arXiv:2601.19404v1 Announce Type: new Abstract: Within the domain of large language models, reinforcement fine-tuning algorithms necessitate the generation of a complete reasoning trajectory beginning from the input query, which incurs significant computational overhead during the rollout phase of training. To address this issue, we analyze the impact of different segments of the reasoning path on […]
Fauna Sprout: A lightweight, approachable, developer-ready humanoid robot
arXiv:2601.18963v1 Announce Type: cross Abstract: Recent advances in learned control, large-scale simulation, and generative models have accelerated progress toward general-purpose robotic controllers, yet the field still lacks platforms suitable for safe, expressive, long-term deployment in human environments. Most existing humanoids are either closed industrial systems or academic prototypes that are difficult to deploy and operate […]
SingMOS-Pro: An Comprehensive Benchmark for Singing Quality Assessment
arXiv:2510.01812v4 Announce Type: replace-cross Abstract: Singing voice generation progresses rapidly, yet evaluating singing quality remains a critical challenge. Human subjective assessment, typically in the form of listening tests, is costly and time consuming, while existing objective metrics capture only limited perceptual aspects. In this work, we introduce SingMOS-Pro, a dataset for automatic singing quality assessment. […]
Temporal Lifting as Latent-Space Regularization for Continuous-Time Flow Models in AI Systems
arXiv:2510.09805v2 Announce Type: replace-cross Abstract: We present a latent-space formulation of adaptive temporal lifting for continuous-time dynamical systems. The method introduces a smooth monotone mapping $t mapsto tau(t)$ that regularizes near-singular behavior of the underlying flow while preserving its conservation laws. In the lifted coordinate, trajectories such as those of the incompressible Navier-Stokes equations on […]
LLM-Specific Utility: A New Perspective for Retrieval-Augmented Generation
arXiv:2510.11358v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) is typically optimized for topical relevance, yet its success ultimately depends on whether retrieved passages are useful for a large language model (LLM) to generate correct and complete answers. We argue that such utility is often LLM-specific rather than universal, due to differences in models’ knowledge, reasoning, […]
Riddle Quest : The Enigma of Words
arXiv:2601.19273v1 Announce Type: cross Abstract: Riddles are concise linguistic puzzles that describe an object or idea through indirect, figurative, or playful clues. They are a longstanding form of creative expression, requiring the solver to interpret hints, recognize patterns, and draw inferences to identify the answers. In this work, we introduce a simple pipeline for creating […]
From Observations to Events: Event-Aware World Model for Reinforcement Learning
arXiv:2601.19336v1 Announce Type: cross Abstract: While model-based reinforcement learning (MBRL) improves sample efficiency by learning world models from raw observations, existing methods struggle to generalize across structurally similar scenes and remain vulnerable to spurious variations such as textures or color shifts. From a cognitive science perspective, humans segment continuous sensory streams into discrete events and […]
In-Network Collective Operations: Game Changer or Challenge for AI Workloads?
arXiv:2601.19132v1 Announce Type: cross Abstract: This paper summarizes the opportunities of in-network collective operations (INC) for accelerated collective operations in AI workloads. We provide sufficient detail to make this important field accessible to non-experts in AI or networking, fostering a connection between these communities. Consider two types of INC: Edge-INC, where the system is implemented […]
A Hybrid Supervised-LLM Pipeline for Actionable Suggestion Mining in Unstructured Customer Reviews
arXiv:2601.19214v1 Announce Type: cross Abstract: Extracting actionable suggestions from customer reviews is essential for operational decision-making, yet these directives are often embedded within mixed-intent, unstructured text. Existing approaches either classify suggestion-bearing sentences or generate high-level summaries, but rarely isolate the precise improvement instructions businesses need. We evaluate a hybrid pipeline combining a high-recall RoBERTa classifier […]
XIMP: Cross Graph Inter-Message Passing for Molecular Property Prediction
arXiv:2601.19037v1 Announce Type: cross Abstract: Accurate molecular property prediction is central to drug discovery, yet graph neural networks often underperform in data-scarce regimes and fail to surpass traditional fingerprints. We introduce cross-graph inter-message passing (XIMP), which performs message passing both within and across multiple related graph representations. For small molecules, we combine the molecular graph […]
Out-of-Distribution Generalization for Neural Physics Solvers
arXiv:2601.19091v1 Announce Type: cross Abstract: Neural physics solvers are increasingly used in scientific discovery, given their potential for rapid in silico insights into physical, materials, or biological systems and their long-time evolution. However, poor generalization beyond their training support limits exploration of novel designs and long-time horizon predictions. We introduce NOVA, a route to generalizable […]
Intersectional Fairness via Mixed-Integer Optimization
arXiv:2601.19595v1 Announce Type: cross Abstract: The deployment of Artificial Intelligence in high-risk domains, such as finance and healthcare, necessitates models that are both fair and transparent. While regulatory frameworks, including the EU’s AI Act, mandate bias mitigation, they are deliberately vague about the definition of bias. In line with existing research, we argue that true […]