arXiv:2603.28817v1 Announce Type: cross Abstract: Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make SLMs suitable for resource-constrained and efficient deployment on edge devices. However, existing jailbreak defenses show limited robustness against heterogeneous attacks, […]
Time is Not Compute: Scaling Laws for Wall-Clock Constrained Training on Consumer GPUs
arXiv:2603.28823v1 Announce Type: cross Abstract: Scaling laws relate model quality to compute budget (FLOPs), but practitioners face wall-clock time constraints, not compute budgets. We study optimal model sizing under fixed time budgets from 5 minutes to 24 hours on consumer GPUs (RTX 4090). Across 70+ runs spanning 50M–1031M parameters, we find: (1)~at each time budget […]
UniAI-GraphRAG: Synergizing Ontology-Guided Extraction, Multi-Dimensional Clustering, and Dual-Channel Fusion for Robust Multi-Hop Reasoning
arXiv:2603.25152v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems face significant challenges in complex reasoning, multi-hop queries, and domain-specific QA. While existing GraphRAG frameworks have made progress in structural knowledge organization, they still have limitations in cross-industry adaptability, community report integrity, and retrieval performance. This paper proposes UniAI-GraphRAG, an enhanced framework built upon open-source GraphRAG. […]
Balancing Efficiency and Empathy: Healthcare Providers’ Perspectives on AI-Supported Workflows for Serious Illness Conversations in the Emergency Department
arXiv:2506.00241v2 Announce Type: replace-cross Abstract: Serious Illness Conversations (SICs), discussions about values and care preferences for patients with life-threatening illness, rarely occur in Emergency Departments (EDs), despite evidence that early conversations improve care alignment and reduce unnecessary interventions. We interviewed 11 ED providers to identify challenges in SICs and opportunities for technology support, with a […]
Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks
arXiv:2509.23067v2 Announce Type: replace-cross Abstract: The rising cost of acquiring supervised data has driven significant interest in self-improvement for large language models (LLMs). Straightforward unsupervised signals like majority voting have proven effective in generating pseudo-labels for verifiable tasks, while their applicability to unverifiable tasks (e.g., translation) is limited by the open-ended character of responses. As […]
GenOL: Generating Diverse Examples for Name-only Online Learning
arXiv:2403.10853v4 Announce Type: replace-cross Abstract: Online learning methods often rely on supervised data. However, under data distribution shifts, such as in continual learning (CL), where continuously arriving online data streams incorporate new concepts (e.g., classes), real-time manual annotation is impractical due to its costs and latency, which hinder real-time adaptation. To alleviate this, ‘name-only’ setup […]
QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
arXiv:2507.13266v4 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has emerged as a central paradigm for training large language models (LLMs) in reasoning tasks. Yet recent studies question RL’s ability to incentivize reasoning capacity beyond the base model. This raises a key challenge: how can RL be adapted to solve harder reasoning problems more effectively? To […]
ARROW: An Adaptive Rollout and Routing Method for Global Weather Forecasting
arXiv:2510.09734v2 Announce Type: replace-cross Abstract: Weather forecasting is a fundamental task in spatiotemporal data analysis, with broad applications across a wide range of domains. Existing data-driven forecasting methods typically model atmospheric dynamics over a fixed short time interval, e.g., 6 hours, and rely on naive autoregression-based rollout for long-term forecasting, e.g., 5 days. However, this […]
Sampling from the Solution Space and Metabolic Environments of Genome-Scale Metabolic Models
arXiv:2603.29546v1 Announce Type: new Abstract: Flux sampling is an analysis that, based on a distribution, picks randomly an efficient number of points from the solution space of a metabolic model. Unlike most constraint-based analyses, flux sampling does not require an objective function to optimize, allowing for the exploration of the whole spectrum of the phenotypes […]
ASI-Evolve: AI Accelerates AI
arXiv:2603.29640v1 Announce Type: new Abstract: Can AI accelerate the development of AI itself? While recent agentic systems have shown strong performance on well-scoped tasks with rapid feedback, it remains unclear whether they can tackle the costly, long-horizon, and weakly supervised research loops that drive real AI progress. We present ASI-Evolve, an agentic framework for AI-for-AI […]
Structural and dynamical strategies to prevent runaway excitation in reservoir computing
arXiv:2603.29597v1 Announce Type: new Abstract: Reservoirs, typically implemented as recurrent neural networks with fixed random connection weights, can be combined with a simple trained readout layer to perform a wide range of computational tasks. However, increasing the magnitude of reservoir connection weights to exploit nonlinear dynamics can cause the network to develop strong spontaneous activity […]
FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration
arXiv:2603.29557v1 Announce Type: new Abstract: Scientific idea generation (SIG) is critical to AI-driven autonomous research, yet existing approaches are often constrained by a static retrieval-then-generation paradigm, leading to homogeneous and insufficiently divergent ideas. In this work, we propose FlowPIE, a tightly coupled retrieval-generation framework that treats literature exploration and idea generation as a co-evolving process. […]