Knowledge catalogue
I feel like I'm eating crazy pills when I read the countless bad takes around how the Vatican would have virtually anointed Anthropic. When if you read the Pope's encyclical it's actually a COMPLETE r
arXiv:2605.24217v1 Announce Type: new Abstract: As Large Language Models (LLMs) transition from research environments to production deployments, evaluating their performance against strict Service Lev
⚠️⚠️⚠️if you believe this you and think you are safe, you don’t understand how S&P is about to change the rules and what that means. run don’t walk to read my essay “This one weird trick might cost yo
Gary Marcus discusses a potentially overlooked financial risk that could have massive implications for retirement savings, presenting his analysis in an essay format on X. The post appears to emphasiz
arXiv:2603.05691v2 Announce Type: replace Abstract: It is increasingly common in machine learning to use learned models to label data and then employ such data to train more capable models. The phenom
arXiv:2605.24009v1 Announce Type: cross Abstract: Convective available potential energy (CAPE) is an important variable for forecasting severe weather and understanding deep convection and precipitati
arXiv:2605.23924v1 Announce Type: new Abstract: Segment-level disclosures are a central component of financial reporting, providing insight into firms' internal organization and the allocation of econ
In our new paper, EDGE-OPD (EviDence GuidEd On-Policy Distillation), we introduce two key ideas for improving On-Policy Distillation (OPD). First, we use guided rollouts that inject privileged context
arXiv:2605.25123v1 Announce Type: cross Abstract: We study inference-time alignment for diffusion-based generative models, aiming to steer a base model toward high-reward outputs without updating its
arXiv:2605.05226v2 Announce Type: replace-cross Abstract: The central challenge of reinforcement learning for reasoning lies not only in the sparsity of outcome-level supervision, but more fundamental
arXiv:2605.24960v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) faithfulness, i.e., whether CoTs genuinely reflect large language models' (LLM) underlying behavior, is typically evaluated und
arXiv:2605.24538v1 Announce Type: cross Abstract: Every major framework for governing artificial intelligence presupposes an identifiable entity -- a developer, deployer, or operator -- who can be hel
arXiv:2605.24339v1 Announce Type: new Abstract: We present IsaacIPC, a robotic simulation framework that couples GPU accelerated incremental potential contact (IPC) with IsaacSim/Lab. IsaacIPC maps si
arXiv:2501.14889v2 Announce Type: replace Abstract: Iterative feature space optimization involves systematically evaluating and adjusting the feature space to improve downstream task performance. Howe
arXiv:2605.24041v1 Announce Type: cross Abstract: Neural operators serve as fast, data-driven surrogates for scientific modeling but typically rely on a monolithic, single-pass inference procedure tha
It's a shame the Pope didn't ask Chris Olah what happened to his plan to give up to 10% of Anthropic to the authors of the work they train on. (Spoiler: it never happened, and the authors on whose wor
arXiv:2605.23997v1 Announce Type: cross Abstract: Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they
arXiv:2605.25916v1 Announce Type: new Abstract: Federated edge learning (FEEL) has recently emerged as a promising paradigm for achieving edge intelligence (EI) via enabling collaborative model traini
arXiv:2605.25376v1 Announce Type: cross Abstract: Observability tells operators when an agent is slow. KYA tells operators when an agent is wrong, drifting, leaking, or quietly going rogue. We present
arXiv:2605.25275v1 Announce Type: new Abstract: The Neural Tangent Kernel (NTK) framework explains optimization in over-parameterized neural networks via approximately linearized dynamics, yielding ex
arXiv:2605.25036v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) extend large language models with visual understanding, but remain vulnerable to hallucination, where outputs are
arXiv:2605.24584v1 Announce Type: cross Abstract: Fast linear algebra in deep learning usually comes with a choice: fixed geometry and exact computation, as in the Fourier transform, or adaptive geome
arXiv:2605.25740v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (GCRL) provides a practical framework for obtaining goal-reaching policies from fixed datasets. However,
arXiv:2605.24005v1 Announce Type: new Abstract: The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous
arXiv:2603.29123v2 Announce Type: replace Abstract: The next-token prediction (NTP) objective trains language models to predict a single token at each step, even though many continuations can express
arXiv:2605.24931v1 Announce Type: new Abstract: Modern robotic policies increasingly rely on action chunking to execute complex tasks in the physical world. While action chunking improves temporal con
arXiv:2605.26012v1 Announce Type: cross Abstract: Deep reinforcement learning (RL) agents commonly rely on high-dimensional neural representations, despite growing evidence that task-relevant value an
arXiv:2605.25360v1 Announce Type: new Abstract: Large language models~(LLMs) are trained on heterogeneous multilingual corpora, yet existing policy optimization methods often implicitly restrict each
arXiv:2605.25179v1 Announce Type: new Abstract: Audio-language models (ALMs) are increasingly used for audio captioning, question answering, and open-ended audio understanding, but their inference cos
lol. OpenAI as the WeWork of AI. Literally called it, in those exact words, @CNBC w @carlquintanilla, 2024. Now even SoftBank is worried. SoftBank's own executives think Sam Altman is scamming their C
