Knowledge catalogue
arXiv:2506.14387v3 Announce Type: replace Abstract: Adapting LLMs with new knowledge is increasingly important, but standard fine-tuning often erodes aligned epistemic abstention: the ability to ackno
arXiv:2604.19064v1 Announce Type: new Abstract: In vision-and-language navigation (VLN), self-improvement from policy-induced experience, using only standard VLN action supervision, critically depends
arXiv:2604.03261v2 Announce Type: replace Abstract: The rise of generative AI is posing increasing risks to online information integrity and civic discourse. Most concretely, such risks can materialis
arXiv:2411.18275v2 Announce Type: replace Abstract: Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities. However, these models remain
arXiv:2601.18891v3 Announce Type: replace Abstract: Caribou across the Arctic has declined in recent decades, motivating scalable and accurate monitoring approaches to guide evidence-based conservatio
arXiv:2604.17679v1 Announce Type: new Abstract: Autonomous navigation requires planning to reach a goal safely and efficiently in complex and potentially dynamic environments. Graph search-based algor
I agree with Connor that most folks concerned about AI have been far too coy about extinction risk, and that ControlAI is one of few exceptions. The world needs more earnest communication efforts. We
arXiv:2604.17815v1 Announce Type: cross Abstract: When language models answer open-ended problems, they implicitly make hidden decisions that shape their outputs, leaving users with uncontextualized a
arXiv:2601.18731v2 Announce Type: replace Abstract: Alignment of Large Language Models (LLMs) aims to align outputs with human preferences, and personalized alignment further adapts models to individu
arXiv:2604.17132v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) often generate refusal responses to harmless queries due to the over-refusal problem. However, existing meth
arXiv:2511.23170v5 Announce Type: replace Abstract: Contrastive vision-language pre-training frameworks such as CLIP have demonstrated impressive zero-shot performance across a range of vision-languag
arXiv:2601.15220v2 Announce Type: replace Abstract: We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle
arXiv:2512.12069v3 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks, necessitating defenses that are both g
arXiv:2412.08812v2 Announce Type: replace Abstract: Reward models trained on aggregate preferences often fail to capture individual users' values, but existing adaptation methods such as fine-tuning o
arXiv:2512.04847v2 Announce Type: replace-cross Abstract: Pre-trained audio models excel at detecting acoustic patterns in auscultation sounds but often fail to grasp their clinical significance, limi
arXiv:2602.13088v2 Announce Type: replace-cross Abstract: The distinction between genuine grassroots activism and automated influence operations is collapsing. While contemporary policy debates priori
The AI industry insists they can manage the risks of superintelligence, but there are in fact zero widely agreed on or accepted solutions to the problem of how one could even control something vastly
arXiv:2510.09689v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have been augmented with web search to overcome the limitations of the static knowledge boundary by accessing up-
arXiv:2604.15124v1 Announce Type: new Abstract: Continuous glucose monitoring (CGM) is central to diabetes care, but explaining CGM patterns clearly and empathetically remains time-intensive. Evidence
arXiv:2604.13203v1 Announce Type: cross Abstract: Mild Cognitive Impairment (MCI) affects 15-20% of adults aged 65 and older, often making kitchen navigation and independent living difficult, particul
arXiv:2604.14986v1 Announce Type: new Abstract: Safe and efficient assistive planning for visually impaired scenarios remains challenging, since existing methods struggle with multi-objective optimiza
arXiv:2509.21823v2 Announce Type: replace Abstract: Reward is critical to the evaluation and training of large language models (LLMs). However, existing rule-based or model-based reward methods strugg
arXiv:2603.27833v2 Announce Type: cross Abstract: In this work, we first prove that the separation principle holds for communication-constrained LQR problems under i.i.d. zero-mean disturbances with a
arXiv:2604.14629v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have shown remarkable capabilities in joint vision-language understanding, but their large scale poses significant challen
arXiv:2604.14237v1 Announce Type: new Abstract: Transistor topology optimization is a critical step in standard cell design, directly dictating diffusion sharing efficiency and downstream routability.
