Knowledge catalogue
arXiv:2511.19706v2 Announce Type: replace-cross Abstract: Rotation invariance is a fundamental requirement across many computer vision tasks. Historically, this inductive bias has been encoded through
arXiv:2606.10334v1 Announce Type: new Abstract: Code-generating large language models (LLMs) increasingly produce visual artifacts such as charts, web pages, and slides by writing programs that are ex
arXiv:2606.09837v1 Announce Type: cross Abstract: Emotional interaction is increasingly crucial for conversational AI, yet current systems lack a self-emotion determination mechanism to drive the stre
arXiv:2606.10688v1 Announce Type: new Abstract: Autonomous driving relies on computationally intensive perception pipelines to continuously detect and track objects in the surrounding environment. Whi
arXiv:2606.09888v1 Announce Type: new Abstract: Linear attention provides an efficient backbone for long-sequence recommendation by avoiding the quadratic cost of standard Transformers, but its compre
arXiv:2606.09849v1 Announce Type: cross Abstract: Building-integrated photobioreactors (PBRs) offer a pathway for carbon-neutral architecture, yet deployment is hindered by configuration complexity an
So far today • Banks to SoftBank: No thanks; OpenAI stock ain’t worth what you say. • Germany to Google: LLMs can be held liable • Senator Warren to SEC and SpaceX: Fix this mess; it’’s foul play to s
arXiv:2606.09887v1 Announce Type: cross Abstract: Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness. Such rewar
arXiv:2606.10091v1 Announce Type: cross Abstract: Machine learning (ML) models are susceptible to various security, privacy, and fairness risks. Adversaries with different characteristics (i.e., objec
Amrith Ramkumar / Wall Street Journal: Sources: Trump administration officials have told CAISI to halt publication of its model assessments while an EO President Trump signed last week is implemented
arXiv:2606.10654v1 Announce Type: new Abstract: We investigate what self-supervised speech recognition models (S3Ms) learn about speaker groups (SGs). We examine several states of S3Ms: pretrained, fi
arXiv:2606.06037v2 Announce Type: cross Abstract: Large audio language models (LALMs) are increasingly deployed in real-world applications, yet their safety alignment is still primarily evaluated on m
arXiv:2406.08726v3 Announce Type: replace Abstract: Large language models (LLMs) generate text that reinforces standard language ideology: a bias towards certain language varieties that are granted mo
arXiv:2606.10653v1 Announce Type: new Abstract: Although pretrained text-to-image (T2I) generation models can produce high-quality images, they often fail to faithfully reflect the semantic intent of
arXiv:2606.10487v1 Announce Type: cross Abstract: Deploying large language models in user-facing systems requires efficient output safety filtering. Existing approaches typically rely on a separate mo
arXiv:2602.02788v2 Announce Type: replace-cross Abstract: We aim to develop physics foundation models for science and engineering that provide real-time solutions to Partial Differential Equations (PD
subtle shift: some folks seemed to have shifted from expecting truly exponential progress to being happy they can find measurable progress at all. and another, even larger group has grown concerned ab
arXiv:2606.09858v1 Announce Type: cross Abstract: Robust decision-making requires compression. A system that forms a rich support state cannot usually preserve its full structure at the point of actio
arXiv:2602.04119v2 Announce Type: replace Abstract: The application of generative models for experimental drug discovery campaigns is severely limited by the difficulty of designing molecules de novo
arXiv:2606.10918v1 Announce Type: cross Abstract: The recent trend in scaling models for robot learning has resulted in impressive policies that can perform various manipulation tasks and generalize t
arXiv:2606.09883v1 Announce Type: cross Abstract: Large language models (LLMs) have made remarkable progress in reasoning tasks, largely driven by post-training paradigms, especially reinforcement lea
arXiv:2606.10371v1 Announce Type: cross Abstract: Diffusion-based action generation has become a foundational component of embodied AI, but its reliance on visual conditioning leaves deployed visuomot
arXiv:2606.11087v1 Announce Type: cross Abstract: Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simu
Dario Amodei's essay discusses the broad societal implications of AI's rapid advancement, examining its potential impacts across multiple domains including employment, economic disruption, accelerated
arXiv:2606.11173v1 Announce Type: new Abstract: Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response. Self-distillation trains t
arXiv:2606.09902v1 Announce Type: cross Abstract: Reservoir computing exploits the fixed dynamics of a recurrent network for temporal processing, requiring only a trained linear readout. Biological ne
Gary Marcus warns about a widespread scam epidemic involving fake profiles that use stolen pictures and randomly generated usernames/handles to deceive people. He shares an example of his response to
This is genuinely big news, major unintended consequences. 🚨Breaking news that could be huge, and enormously bad for GenAI, if other countries make similar decisions. https://the-decoder.com/landmark-
this is important. and scary. CAISI has reportedly been directed to stop publishing public model assessments as the new AI EO gets implemented. Natsec engagement on AI is essential. But pulling CAISI'
Today I'm publishing a new essay, Policy on the AI Exponential. AI is progressing extremely fast—much faster than the policy process was built to handle. The essay lays out where I think the technolog
