregressive large language models (AR-LLMs), yet their optimization can be substantially less stable. We study blockwise MDMs and compare them with AR-LLMs on three controlled tasks that stress different aspects of structured generation: in-context linear regression, […]
S-SONDO: Self-Supervised Knowledge Distillation for General Audio Foundation Models
arXiv:2604.24933v1 Announce Type: new Abstract: General audio foundation models have recently achieved remarkable progress, enabling strong performance across diverse tasks. However, state-of-the-art models remain extremely large, often with hundreds of millions of parameters, leading to high inference costs and limited deployability on edge devices. Knowledge distillation is a proven strategy for model compression, but prior […]
Adaptive Prompt Embedding Optimization for LLM Jailbreaking
arXiv:2604.24983v1 Announce Type: new Abstract: Existing white-box jailbreak attacks against aligned LLMs typically append discrete adversarial suffixes to the user prompt, which visibly alters the prompt and operates in a combinatorial token space. Prior work has avoided directly optimizing the embeddings of the original prompt tokens, presumably because perturbing them risks destroying the prompt’s semantic […]
Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate
arXiv:2604.24881v1 Announce Type: new Abstract: Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency, we develop a framework that distills multi-agent debate into a single LLM through a two-stage fine-tuning pipeline combining debate structure learning […]
Co-Director: Agentic Generative Video Storytelling
arXiv:2604.24842v1 Announce Type: new Abstract: While diffusion models generate high-fidelity video clips, transforming them into coherent storytelling engines remains challenging. Current agentic pipelines automate this via chained modules but suffer from semantic drift and cascading failures due to independent, handcrafted prompting. We present Co-Director, a hierarchical multi-agent framework formalizing video storytelling as a global optimization […]
A multi-stage soft computing framework for complex disease modelling and decision support: A liver cirrhosis case study
arXiv:2604.24796v1 Announce Type: new Abstract: Liver cirrhosis is a major global health problem causing millions of deaths annually, and timely detection with aggressive treatment can significantly improve patients’ quality of life. Modelling complex diseases from biomedical data is computationally challenging due to high dimensionality, strong feature correlations, noise, and limited labelled samples. Conventional Machine Learning […]
A First Look at the Security Issues in the Model Context Protocol Ecosystem
arXiv:2510.16558v2 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) has emerged as a standard for connecting large language models (LLMs) with external tools. However, this MCP ecosystem introduces new security risks across hosts, servers, and registries. In this paper, we present the first cross-entity security study of MCP under a two-stage attack surface. At […]
Toward a Science of Intent: Closure Gaps and Delegation Envelopes for Open-World AI Agents
arXiv:2604.25000v1 Announce Type: new Abstract: Recent work has framed intelligence in verifiable tasks as reducing time-to-solution through learned structure and test-time search, while systems work has explored learned runtimes in which computation, memory and I/O migrate into model state. These perspectives do not explain why capable models remain difficult to deploy in open institutions. We […]
MGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning Evaluation
arXiv:2601.21225v2 Announce Type: replace-cross Abstract: Large language models have made substantial progress in mathematical reasoning. However, benchmark development for multilingual evaluation has lagged behind English in both difficulty and recency. Recently, GSM-Symbolic showed a strong evidence of high variance when models are evaluated on different instantiations of the same question; however, the evaluation was conducted […]
MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives
arXiv:2604.24833v1 Announce Type: cross Abstract: Despite transformative advances in generative motion synthesis, real-time interactive motion control remains dominated by traditional techniques. In this work, we identify two key challenges in bridging research and production: 1) Real-time scalability: Industry applications demand real-time generation of a vast repertoire of motion skills, while generative methods exhibit significant degradation […]
Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
arXiv:2604.03472v2 Announce Type: replace-cross Abstract: Co-evolutionary self-play, where one language model generates problems and another solves them, promises autonomous curriculum learning without human supervision. In practice, the proposer quickly converges to a narrow distribution of problems that satisfy the reward function. This diversity collapse renders the curriculum uninformative for the solver, stalling the co-evolutionary loop. […]
AIDOVECL: AI-generated Dataset of Outpainted Vehicles for Eye-level Classification and Localization
arXiv:2410.24116v3 Announce Type: replace-cross Abstract: Image labeling is a critical bottleneck in the development of computer vision technologies, often constraining machine learning performance due to the time-intensive nature of manual annotations. This work introduces a novel approach that leverages outpainting to mitigate annotated data scarcity by generating artificial contexts and annotations, significantly reducing labeling efforts. […]