Knowledge catalogue
Politico: Sources: the WH is mulling EOs to address security risks from advanced AI, including barring companies from “interfering” with the government's use of models — A White House spokesperson sai
arXiv:2605.02258v1 Announce Type: new Abstract: Vision Foundation Models (VFMs) pretrained on large-scale RGB data have demonstrated remarkable representation quality, yet their applicability to multi
arXiv:2605.01205v1 Announce Type: new Abstract: Cross-Tokenizer Knowledge Distillation (CTKD) enables knowledge transfer between a large language model and a smaller student, even when they employ dif
arXiv:2605.00974v1 Announce Type: cross Abstract: LLMs are increasingly equipped with safety alignment mechanisms, yet recent studies demonstrate that they remain vulnerable to jailbreaking attacks th
arXiv:2605.02586v1 Announce Type: new Abstract: Existing cross-subject fMRI decoding methods typically train a model on multiple scanned subjects and then adapt it to a new subject using substantial p
arXiv:2605.02122v1 Announce Type: new Abstract: Human evaluation remains the primary standard for assessing modern AI systems, yet annotator disagreement, bias, and variability make system rankings fr
arXiv:2605.01510v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success in high-quality image synthesis, sparking interest in image-guided generation tasks such as subject-dr
arXiv:2507.19673v3 Announce Type: replace Abstract: Accurate pain assessment in patients with limited ability to communicate, such as older adults with severe dementia, represents a critical healthcar
arXiv:2506.01097v2 Announce Type: replace Abstract: Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficien
Thank you @UN Secretary General @antonioguterres for an excellent discussion on the current state of AI capabilities, and the urgent need for robust global governance. International collaboration is c
arXiv:2605.01611v1 Announce Type: cross Abstract: Due to ambiguity in the wording of the EU AI Act, we examine the question of to what extent frontier biological foundation models such as ESM3 are sub
arXiv:2603.05228v3 Announce Type: replace Abstract: Mechanistic interpretability typically relies on post-hoc analysis of trained networks. We instead adopt an interventional approach: testing hypothe
arXiv:2601.19597v3 Announce Type: replace Abstract: While InfoNCE underlies modern contrastive learning, its geometric mechanisms remain under-characterized beyond the canonical alignment--uniformity
arXiv:2605.02427v1 Announce Type: cross Abstract: A recurring pattern in 'reasoning without training' is that base LLMs already assign non-trivial probability mass to correct multi-step solutions; the
arXiv:2605.01311v1 Announce Type: new Abstract: Offline evaluation of language models from usage logs is biased when model choice is confounded: the same user-side factors that influence which model i
arXiv:2411.04696v5 Announce Type: replace Abstract: Learning correlations from data forms the foundation of today's machine learning (ML) and artificial intelligence research. While contemporary metho
Today, the CEO of @coinbase announced a 14% headcount reduction. Let's talk about why. He cites AI as a core reason for the shift, alongside market dynamics - though we don't know whether each of thos
Too early to tell how the trial ends, but if Elon does win, the takeaway might be in part that Greg Brockman made two immense blunders: 1. Writing down all that stuff in his diary 2. Blowing off Elon’
arXiv:2605.01110v1 Announce Type: new Abstract: Graph neural tangent kernels give a principled infinite-width theory for graph neural networks, but inherit a basic limitation of graph models: they see
arXiv:2605.00972v1 Announce Type: cross Abstract: Earth system science is producing increasingly large, high-dimensional datasets from physics based Earth system models to AI-based weather and climate
arXiv:2605.01663v1 Announce Type: new Abstract: We propose Flow-Anchored Noise-conditioned Q-Learning (FAN), a highly efficient and high-performing offline reinforcement learning (RL) algorithm. Recen
arXiv:2605.00721v1 Announce Type: cross Abstract: The Room Acoustics and Speaker Distance Estimation (SDE) Challenge at ICASSP 2025 explores the effectiveness of augmented room impulse response (RIR)
arXiv:2605.01928v1 Announce Type: new Abstract: Neural networks increasingly embed non-differentiable components (spiking neurons, quantized layers, discrete routing, blackbox simulators, etc.) where
arXiv:2605.01950v1 Announce Type: new Abstract: World models enable long-horizon planning by internally generating and evaluating imagined trajectories, making them a promising foundation for generali
arXiv:2605.00224v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human preferences is commonly done via reinforcement learning from human feedback (RLHF) with Proximal Policy
arXiv:2605.02126v1 Announce Type: new Abstract: Ultrasound foundation models have achieved strong performance on structured prediction tasks but remain exclusively vision-based, limiting zero-shot and
arXiv:2208.01899v2 Announce Type: replace Abstract: Imitation learning learns a policy from expert trajectories. While the expert data is believed to be crucial for imitation quality, it was found tha
arXiv:2605.02762v1 Announce Type: new Abstract: Online mapping and end-to-end (E2E) planning in autonomous driving remain largely sensor-centric, leaving rich map priors, including HD/SD vector maps,
arXiv:2605.02884v1 Announce Type: new Abstract: Ensuring the coherence of regional socio-economic statistics is a central task for national statistical institutes. Traditional validation tools, such a
New York Times: US labor experts and economists warn US unemployment benefits are unlikely to protect against AI job losses, and the GOP-led Congress is doing little to prepare — Economists aren't sur
