arXiv:2605.06583v1 Announce Type: new Abstract: We propose a deterministic adjoint matching framework that formulates human preference alignment for flow-based generative models as an optimal control problem over velocity fields. One can directly regress the control toward a value-gradient-induced target under the current policy, leading to a simple and stable training objective. Building on this perspective, […]
Contrastive Identification and Generation in the Limit
arXiv:2605.06211v1 Announce Type: cross Abstract: In the classical identification in the limit model of Gold [1967], a stream of positive examples is presented round by round, and the learner must eventually recover the target hypothesis. Recently, Kleinberg and Mullainathan [2024] introduced generation in the limit, where the learner instead must eventually output novel elements of […]
MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
arXiv:2605.06623v1 Announce Type: new Abstract: Large language model (LLM)-based Multi-agent systems (MAS) have shown promise in tackling complex collaborative tasks, where agents are typically orchestrated via role-specific prompts. While the quality of these prompts is pivotal, jointly optimizing them across interacting agents remains a non-trivial challenge, primarily due to the misalignment between local agent objectives […]
FoodCHA: Multi-Modal LLM Agent for Fine-Grained Food Analysis
arXiv:2605.05499v1 Announce Type: new Abstract: The widespread adoption of camera-equipped mobile devices and wearables has enabled convenient capture of meal images, making food recognition a key component for real time dietary monitoring. However, real-world food images present challenges due to high intra-class similarity and the frequent presence of multiple food items within a single image. […]
Log-Likelihood, Simpson’s Paradox, and the Detection of Machine-Generated Text
arXiv:2605.06294v1 Announce Type: cross Abstract: The ability to reliably distinguish human-written text from that generated by large language models is of profound societal importance. The dominant approach to this problem exploits the likelihood hypothesis: that machine-generated text should appear more probable to a detector language model than human-written text. However, we demonstrate that the token-level […]
MedMamba: Recasting Mamba for Medical Time Series Classification
arXiv:2605.05214v1 Announce Type: cross Abstract: Medical time series, such as electrocardiograms (ECG) and electroencephalograms (EEG), exhibit complex temporal dynamics and structured cross-channel dependencies, posing fundamental challenges for automated analysis. Conventional convolutional and recurrent models struggle to capture long-range dependencies, while Transformer-based approaches incur quadratic complexity and often introduce redundant interactions that are misaligned with the […]
Housing Potential Common Data Model and City Digital Twin
arXiv:2605.05535v1 Announce Type: new Abstract: The evaluation of housing potential requires consideration of a location from multiple perspectives, ranging from zoning and land use to population characteristics and access to services. This research introduces the Housing Potential Common Data Model (HPCDM) to overcome existing data silos, serving as a standard to support integration and interoperability […]
Sparse Prefix Caching for Hybrid and Recurrent LLM Serving
arXiv:2605.05219v1 Announce Type: cross Abstract: Prefix caching is a key latency optimization for autoregressive LLM serving, yet existing systems assume dense per-token key/value reuse. State-space models change the structure of the problem: a recurrent layer can resume from a single stored state rather than requiring the entire token history. This asymmetry opens a new design […]
Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
arXiv:2605.06376v1 Announce Type: cross Abstract: Step distillation has become a leading technique for accelerating diffusion models, among which Distribution Matching Distillation (DMD) and Consistency Distillation are two representative paradigms. While consistency methods enforce self-consistency along the full PF-ODE trajectory to steer it toward the clean data manifold, vanilla DMD relies on sparse supervision at a […]
Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
arXiv:2605.05224v1 Announce Type: cross Abstract: The unauthorized use of personal data in model training has emerged as a growing privacy threat. Unlearnable examples (UEs) address this issue by embedding imperceptible perturbations into benign examples to obstruct feature learning. However, existing studies mainly evaluate UEs under from-scratch training settings, leaving their behavior under the widely adopted […]
AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases
arXiv:2605.05538v1 Announce Type: new Abstract: We present AgenticRAG, a practical agentic harness for retrieval and analysis over enterprise knowledge bases. Standard RAG pipelines place significant burden of grounding on the search stack, constraining the language model to a fixed candidate set chosen deep in the retrieval process. Our approach reduces this overdependence by layering a […]
Evolutionary fine tuning of quantized convolution-based deep learning models
arXiv:2605.05228v1 Announce Type: cross Abstract: Deep learning models are the most efficient models in many machine learning tasks. The main disadvantage when using them in IoT, mobile devices, independent autonomous or real-time systems is their complexity and memory size. Therefore, much research has concentrated on compression techniques of deep learning architectures. One of the most […]