3,690 items tracked: 31 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2605.13047v2 Announce Type: replace-cross Abstract: Evaluating whether large vision-language models (VLMs) align with human perception for high-level semantic scene comprehension remains a challenge.
arXiv:2605.15688v2 Announce Type: replace-cross Abstract: Concept Activation Vectors (CAV) and the Testing with CAVs (TCAV) method are fundamental tools for concept-based explainability in deep learning, yet their practi…
arXiv:2605.16026v2 Announce Type: replace-cross Abstract: Multilingual speech translation frontends built on speech large language models typically condition on language identity, as a learned embedding or a prompted lan…
arXiv:2605.17086v3 Announce Type: replace-cross Abstract: Automation can displace or complement labour, but this need not be constant across economies.
arXiv:2605.17316v2 Announce Type: replace-cross Abstract: Traffic sensor data exhibit strong temporal and cross-sensor dependencies, yet long gaps erase both a sensor's local history and the joint observations needed to…
arXiv:2605.20440v3 Announce Type: replace-cross Abstract: Symmetry determines which physical responses of molecules and crystals are allowed and underlies many models used throughout the physical sciences.
arXiv:2605.21405v2 Announce Type: replace-cross Abstract: Third-party Python libraries introduce dependency-management overhead, supply-chain risk, and deployment friction.
arXiv:2605.25836v2 Announce Type: replace-cross Abstract: Extracting MITRE ATT&CK techniques from cyber threat intelligence (CTI) reports is an open-set, multi-label problem requiring both high recall (not missing techni…
arXiv:2605.26184v2 Announce Type: replace-cross Abstract: Hybrid post-training combining supervised fine-tuning (SFT) and reinforcement learning (RL) is the standard paradigm for aligning large language models, yet fixed…
arXiv:2605.26937v3 Announce Type: replace-cross Abstract: Parametric knowledge in large language models (LLMs) is a cornerstone of their success, yet remains poorly understood.
arXiv:2605.27016v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can hallucinate, but do model uncertainty estimators reliably reveal when they do?
arXiv:2605.28918v2 Announce Type: replace-cross Abstract: For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging than one-…
arXiv:2605.29107v3 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly rank products, documents, and recommendations for user queries, which makes manipulating these rankings a growing concer…
arXiv:2605.30462v2 Announce Type: replace-cross Abstract: Can a dataset be recognized from the spurious correlations it induces during training?
arXiv:2606.00299v2 Announce Type: replace-cross Abstract: Video Diffusion Models (VDMs) synthesize high-quality videos, but precise camera and motion control remains challenging when large viewpoint shifts, changing occl…
arXiv:2606.00702v2 Announce Type: replace-cross Abstract: We propose to turn generalist multi-embodiment value functions into reusable models for robot design.
arXiv:2606.00920v2 Announce Type: replace-cross Abstract: A benchmark score is a measurement whose uncertainty has two sources: an aleatoric component from stochastic decoding and an epistemic component from the finite p…
arXiv:2606.01442v3 Announce Type: replace-cross Abstract: Spiking neural networks (SNNs) are increasingly studied for network intrusion detection, but comparative evidence on how neuron models and spike encodings affect…
arXiv:2606.02465v2 Announce Type: replace-cross Abstract: Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, but still exhibit substantial multilingual reasoning gaps, largely due to…
arXiv:2606.03163v5 Announce Type: replace-cross Abstract: This yellow paper describes the technical architecture of OpenAgenet / OAN.
arXiv:2606.04074v2 Announce Type: replace-cross Abstract: Adaptive patching has been proposed for time-series forecasting: allocate finer patches where the sequence looks locally informative.
arXiv:2606.04269v2 Announce Type: replace-cross Abstract: Deformable object manipulation (DOM) is challenging due to high-dimensional, partially observable states that evolve through long-horizon, topology-changing inter…
arXiv:2606.04806v2 Announce Type: replace-cross Abstract: LLMs and agentic systems are increasingly deployed in social environments, making normative competence critical for safe and appropriate behavior.
