arXiv:2604.18655v2 Announce Type: replace-cross Abstract: Deploying large language models (LLMs) on smartphones poses significant engineering challenges due to stringent constraints on memory, latency, and runtime flexibility. In this work, we present a hardware-aware framework for efficient on-device inference of a LLaMA-based multilingual foundation model supporting multiple use cases on Samsung Galaxy S24 and S25 devices […]
Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets
arXiv:2604.22294v1 Announce Type: cross Abstract: Real-world document question answering is challenging. Analysts must synthesize evidence across multiple documents and different parts of each document. However, any fixed LLM context window can be exceeded as document collections grow. A common workaround is to decompose documents into chunks and assemble answers from chunk-level outputs, but this introduces […]
UR$^2$: Unify RAG and Reasoning through Reinforcement Learning
arXiv:2508.06165v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown strong capabilities through two complementary paradigms: Retrieval-Augmented Generation (RAG) for knowledge grounding and Reinforcement Learning from Verifiable Rewards (RLVR) for complex reasoning. However, existing attempts to unify these paradigms remain narrow in scope, typically limited to open-domain QA with fixed retrieval settings, which constrains […]
Test-Time Matching: Unlocking Compositional Reasoning in Multimodal Models
arXiv:2510.07632v2 Announce Type: replace Abstract: Frontier AI models have achieved remarkable progress, yet recent studies suggest they struggle with compositional reasoning, often performing at or below random chance on established benchmarks. We revisit this problem and show that widely used evaluation metrics systematically underestimate model capability. To correct this artifact, we introduce a group matching […]
Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy
arXiv:2604.22562v1 Announce Type: cross Abstract: Client contribution estimation in Federated Learning is necessary for identifying clients’ importance and for providing fair rewards. Current methods often rely on server-side validation data or self-reported client information, which can compromise privacy or be susceptible to manipulation. We introduce a data-free signal based on the matrix von Neumann (spectral) […]
Multiplex Hypergraph Modeling of Higher Order Structures in Psychometric Networks
arXiv:2604.22744v1 Announce Type: cross Abstract: Psychiatric disorders have been traditionally conceptualized as latent conditions producing observable symptoms, but recent studies suggest that psychopathology may emerge from symptoms interactions. Psychometric networking model these relations focusing on pairwise associations but overlooks higher-order dependencies arising among groups of variables. These dependencies may reflect synergistic mechanisms, where joint symptom […]
Teaching an Agent to Sketch One Part at a Time
arXiv:2603.19500v2 Announce Type: replace Abstract: We develop a method for producing vector sketches one part at a time. To do this, we train a multi-modal language model-based agent using a novel multi-turn process-reward reinforcement learning following supervised fine-tuning. Our approach is enabled by a new dataset we call ControlSketch-Part, containing rich part-level annotations for sketches, […]
CAP: Controllable Alignment Prompting for Unlearning in LLMs
arXiv:2604.21251v2 Announce Type: replace-cross Abstract: Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensitive information, necessitating selective knowledge unlearning for regulatory compliance and ethical safety. However, existing parameter-modifying methods face fundamental limitations: high computational costs, uncontrollable forgetting boundaries, and strict dependency on model weight access. These constraints render them impractical for closed-source […]
How Supply Chain Dependencies Complicate Bias Measurement and Accountability Attribution in AI Hiring Applications
arXiv:2604.22679v1 Announce Type: cross Abstract: The increasing adoption of AI systems in hiring has raised concerns about algorithmic bias and accountability, prompting regulatory responses including the EU AI Act, NYC Local Law 144, and Colorado’s AI Act. While existing research examines bias through technical or regulatory lenses, both perspectives overlook a fundamental challenge: modern AI […]
AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage
arXiv:2505.20662v4 Announce Type: replace Abstract: Efficient reproduction of research papers is pivotal to accelerating scientific progress. However, the increasing complexity of proposed methods often renders reproduction a labor-intensive endeavor, necessitating profound domain expertise. To address this, we introduce the paper lineage, which systematically mines implicit knowledge from the cited literature. This algorithm serves as the […]
Enzyme-Substrate Complex Formation Modulates Diffusion-Driven Patterning In Metabolic Pathways
arXiv:2512.15737v3 Announce Type: replace Abstract: Spatial organization in metabolic pathways can arise from the interplay between enzymatic reaction kinetics and diffusion-driven instabilities. In this work we investigate how reversible enzyme–substrate binding influences pattern formation in a two-step metabolic pathway. Starting from a mechanistic description in which the substrate reversibly binds to the first enzyme before […]
PrivSTRUCT: Untangling Data Purpose Compliance of Privacy Policies in Google Play Store
arXiv:2604.22157v1 Announce Type: cross Abstract: Existing research typically treats privacy policies as flat, uniform text, extracting information without regard for the document’s logical hierarchy. Disregard for structural cues of section headings designed to guide the reader, often leads automated methods to entangle distinct data practices, particularly when linking sensitive data items to their specific purposes. […]