arXiv:2601.23286v2 Announce Type: replace Abstract: While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, o
arXiv:2605.01518v1 Announce Type: new Abstract: The ability to push large objects in a goal-directed manner using onboard egocentric perception is an essential skill for humanoid robots to perform com
Gary Marcus critiques the gap between AI aspirations and current reality, suggesting that instead of achieving transformative 'singularity' breakthroughs, AI development has become cyclical—repeating
arXiv:2605.02323v1 Announce Type: new Abstract: Compositional inference - the decomposition of observations into an unknown number of latent components - is central to perception and scientific data a
While AI leaders warn superintelligent AI could cause human extinction, governments are asleep at the wheel. The companies building superintelligence admit the danger, yet expect to create the tech wi
arXiv:2605.01416v1 Announce Type: cross Abstract: The increasing scale and complexity of online platforms raises critical policy questions around harmful content, digital well-being, and user autonomy
arXiv:2505.13150v2 Announce Type: replace Abstract: Behavioral Foundation Models (BFMs) proved successful in producing policies for arbitrary tasks in a zero-shot manner, requiring no test-time traini
arXiv:2605.00457v1 Announce Type: cross Abstract: The coexistence of NR-U and Wi-Fi in unlicensed spectrum introduces a system-level resource coordination problem, where heterogeneous channel access m
Gary Marcus explores hypothetical scenarios and consequences if OpenAI were to fail or lose its competitive position in the AI industry. The post likely examines implications for AI development, the b
arXiv:2605.00229v1 Announce Type: cross Abstract: We study the problem of training diffusion and flow generative models to sample from target distributions defined by an exponential tilting of a base
arXiv:2605.00443v1 Announce Type: cross Abstract: The advancement of generalized deepfake disruption is constrained by the interruption imbalance, a fundamental bottleneck inherent to the generation o
arXiv:2605.00410v1 Announce Type: new Abstract: A multi-agent pipeline with N agents typically issues N LLM calls per run. Merging agents into fewer calls (compound execution) promises token savings,
Almost every warning that I have issued over the last several years has come true. You better hope to God or Darwin or whoever you believe in that this one is wrong. Accidental nuclear war is a potent
🌐At the @UN, @Yoshua_Bengio briefed @antonioguterres on AI governance, followed by a reception with @CanadaUN & @DavidLametti opened by @EgriseldaL As AI risks grow, global coordination matters. 🔗AI D
arXiv:2508.06361v4 Announce Type: replace Abstract: Large Language Models (LLMs) are widely deployed in reasoning, planning, and decision-making tasks, making their trustworthiness critical. A signifi
arXiv:2411.10915v2 Announce Type: replace Abstract: Large Language Models (LLMs) have revolutionized natural language processing, but their susceptibility to biases poses significant challenges. This
arXiv:2605.00632v1 Announce Type: new Abstract: Automatic generation of executable Blender code from natural language remains challenging, with state-of-the-art LLMs producing frequent syntactic error
arXiv:2605.00405v1 Announce Type: new Abstract: Most existing heterogeneous cooperative perception methods depend on prior preparation like offline joint training or tailored collaborator-model adapta
arXiv:2602.00665v3 Announce Type: replace Abstract: Customer-service question answering (QA) systems increasingly rely on conversational language understanding. While Large Language Models (LLMs) achi
Confirmed 2.5 years later, by Greg Brockman. Remember how Sam Altman told the US Senate he had no “direct” investment in OpenAI? and how they gushed over his apparent selflessness? 👉He didn’t mention
arXiv:2605.00298v1 Announce Type: new Abstract: Deploying reinforcement learning policies in the real world requires adapting to time-varying environments. We study this problem in the contextual Mark
arXiv:2512.20260v5 Announce Type: replace Abstract: Weakly-Supervised Camouflaged Object Detection (WSCOD) aims to locate and segment objects that are visually concealed within their surrounding scene
arXiv:2605.00723v1 Announce Type: cross Abstract: We propose Decentralized Proximal Stochastic Gradient Langevin Dynamics (DE-PSGLD), a decentralized Markov chain Monte Carlo (MCMC) algorithm for samp
arXiv:2605.00066v1 Announce Type: new Abstract: Open-loop evaluation offers fast, reproducible assessment of autonomous driving planners, but its ability to predict real closed-loop driving performanc
Gary Marcus and Sam Altman testified before the Senate regarding AI oversight, with Marcus noting that two individuals stood up during the hearing and asserting that one of them told the truth. This r
arXiv:2605.00238v1 Announce Type: new Abstract: Automated short answer grading (ASAG) with large language models (LLMs) is commonly evaluated with aggregate metrics such as macro-F1 and Cohen's kappa.
arXiv:2605.00185v1 Announce Type: new Abstract: Dataset Distillation aims to compress a large dataset into a small synthetic one while maintaining predictive performance. We show that as different dem
arXiv:2605.00592v1 Announce Type: new Abstract: In Machine Learning, an accepted definition of fairness of a decision taken by a classifier is that it should not depend on protected features, such as
arXiv:2605.00678v1 Announce Type: new Abstract: Aerosol Optical Depth (AOD) retrieval is essential for Earth observation, supporting applications from air quality monitoring to climate studies. Conven
arXiv:2509.24621v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) are emerging as versatile foundations for mixed-modality retrieval. Yet, they often require heavy post-hoc