Knowledge catalogue
arXiv:2605.02740v1 Announce Type: cross Abstract: Evidence derived from large-scale real-world data (RWD) is increasingly informing regulatory evaluation and healthcare decision-making. Administrative
arXiv:2605.01995v1 Announce Type: new Abstract: The perception of an Autonomous Driving System (ADS) critically depends on relevant, comprehensive, and diverse datasets to ensure its safety while oper
arXiv:2511.03828v2 Announce Type: replace Abstract: Offline-to-online reinforcement learning (O2O RL) faces a central challenge between retaining offline conservatism and adapting to online feedback u
arXiv:2410.16636v2 Announce Type: replace-cross Abstract: We study the problem of conditional two-sample testing, which aims to determine whether two populations have the same distribution after accou
arXiv:2605.02435v1 Announce Type: new Abstract: The Distributional Alignment Game framework provides a powerful variational perspective on Answer-Level Fine-Tuning (ALFT). However, standard algorithms
arXiv:2605.02108v1 Announce Type: new Abstract: Deep residual architectures are modeled as products of near-identity Jacobians. This paper proves deterministic quotient-geometric estimates for singula
arXiv:2605.02111v1 Announce Type: new Abstract: This paper develops the angular and static-channel component of Geometric and Spectral Alignment for residual Jacobian chains. Starting from Cartan-coor
arXiv:2605.02086v1 Announce Type: new Abstract: 3D Gaussian splatting (3DGS) is a state-of-the-art representation for real-time photorealistic novel-view synthesis, yet a single high-fidelity scene ty
arXiv:2605.01529v1 Announce Type: new Abstract: Imitation learning offers a promising framework for enabling robots to acquire diverse skills from human users. However, most imitation learning algorit
arXiv:2605.02626v1 Announce Type: new Abstract: Preference optimization has become a central paradigm for aligning large language models with human feedback. Direct Preference Optimization (DPO) simpl
arXiv:2507.21153v2 Announce Type: replace Abstract: The exponential growth of digital services has positioned data centers among the most energy-intensive infrastructures in the modern economy, raisin
arXiv:2603.12243v3 Announce Type: replace Abstract: Mastering dexterous manipulation with multi-fingered hands has been a grand challenge in robotics for decades. Despite its potential, the difficulty
arXiv:2603.03584v2 Announce Type: replace Abstract: Maintaining situational awareness in complex driving scenarios is challenging. It requires continuously prioritizing attention among extensive scene
arXiv:2508.12778v2 Announce Type: replace Abstract: Medical large vision-language Models (Med-LVLMs) have shown promise in clinical applications but suffer from factual inaccuracies and unreliable out
arXiv:2511.22581v3 Announce Type: replace Abstract: We prove that in any Dec-POMDP, sufficiently high entropy regularization ensures that the policy gradient flow with tabular softmax parametrization
arXiv:2605.02007v1 Announce Type: cross Abstract: In recent years, several advances have been observed in Deep Learning with surprising results. Models in this area have been increasingly used in nume
arXiv:2605.02784v1 Announce Type: new Abstract: Accurately recovering human pose and appearance from video is an essential component of scene reconstruction, with applications to motion capture, motio
arXiv:2605.01574v1 Announce Type: new Abstract: Vehicle Routing Problem (VRP) is one of the most complex NP-hard combinatorial optimization problem in transportation and logistics that requires a dyna
arXiv:2605.01581v1 Announce Type: new Abstract: Diffusion-based visuomotor policies perform well in robotic manipulation, yet current methods still inherit image-generation-style decoders and multi-st
arXiv:2605.02580v1 Announce Type: new Abstract: Recognizing unknown objects is crucial for safety-critical applications such as autonomous driving and robotics. Open-Set Panoptic Segmentation (OPS) ai
Gary Marcus reflects on changing public perception of Sam Altman, noting that skepticism toward Altman's claims was once dismissed as hatred but has become more mainstream. The post suggests a shift i
I predict this will be the most embarrassing cover in the history of this magazine. This is like putting Enron executives on your cover, or doing a gauzy special report on Bernie Madoff. Sam Altman is
arXiv:2510.25426v2 Announce Type: replace Abstract: The rapid advancement of Large Language Models (LLMs) is positioning language at the core of human-computer interaction (HCI). We argue that advanci
Important new development. AI company employees have an enormous amount of power — far more than they realize. Absent legislation, AI co worker power is one of the key levers to shaping what the indus
arXiv:2605.02544v1 Announce Type: cross Abstract: The widespread adoption of machine learning in critical applications demands techniques to mitigate high-consequence errors. Our method utilizes a dua
In vividly explaining how he deceived Musk about his commitment to the nonprofit, without a trace of remorse, OpenAI’s Brockman has done Musk’s counsel quite a service. Brockman’s also been pretty gre
arXiv:2605.01402v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) struggle with numerical regression under long-tailed target distributions. Token-level supervised fine-tuning (
arXiv:2601.06035v2 Announce Type: replace-cross Abstract: The release of SAM 3D Body is a recent development in human mesh recovery, demonstrating improved performance in producing clean, topologicall
arXiv:2412.15251v3 Announce Type: replace Abstract: Multimodal large language models (MLLMs) are effective at capturing the semantics of short video content; however, they often fail to attend to the
Katie Miller began following Gary Marcus on X (formerly Twitter). Gary Marcus is a cognitive scientist and AI researcher known for his public commentary on artificial intelligence and technology polic