arXiv:2606.09881v1 Announce Type: cross Abstract: Deepfake detectors show large performance gaps across demographic groups. Existing fairness approaches require demographic labels, retraining, or sacr
arXiv:2606.11119v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models. H
arXiv:2606.10472v1 Announce Type: cross Abstract: Dynamic multi-resource allocation is a central problem in shared computing environments, where users' demands arrive sequentially and resources must b
arXiv:2606.09866v1 Announce Type: cross Abstract: Fine-tuning safety aligned large language models (LLMs) on downstream data improves adaptation but may erode learned safety behavior. Existing methods
arXiv:2606.10501v1 Announce Type: new Abstract: Deploying Vision-Language-Action (VLA) models in real robotic systems requires robustness not only to semantic and perceptual variations, but also to em
arXiv:2606.11131v1 Announce Type: new Abstract: Most existing deep learning-based PET image denoising methods assume a fixed and known dose reduction factor (DRF) for low-dose PET images. However, the
arXiv:2606.09856v1 Announce Type: cross Abstract: Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such as mathematics and coding where correctness is veri
arXiv:2411.05698v3 Announce Type: replace-cross Abstract: Convolutional Neural Networks (CNNs) have shown remarkable performance in image classification. However, interpreting their predictions is cha
Senator Elizabeth Warren criticized the SEC for insufficient enforcement and investor protection, urging the agency to strengthen oversight and prevent harm to retail investors. The post, shared by AI
What if, Germany locked itself out of the LLM race and • Had students who actually learned things in high school, instead of turning in prompt outputs they barely read • Emerged from the sea of slop •
arXiv:2606.09421v2 Announce Type: replace Abstract: Large language model agents increasingly rely on skills: reusable procedural documents encoding workflows, tool use, implementation patterns, valida
arXiv:2512.06343v3 Announce Type: replace-cross Abstract: Reward models are central to Large Language Model (LLM) alignment within the framework of RLHF. The standard objective used in reward modeling
arXiv:2606.10740v1 Announce Type: new Abstract: Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation. A model can lock onto an unsafe stance early in a long dialo
arXiv:2606.11190v1 Announce Type: new Abstract: Cross-modal alignment (CA) and cross-modal prediction (CP) are the dominant paradigms for multimodal representation learning, yet there is no systematic
When you hear AI 'safety' you should hear 'censorship' and 'control' instead. All of us surveilled and spied by safeguards of loving grace. Today it's intelligent Terms of Service control. You can't d
Why are AI research restrictions treated differently from every other safeguard? @theemozilla and @karan4d, co-founders of Nous Research: 'On the bio stuff... just saying no to the user and being hone
Wow. This is worth watching, might have huge impact. @SenWarren makes some valid points, and the SEC owes her public answers Sen. Warren calls on SEC to delay SpaceX IPO @CNBC https://www.cnbc.com/202
arXiv:2606.10244v1 Announce Type: cross Abstract: We introduce Yielding Universal Bidigital Interface (YUBI), a finger-aligned gripper designed to enable intuitive, ergonomic, and scalable data collec
arXiv:2602.12246v2 Announce Type: replace-cross Abstract: The convergence of robotics and next-generation communication is a critical driver of technological advancement. As the world transitions from
arXiv:2606.09470v1 Announce Type: cross Abstract: Automated L2 speech assessment can assign proficiency labels, but often lacks interpretability. We propose a rubric-guided SpeechLLM for multi-aspect,
arXiv:2512.07355v2 Announce Type: replace Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what
arXiv:2606.08517v1 Announce Type: new Abstract: Selective predictors answer on confident inputs and abstain elsewhere; deploying one safely needs a single finite-sample certificate that simultaneously
arXiv:2602.24181v2 Announce Type: replace-cross Abstract: Pre-trained vision encoders like DINOv2 have demonstrated exceptional performance on unimodal tasks. However, we observe that their features a
arXiv:2606.09253v1 Announce Type: new Abstract: Deformable image registration (DIR) is widely used in radiotherapy for dose propagation and accumulation, but uncertainty in the underlying deformation
arXiv:2606.09073v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) is bottlenecked by reward hacking, where the policy exploits errors in a proxy reward model (RM) and
arXiv:2606.09542v1 Announce Type: new Abstract: Traffic accident anticipation -- predicting the likelihood of an imminent collision at every frame of a dashcam video -- is safety-critical yet difficul
arXiv:2606.08292v1 Announce Type: new Abstract: In mechanistic interpretability, attention heads are commonly elevated to role claims (e.g., 'this head represents addition') when they are necessary fo
absolutely correct @GaryMarcus I've recently learned not to believe anything that anyone says anymore when it comes to AI companies. They're all competing to win against each other while exploiting, s
arXiv:2606.08508v1 Announce Type: cross Abstract: Generative robot policies fail unpredictably at deployment: they hesitate at critical moments, drift off-task, or commit to unrecoverable actions. Exi
arXiv:2606.08480v1 Announce Type: cross Abstract: Reinforcement learning (RL) presents a promising avenue for enhancing generative recommendation beyond supervised imitation, leveraging reward signals