Knowledge catalogue
arXiv:2603.25821v3 Announce Type: replace-cross Abstract: We present Doctorina MedBench, an evaluation framework for agent-based medical AI based on the simulation of physician-patient interactions. U
arXiv:2608.13461v1 Announce Type: new Abstract: Post-click conversion rate (CVR) is a key metric in various scenarios including e-commerce and advertising, reflecting the efficiency and user experienc
arXiv:2608.12746v1 Announce Type: cross Abstract: Object hallucination in multimodal large language models arises when language priors and corpus co-occurrence bias outweigh the visual evidence, with
arXiv:2512.02694v3 Announce Type: replace-cross Abstract: We propose the first return time distribution (FRTD) of a random walk as an interpretable and mathematically grounded node embedding. The FRTD
arXiv:2608.12534v1 Announce Type: cross Abstract: Autonomous agent teams deployed in settings such as marine and extraterrestrial outposts must coordinate actions to achieve optimal outcomes across mu
arXiv:2608.12363v1 Announce Type: cross Abstract: European countries are debating policies to mitigate the increased energy costs caused by renewed geopolitical tensions, while pursuing decarbonizatio
arXiv:2608.12408v1 Announce Type: cross Abstract: Representational similarity analysis (RSA) is increasingly used to ask which learning rules give convolutional networks brain-like representations. Be
arXiv:2603.16285v2 Announce Type: replace Abstract: Character-centric story visualization aims to synthesize coherent image sequences that depict narrative events and interactions while preserving rec
arXiv:2506.18278v4 Announce Type: replace-cross Abstract: We introduce an original minimax framework for finite-time performance analysis in queueing control and propose a surprisingly simple Lyapunov
arXiv:2608.12845v1 Announce Type: cross Abstract: Semantic ID (SID)-based generative recommendation has recently achieved remarkable success. However, existing methods suffer from a previously overloo
arXiv:2608.12355v1 Announce Type: cross Abstract: Recent progress in AI coding agent research has led to rapid improvements in agents' ability to autonomously perform complex software engineering task
arXiv:2608.12715v1 Announce Type: cross Abstract: Generative speech enhancement faces three gaps: spectral models capture harmonic structure but often disrupt phase, waveform models preserve phase but
I follow the AI & math discourse a bit - without understanding the actual math. I thought I might offer some thoughts as a scientist in structural biology - a field transformed by various tech over th
arXiv:2608.12957v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) learns from reward differences within a rollout group, but receives no useful relative signal when every sam
arXiv:2608.13505v1 Announce Type: cross Abstract: Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific t
arXiv:2608.13262v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous c
arXiv:2608.13328v1 Announce Type: cross Abstract: Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguisti
arXiv:2602.17045v2 Announce Type: replace Abstract: A growing body of work attempts to evaluate the theory of mind (ToM) abilities of humans and large language models (LLMs) using static, non-interact
arXiv:2608.13040v1 Announce Type: cross Abstract: Enabling agents to learn from experience and internalize it into their policy has become a central problem in self-evolving AI. On-policy self-distill
arXiv:2608.12477v1 Announce Type: new Abstract: Clinical prediction models are often developed as if the outcome of interest were cleanly observed for every patient. This assumption fails when treatme
arXiv:2608.13450v1 Announce Type: cross Abstract: Autonomous vehicles depend on large safety-critical software stacks, where weaknesses reachable from adversarial inputs may affect steering, braking,
arXiv:2608.12321v1 Announce Type: cross Abstract: When a salient surface cue competes with an implicit feasibility constraint, LLMs often fail -- but aggregate accuracy conflates genuine constraint in
arXiv:2608.12825v1 Announce Type: new Abstract: Recent query-based feed-forward 3DGS methods represent a scene using learnable queries, each aggregating multi-view evidence and decoding a group of Gau
arXiv:2608.12356v1 Announce Type: cross Abstract: A college offering several overlapping computing degrees implicitly assumes that its programs are differentiated in line with how the labor market seg
arXiv:2608.12689v1 Announce Type: cross Abstract: Multi-parametric magnetic resonance imaging (mpMRI) is a cornerstone for brain tumor diagnosis and treatment, yet current AI models face critical limi
arXiv:2608.12436v1 Announce Type: new Abstract: Multi-AUV ad-hoc network-based target tracking requires networked autonomous underwater vehicles (AUVs) to cooperatively track maneuvering targets under
arXiv:2504.18455v2 Announce Type: replace-cross Abstract: We study distributed multiview representation learning, a problem in which K clients each observe a distinct but possibly statistically correl
arXiv:2608.13362v1 Announce Type: new Abstract: Dexterous manipulation promises substantially richer robot interaction with the physical world, but learning these behaviours remains constrained by the
neurosymbolic world models – *exactly* what I argued for in 2020 in the Next Decade in AI – for the win. Jeremy's excellent work here is a great illustration of a very powerful type of approach: LLM-g
arXiv:2608.12995v1 Announce Type: new Abstract: Heterogeneous USV cooperative pursuit in constrained port waterways requires evader interception under navigation, traffic, and role constraints. This p
