arXiv:2603.12290v1 Announce Type: new Abstract: Scholarly web is a vast network of knowledge connected by citations. However, this system is increasingly compromised by miscitation, where references do not support or even contradict the claims they are cited for. Current miscitation detection methods, which primarily rely on semantic similarity or network anomalies, struggle to capture the nuanced relationship between a citation’s context and its place in the wider network. While large language models (LLMs) offer powerful capabilities in semantic […]

Ver mais

Over the past few months it’s become clear that coding agents are extraordinarily good at building a weird version of a “clean room” implementation of code. The most famous version of this pattern is when Compaq created a clean-room clone of the IBM BIOS back in 1982. They had one team of engineers reverse engineer the BIOS to create a specification, then handed that specification to another team to build a new ground-up version. This process used to […]

Ver mais

You’re not bad at planning. Your calendar is packed with appointments, meal schedules, and activities that look perfectly organized. But somehow, those carefully laid plans vanish between your phone screen and real life. The truth is, most households struggle with execution, not planning. Everyone knows what needs to happen. Yet nobody takes action because the information lives in scattered places. A calendar app here, a sticky note there, and verbal reminders everywhere create chaos. This isn’t about downloading […]

Ver mais

arXiv:2602.20351v1 Announce Type: new Abstract: Full-Reference image quality assessment (FR IQA) is important for image compression, restoration and generative modeling, yet current neural metrics remain slow and vulnerable to adversarial perturbations. We present BiRQA, a compact FR IQA metric model that processes four fast complementary features within a bidirectional multiscale pyramid. A bottom-up attention module injects fine-scale cues into coarse levels through an uncertainty-aware gate, while a top-down cross-gating block routes semantic context back to high resolution. To […]

Ver mais

arXiv:2601.16999v1 Announce Type: cross Abstract: Named Entity Recognition (NER) serves as a foundational component in many natural language processing (NLP) pipelines. However, current NER models typically output a single predicted label sequence without any accompanying measure of uncertainty, leaving downstream applications vulnerable to cascading errors. In this paper, we introduce a general framework for adapting sequence-labeling-based NER models to produce uncertainty-aware prediction sets. These prediction sets are collections of full-sentence labelings that are guaranteed to contain the correct […]

Ver mais

Model-based offline reinforcement learning (RL) aims to enhance offline RL with a dynamics model that facilitates policy exploration. However, textit{model exploitation} could occur due to inevitable model errors, degrading algorithm performance. Adversarial model learning offers a theoretical framework to mitigate model exploitation by solving a maximin formulation. Within such a paradigm, RAMBO~citep{rigter2022rambo} has emerged as a representative and most popular method that provides a practical implementation with model gradient. However, we empirically reveal that severe Q-value underestimation and […]

Ver mais

arXiv:2601.10824v1 Announce Type: new Abstract: Social robots hold promise for reducing job interview anxiety, yet designing agents that provide both psychological safety and instructional guidance remains challenging. Through a three-phase iterative design study (N = 8), we empirically mapped this tension. Phase I revealed a “Safety-Guidance Gap”: while a Person-Centered Therapy (PCT) robot established safety (d = 3.27), users felt insufficiently coached. Phase II identified a “Scaffolding Paradox”: rigid feedback caused cognitive overload, while delayed feedback lacked specificity. […]

Ver mais

arXiv:2601.20020v1 Announce Type: cross Abstract: We consider the problem of graph matching for a sequence of graphs generated under a time-dependent Markov chain noise model. Our edgelighter error model, a variant of the classical lamplighter random walk, iteratively corrupts the graph $G_0$ with edge-dependent noise, creating a sequence of noisy graph copies $(G_t)$. Much of the graph matching literature is focused on anonymization thresholds in edge-independent noise settings, and we establish novel anonymization thresholds in this edge-dependent noise […]

Ver mais

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced LLM reasoning, but remains constrained by inefficient exploration under limited rollout budgets, leading to low sampling success and unstable training in complex tasks. We find that many exploration failures arise not from problem difficulty, but from a small number of prompt tokens that introduce interference. Building on this insight, we propose the Less Noise Sampling Framework (LENS), which first prompts by identifying and removing interference tokens. then transfers successful rollouts […]

Ver mais