arXiv:2604.13488v1 Announce Type: new Abstract: Autonomous Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) enable digital automation on end-user devices. Whil
arXiv:2604.14548v1 Announce Type: cross Abstract: As speech language models (SLMs) transition from personal devices into shared, multi-user environments, their responses must account for far more than
Siladitya Ray / Forbes: What some leaders think of using universal income to mitigate AI-fueled layoffs: Musk calls it the “best way”, OpenAI's policy doc mentions a Public Wealth Fund — Topline — Elo
arXiv:2604.13459v1 Announce Type: new Abstract: Turbofan engine degradation under sustained operational stress necessitates robust prognostic systems capable of accurately estimating the Remaining Use
arXiv:2604.13561v1 Announce Type: new Abstract: Vision-language models trained with contrastive learning on paired medical images and reports show strong zero-shot diagnostic capabilities, yet the eff
arXiv:2604.13883v1 Announce Type: new Abstract: Modern machine learning models typically represent inputs as fixed points in a high-dimensional embedding space. While this approach has been proven pow
In 2023, the FDA removed 19 peptides from the list of drugs that compounding pharmacies could produce, and in 2026 the FDA announced it will review whether to add back 7 of these peptides following pr
arXiv:2511.14755v2 Announce Type: replace-cross Abstract: As perception-based controllers for autonomous systems become increasingly popular in the real world, it is important that we can formally ver
arXiv:2604.13660v1 Announce Type: new Abstract: In Deepfake Detection (DFD) tasks, researchers proposed two types of MLLM-based methods: complementary combination with small DFD detectors, or static f
arXiv:2604.12628v1 Announce Type: cross Abstract: Path-planning for autonomous vehicles in threat-laden environments is a fundamental challenge. While traditional optimal control methods can find idea
arXiv:2604.12255v1 Announce Type: cross Abstract: Dynamic facial expression recognition in the wild remains challenging due to data scarcity and long-tail distributions, which hinder models from effec
arXiv:2601.10398v3 Announce Type: replace Abstract: In LLM-based text-to-SQL systems, unanswerable and underspecified user queries may generate not only incorrect text but also executable programs tha
arXiv:2604.12693v1 Announce Type: new Abstract: Deep learning models often achieve expert-level accuracy in medical image classification but suffer from a critical flaw: semantic incoherence. These hi
arXiv:2604.12086v1 Announce Type: new Abstract: Designing robust reinforcement learning (RL) agents in the presence of imperfect reward signals remains a core challenge. In practice, agents are often
arXiv:2604.12232v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed across diverse domains, yet their vulnerability to jailbreak attacks, where adversarial inputs
arXiv:2604.12817v1 Announce Type: new Abstract: Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To im
arXiv:2604.11490v1 Announce Type: new Abstract: While the field of vision-language (VL) has achieved remarkable success in integrating visual and textual information across multiple languages and doma
arXiv:2604.11287v1 Announce Type: new Abstract: Background: Large language models (LLMs) have been explored as tools for generating personalized exercise prescriptions, yet the consistency of outputs
arXiv:2604.11775v1 Announce Type: cross Abstract: Perturbation-based explainability methods such as KernelSHAP provide model-agnostic attributions but are typically impractical for patch-based 3D medi
arXiv:2604.11733v1 Announce Type: cross Abstract: We study routing games in which travelers optimize over routes that are remembered or surfaced, rather than over a fixed exogenous action set. The pap
arXiv:2604.10437v1 Announce Type: new Abstract: Vision--language models (VLMs) for radiology report generation (RRG) can produce long-form chest CT reports from volumetric scans and show strong potent
arXiv:2604.10991v1 Announce Type: cross Abstract: The growing use of generative artificial intelligence (AI) in academic writing has raised increasing concerns regarding transparency and academic inte
arXiv:2604.10023v1 Announce Type: cross Abstract: With the growing availability of open-sourced adapters trained on the same diffusion backbone for diverse scenes and objects, combining these pretrain
arXiv:2604.05165v2 Announce Type: replace Abstract: Reconfigurable Intelligent Surfaces (RIS) has a potential to engineer smart radio environments for next-generation millimeter-wave (mmWave) networks
arXiv:2604.09998v1 Announce Type: cross Abstract: Large language models (LLMs) have recently emerged as promising tools for augmenting Security Operations Center (SOC) workflows, with vendors increasi
arXiv:2604.09757v1 Announce Type: cross Abstract: Medical vision--language models (VLMs) have shown strong potential for medical visual question answering (VQA), yet their reasoning remains largely te
arXiv:2604.10147v1 Announce Type: cross Abstract: Capturing user intent across heterogeneous behavioral domains stands as a fundamental challenge in session-based recommender systems. Yet, existing mu
arXiv:2509.13047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across many domains, yet their application to specialized fields remain
arXiv:2604.11477v1 Announce Type: new Abstract: The alignment of Multi-Agent Systems (MAS) for autonomous software engineering is constrained by evaluator epistemic uncertainty. Current paradigms, suc
arXiv:2604.10475v1 Announce Type: new Abstract: Modeling household-level trip generation is fundamental to accurate demand forecasting, traffic flow estimation, and urban system planning. Existing stu
arXiv:2604.10664v1 Announce Type: new Abstract: Multi-objective optimization (MOO) has been widely studied in literature because of its versatility in human-centered decision making in real-life appli
arXiv:2604.11548v1 Announce Type: new Abstract: The rise of OpenClaw in early 2026 marks the moment when millions of users began deploying personal AI agents into their daily lives, delegating tasks r
arXiv:2604.10404v1 Announce Type: cross Abstract: Edge-based multimodal medical monitoring requires models that balance diagnostic accuracy with severe energy constraints. Continuous acquisition of EC
arXiv:2604.09839v1 Announce Type: new Abstract: Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in output behavior. It has als
arXiv:2604.11195v1 Announce Type: cross Abstract: Existing object detectors often struggle to generalize across domains while adapting to emerging novel categories. Adaptive open-set object detection