arXiv:2608.13039v1 Announce Type: new Abstract: The paper introduces the ante-hoc Explainable AI methodology to assess the global feature importance of the Machine Learning models used for heat demand
arXiv:2510.15076v2 Announce Type: replace Abstract: The ell_p-norm objectives for correlation clustering present a fundamental trade-off between minimizing total disagreements (the ell_1-norm) and ens
arXiv:2608.12346v1 Announce Type: new Abstract: This position paper argues that modern AI alignment methods - originally designed to prevent harmful output - are dual-use technologies that may easily
arXiv:2608.12372v1 Announce Type: new Abstract: AI systems are increasingly employed as decision aids, decision delegates, or autonomous decision-makers. This position paper argues that in many settin
arXiv:2608.12892v1 Announce Type: new Abstract: Activation steering turns localized representations into control directions, but localization alone does not reveal whether a direction has a selective
arXiv:2608.13190v1 Announce Type: cross Abstract: Group-robust learning is crucial for maintaining accuracy on rare subpopulations when training-group labels are unavailable. However, existing methods
arXiv:2608.13428v1 Announce Type: new Abstract: Assessing the maturity of artificial intelligence technologies is essential for investment decisions, project management, and policy monitoring, yet the
arXiv:2608.12984v1 Announce Type: cross Abstract: Long-form research reports generated by large language models drift, contradict themselves, and lose provenance: the same metric appears with differen
arXiv:2608.12877v1 Announce Type: new Abstract: Multi-hop fact verification, which verifies claims by reasoning over multiple pieces of evidence, is critical for combating misinformation on social med
arXiv:2608.12360v1 Announce Type: cross Abstract: Background: AI/ML-enabled medical devices are increasingly deployed in healthcare under evolving regulatory frameworks. As these systems become more i
remember how i said OpenAI might turn out to be the WeWork of AI? OpenAI is falling apart right now. 9 of their most important leaders have left the company recently, and Altman is about to ask the pu
arXiv:2608.12912v1 Announce Type: new Abstract: This paper considers the overestimation bias problem of Q-learning in the setting of a large action space, for the purpose of relieving the bottleneck o
arXiv:2608.13087v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) solvers report the best of many sampled solutions per instance, and the sample count is, by convention, identi
arXiv:2608.12564v1 Announce Type: new Abstract: Automating empirical research is a long-standing direction of AI. Recent automatic research (AutoResearch) agents bring this goal within reach, as moder
arXiv:2608.12338v1 Announce Type: new Abstract: Text-to-SQL aims to convert natural language questions into executable SQL queries. While memory-based agent system improves complex SQL generation, exi
arXiv:2606.16454v2 Announce Type: replace-cross Abstract: Low-Rank Adaptation (LoRA) enables efficient adaptation of large pretrained models to downstream tasks by parameterizing weight updates with l
arXiv:2603.01891v2 Announce Type: replace Abstract: Action chunking improves exploration and accelerates value propagation in long-horizon reinforcement learning, but naively applying off-policy metho
arXiv:2608.13341v1 Announce Type: cross Abstract: Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Convent
// Skill Misevolution in Self-Improving LLM Agents // Self-improving agents write their successes down as reusable skills. An unsafe success becomes reusable policy long after the input that triggered
arXiv:2509.17449v2 Announce Type: replace Abstract: Queer vernacular is rarely studied in NLP, despite advancements in resources and evaluation for other sociolects and informal language. Because of t
arXiv:2608.12511v1 Announce Type: cross Abstract: Privacy documents (e.g., privacy policies) are a central mechanism through which digital services disclose data practices and seek user consent. Over
arXiv:2604.03181v2 Announce Type: replace-cross Abstract: Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing pol
arXiv:2608.13317v1 Announce Type: new Abstract: Large language model based multi-agent systems usually communicate in text, i.e., using discrete tokens. However, text introduces a discrete bottleneck.
arXiv:2608.12874v1 Announce Type: new Abstract: Plasticity loss has emerged as a critical challenge in continual learning that significantly hinders the acquisition of sequential tasks. While optimizi
arXiv:2608.13482v1 Announce Type: cross Abstract: As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today
arXiv:2608.13212v1 Announce Type: new Abstract: Networked systems, from power grids to traffic networks and cloud clusters, carry loads across nodes with limited capacity. A node whose load exceeds it
arXiv:2608.13179v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) offers a verifier-bounded performance ceiling for training multi-turn tool-use agents, yet its tra
arXiv:2608.13026v1 Announce Type: new Abstract: Outcome-driven reinforcement learning offers a scalable way to post-train vision-language-action (VLA) policies from sparse task-success feedback. In co
that should be fairly obvious even now Looking back with a few year's perspective, it seems pretty likely to me that @hlntnr was correct that ending OpenAI due to firing CEO Sam Altman 'would actually
arXiv:2606.18479v2 Announce Type: replace Abstract: Reject inference methods are widely used to mitigate survival bias in credit scoring, yet their effectiveness remains poorly understood. We systemat