arXiv:2605.23952v1 Announce Type: new Abstract: Artificial agents now generate behavior rich enough to invite trust, surprise, and concern, yet our evaluation tools still privilege capability scores o
arXiv:2605.26004v1 Announce Type: cross Abstract: Instruction tuning of large vision-language models (LVLMs) increasingly depends on massive multimodal corpora, yet these datasets contain samples with
arXiv:2605.24139v1 Announce Type: new Abstract: Imperfect-information games (IIGs) are challenging, as players must make decisions without fully observing the true game state. While AlphaZero has achi
arXiv:2602.17658v2 Announce Type: replace-cross Abstract: Reward modeling is central to alignment pipelines such as RLHF, RLAIF, and PPO-based policy optimization, yet its reliability is constrained b
arXiv:2605.25342v1 Announce Type: new Abstract: Aligning large language models (LLMs) with diverse and multifaceted user preferences is a fundamental challenge in personalized AI systems. Existing mul
arXiv:2602.02474v2 Announce Type: replace-cross Abstract: Most Large Language Model (LLM) agent memory systems rely on a small set of static, hand-designed operations for extracting memory. These fixe
arXiv:2605.23981v1 Announce Type: cross Abstract: Generative AI research increasingly confronts a shared problem: systems must sustain yet govern their own generative activity when uncertainty is high
arXiv:2605.25025v1 Announce Type: new Abstract: Coordinating micro-robotic swarms in physiologically realistic, time-dependent fluid environments remains an unsolved challenge for biomedical and envir
arXiv:2601.05483v2 Announce Type: replace Abstract: Understanding urban environment change is essential for sustainable development. However, current approaches, particularly remote sensing change det
arXiv:2605.24754v1 Announce Type: cross Abstract: Neural network weights are increasingly a bottleneck for deployment, yet most compression pipelines treat layers independently and overlook cross-laye
arXiv:2605.24592v1 Announce Type: new Abstract: This paper presents MuGen, a data-driven framework for learning and deploying multi-skill locomotion on humanoid robots. MuGen enables a robot to perfor
arXiv:2605.25746v1 Announce Type: cross Abstract: As large language model (LLM)-based multi-agent systems scale to handle increasingly complex tasks, balancing structural stability and dynamic adaptab
arXiv:2605.25929v1 Announce Type: cross Abstract: The effectiveness of multi-agent LLM deliberation depends not only on the agents' individual predictions, but also on how they communicate and collabo
arXiv:2512.08508v2 Announce Type: replace-cross Abstract: Identifying enzymes that catalyze target biochemical reactions is a key step in computational enzyme discovery and biocatalyst design. Recent
arXiv:2209.11572v3 Announce Type: replace-cross Abstract: As an increasingly popular task in multimedia information retrieval, video moment retrieval (VMR) aims to localize the target moment from an u
arXiv:2605.25210v1 Announce Type: cross Abstract: Diffusion models are increasingly used as powerful conditional generators, yet real deployments often involve multiple target distributions arising fr
arXiv:2605.25220v1 Announce Type: cross Abstract: High-fidelity 3D Gaussian head avatar generation is critical for applications such as AR/VR, telepresence, and digital humans. Existing methods depend
arXiv:2605.24364v1 Announce Type: cross Abstract: Multicalibration extends classical calibration by requiring predictions to be unbiased over a rich collection of functions, encompassing both predicti
arXiv:2605.23961v1 Announce Type: cross Abstract: The design of RNA molecules that interact with specific proteins is a critical challenge in experimental and computational biology. Despite recent pro
arXiv:2512.23076v2 Announce Type: replace-cross Abstract: Emotional states manifest as coordinated yet heterogeneous physiological responses across central and autonomic systems, posing a fundamental
arXiv:2505.23803v2 Announce Type: replace-cross Abstract: Phishing email detection faces significant challenges due to evolving adversarial tactics and heterogeneous attack patterns. Traditional appro
arXiv:2605.24193v1 Announce Type: cross Abstract: Competitive music transcription models require large amounts of paired audio-score data, which is scarce due to collection costs, alignment difficulty
arXiv:2510.20390v2 Announce Type: replace Abstract: Grasping accuracy is a critical prerequisite for precise object manipulation, often requiring careful alignment between the robot hand and object. N
arXiv:2605.24152v1 Announce Type: new Abstract: We present a neuro-inspired framework for embodied planning and control. Building on three principles that enable fast and highly effective goal-directe
arXiv:2605.24071v1 Announce Type: cross Abstract: Training a reinforcement learning agent on-policy means collecting fresh experience at every update, and that experience comes with a hidden problem.
arXiv:2605.25381v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a core technique for post-training of Large Language Models (LLMs). While policy optimi
arXiv:2605.25829v1 Announce Type: cross Abstract: Recent vision-language-action (VLA) models and world action models (WAMs) advance robotic manipulation by enriching intermediate representations with
Gary Marcus, a prominent AI researcher and critic, questions whether a word cloud diagram could possess consciousness, likely engaging in ironic commentary on overclaimed AI capabilities or consciousn
arXiv:2602.10635v2 Announce Type: replace Abstract: Socially intelligent AI systems must entail reasoning across diverse human behavioral tasks, and generalization to new contexts. However, AI has yet
arXiv:2605.25819v1 Announce Type: new Abstract: Membership inference attacks (MIAs) are popular methods for empirically assessing the leakage of sensitive information in the training data through mode