arXiv:2606.04970v2 Announce Type: replace-cross Abstract: Proactive multimodal assistants must decide when guidance is needed and what to say, while tracking progress through extended procedures and helping users recover…
arXiv:2606.05174v2 Announce Type: replace-cross Abstract: Large language models can support medical question answering, but privacy, cost, and reliability still limit their clinical use in focused domains.
arXiv:2606.06218v3 Announce Type: replace-cross Abstract: A policy tuned for one robot often behaves differently on another, whether due to the sim-to-real gap, unknown payloads, or the differing dynamics of two instance…
arXiv:2606.06694v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are rapidly assuming an intermediary role in housing search through the integration of listing platforms within conversational interf…
arXiv:2606.07943v3 Announce Type: replace-cross Abstract: Large language model agents use skills that package reusable instructions, code, and resources.
arXiv:2606.08653v4 Announce Type: replace-cross Abstract: Action-supervised fine-tuning of vision-language-action (VLA) policies can compress visual structure that is weakly constrained by the action objective.
arXiv:2606.10173v2 Announce Type: replace-cross Abstract: On-device inference reduces exposure to remote infrastructure, but it does not establish privacy for an operating-system assistant that aggregates cross-applicati…
arXiv:2606.15610v2 Announce Type: replace-cross Abstract: Passing an exact-clone null gate does not entail passing a matched target-selection utility gate.
arXiv:2606.15734v2 Announce Type: replace-cross Abstract: Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate weight drift, poten…
arXiv:2606.18831v2 Announce Type: replace-cross Abstract: Long-context reasoning is an essential capability for large language models, particularly when they are deployed as autonomous agents that must reason over length…
arXiv:2606.19370v2 Announce Type: replace-cross Abstract: Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data.
arXiv:2606.22352v2 Announce Type: replace-cross Abstract: Dictionary learning has long been studied from both optimization and probabilistic perspectives.
arXiv:2606.26277v2 Announce Type: replace-cross Abstract: Sequential user behavior modeling is widely adopted in industrial recommender systems; however, significant gaps remain in financial services, where pre-login web…
arXiv:2606.27354v2 Announce Type: replace-cross Abstract: Neural surrogate models offer fast approximate mappings from PDE parameters to solutions, but they typically treat solving as a purely statistical task: once trai…
arXiv:2606.27786v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) enhances the faithfulness of large language models (LLMs) by incorporating external knowledge into the generation process.
arXiv:2606.28438v2 Announce Type: replace-cross Abstract: Recursive self-training can degrade neural generative models when generated data is reused without fresh human data or external quality control.
arXiv:2606.28529v3 Announce Type: replace-cross Abstract: Embodied foundation models have recently been widely used to improve robot generalization and task success rates.
arXiv:2606.29898v2 Announce Type: replace-cross Abstract: Real-world evaluation is the gold standard for robot manipulation policies because it tests them against the physical conditions and deployment challenges they ar…
arXiv:2606.30161v2 Announce Type: replace-cross Abstract: Federated Learning (FL) enables multiple clients to collaboratively train machine learning models without sharing their local data.
arXiv:2606.32032v2 Announce Type: replace-cross Abstract: Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes.
arXiv:2607.00065v2 Announce Type: replace-cross Abstract: Any-angle path planning extends traditional graph-based path planning by allowing movement between any pair of vertices, rather than being restricted by predefine…
arXiv:2607.01455v4 Announce Type: replace-cross Abstract: Language models learn continuous programs over discrete symbols, with the embedding table and LM-head acting as the read/write interface between them.
arXiv:2607.03926v2 Announce Type: replace-cross Abstract: Synthetic tabular data support use cases like data sharing, model development under access restrictions, and rapid prototyping of analytical workflows.
arXiv:2607.04383v5 Announce Type: replace-cross Abstract: Large Audio-Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection (SED)…
arXiv:2607.06546v2 Announce Type: replace-cross Abstract: Denoising graphs is a fundamental problem in graph learning and the core operation of graph diffusion models.
arXiv:2607.09020v2 Announce Type: replace-cross Abstract: Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately.
arXiv:2607.09316v2 Announce Type: replace-cross Abstract: Thematic indexing -- the practice of assigning structured conceptual labels to sections of text -- is essential to scholarly access in large-scale literary and hi…