arXiv:2602.12873v4 Announce Type: replace-cross Abstract: Generative social robots (GSRs) powered by large language models enable adaptive, conversational tutoring but also introduce risks such as mis
arXiv:2605.01731v1 Announce Type: new Abstract: Platooning of connected and automated vehicles provides significant benefits in terms of energy efficiency, traffic throughput, and, most critically, sa
arXiv:2510.03599v2 Announce Type: replace Abstract: We present a unified framework for multi-task locomotion and manipulation policy learning grounded in a contact-explicit representation. Instead of
arXiv:2605.01735v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed in real-world systems, they must support post-hoc removal of specific content to meet privacy
arXiv:2509.21173v5 Announce Type: replace Abstract: Vision-Language Models (VLMs) such as CLIP have revolutionized zero-shot classification and safety-critical tasks, including Out-of-Distribution (OO
arXiv:2605.00925v1 Announce Type: cross Abstract: Integrating molecular, morphological, and clinical data is essential for basic and translational biomedical research, yet systematic frameworks for jo
arXiv:2605.01957v1 Announce Type: cross Abstract: Low-dimensional projections of text embeddings support visual analysis of document collections, but their spatial organization may not reflect the rel
arXiv:2511.19175v2 Announce Type: replace-cross Abstract: A critical barrier to the trustworthiness of sixth-generation (6G) agentic autonomous networks is the uncertainty neglect bias; a cognitive te
arXiv:2601.19487v2 Announce Type: replace Abstract: Safety-aligned LLMs suffer from two failure modes: jailbreak (answering harmful inputs) and over-refusal (declining benign queries). Existing vector
arXiv:2506.24056v2 Announce Type: replace-cross Abstract: RLHF-style alignment trains language models to refuse unsafe requests, but how much operational margin does this refusal rest on? We introduce
arXiv:2410.18717v2 Announce Type: replace Abstract: Recent advancements in artificial intelligence hold ample potential for monitoring applications using surveillance cameras. However, concerns about
arXiv:2512.21985v2 Announce Type: replace Abstract: In high-stakes domains, small task-specific vision models are crucial due to their low computational requirements and the availability of numerous m
arXiv:2605.01306v1 Announce Type: cross Abstract: Laser absorption spectroscopy (LAS) is a well-established technique for non-intrusive measurement of gas species in combustion and atmospheric environ
arXiv:2605.01347v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own trajectories under token-level teacher supervision, but existing methods are capped by a single
Major new class action lawsuit accuses Meta of copyright infringement around AI training. It says they trained on pirated books, and that AI books flooding the market demonstrates market harm. These l
arXiv:2605.02183v1 Announce Type: new Abstract: Adversarial training is effective on balanced datasets, but its robustness degrades under longtailed class distributions, where tail classes suffer high
arXiv:2605.01335v1 Announce Type: cross Abstract: We characterize the fundamental limits of high-dimensional mean testing under arbitrary truncation, where samples are drawn from the conditional distr
Foo Yun Chee / Reuters: Meta says it will expand Instagram teen account safeguards to 27 EU countries, and plans to roll them out on Facebook in the US, ahead of the UK and EU in June — Meta Platforms
arXiv:2605.01167v1 Announce Type: new Abstract: Activation steering is a method for controlling Large Language Model (LLM) behavior by intervening in its internal representations to increase the align
arXiv:2605.02014v1 Announce Type: cross Abstract: We introduce Mira, a sample-based score for assessing the accuracy of a candidate conditional distribution using only joint samples from the true data
arXiv:2605.02751v1 Announce Type: cross Abstract: Language models (LMs) are increasingly used in high-stakes, multi-agent settings, where following instructions and maintaining value alignment are cri
arXiv:2605.01743v1 Announce Type: new Abstract: With the burgeoning development of fields such as the Metaverse, Virtual Reality (VR), and Digital Twins, text-to-3D generation has emerged as a researc
arXiv:2605.01356v1 Announce Type: new Abstract: Learning constraint-satisfying policies from offline data without risky online interaction is crucial for safety-critical decision making. Conventional
arXiv:2605.02292v1 Announce Type: new Abstract: Chest X-ray classification suffers from severe class imbalance where gradient updates bias toward majority classes, causing feature drift and poor perfo
arXiv:2605.01374v1 Announce Type: new Abstract: Knowledge distillation is a key technique for compressing large language models (LLMs), but most existing methods align representations at fixed layers
arXiv:2605.01736v1 Announce Type: new Abstract: Understanding the geometric and semantic structure of environments is essential for embodied navigation and reasoning. Existing semantic mapping methods
arXiv:2605.01961v1 Announce Type: new Abstract: Learning from human preference data is becoming a useful tool, from fine-tuning large language models to training reinforcement learning agents. However
arXiv:2605.00872v1 Announce Type: cross Abstract: Hypertensive disorders of pregnancy remain a leading cause of maternal and fetal morbidity worldwide, yet diagnosis relies on intermittent cuff-based
arXiv:2605.01163v1 Announce Type: cross Abstract: Shared embedding spaces are widely used for multimodal search and data curation. In practice, two problems often limit how well this works. First, emb
arXiv:2508.02046v4 Announce Type: replace-cross Abstract: Recent advances in Graphical User Interface (GUI) and embodied navigation have driven progress, yet these domains have largely evolved in isol