Knowledge catalogue
arXiv:2412.09529v4 Announce Type: replace Abstract: Radiology, with its heterogeneous modalities, anatomies, and evolving protocols, is a natural yet high-stakes testbed for agentic AI. As LLMs grow m
arXiv:2609.07091v1 Announce Type: new Abstract: Autonomous mobile robots performing person-following tasks often suffer from temporary occlusions and sensor track loss in dynamic environments. This re
arXiv:2609.08300v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) achieve remarkable performance on generic image captioning, they frequently suffer from structural halluc
arXiv:2403.14293v3 Announce Type: replace Abstract: As robots become increasingly integrated into various industries, understanding how humans respond to robotic failures is critical. This study syste
arXiv:2609.07990v1 Announce Type: new Abstract: Sequential reinforcement learning (RL) solvers and global diffusion model (DM) solvers for neural combinatorial optimization exhibit complementary failu
arXiv:2603.26517v2 Announce Type: replace-cross Abstract: The discovery of constitutive laws from experimentally accessible measurements is a central problem in nonlinear computational mechanics. Many
arXiv:2609.08690v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models expand model capacity without a proportional increase in training compute, but increasing sparsity makes reliable hyperp
arXiv:2601.21255v2 Announce Type: replace Abstract: A central problem in self-supervised learning is preventing representation collapse. Most methods avoid it through global mechanisms, such as contra
arXiv:2609.08121v1 Announce Type: new Abstract: Low-rank tensor modeling has become an effective tool for hyperspectral anomaly detection. However, existing methods still suffer from high computationa
arXiv:2603.25255v2 Announce Type: replace Abstract: Trajectory anomaly detection underpins applications from fraud detection to urban mobility analysis. Dense GPS methods preserve fine-grained evidenc
arXiv:2609.07017v1 Announce Type: new Abstract: Hyperball optimizers constrain parameter norms and update only their directions, establishing a distinct paradigm for neural network optimization. Altho
arXiv:2609.08286v1 Announce Type: new Abstract: Multi-scale modeling has become an effective approach for long-term time series forecasting, capturing temporal patterns that range from fine-grained lo
arXiv:2609.07596v1 Announce Type: cross Abstract: Vision-language models are increasingly used in settings where some input modalities may be unavailable, yet we know little about whether they can fai
I dropped out of a PhD in AI safety partially for the opposite reason. I didn’t believe AI existential risk was as important as the doomers think. My biggest pet peeve is that no one can really provid
i just tried Muse*, connected it to my GitHub, and continued the work I was doing in ChatGPT/Claude w no interruptions which is great cuz i now have more credits across more services to do work with :
I like this framing a lot: agent improvement is harness improvement, not model improvement The interesting interventions are often at the tool boundary: - what context you pass - when tools are provid
I’ve been experimenting with explaining AI/LLM concepts in a way that doesn’t assume too much technical background. This video is about KV Cache and why longer context windows require more memory duri
I put together a mega write-up on GPT-6 Astra & looped transformers. How looped transformers / recurrent depth works, cost-tradeoffs, whether it hides reasoning traces, with lots of figures and a tour
I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving
(hopefully this is okay to here - it seems like audio models and image / video modeals is allowed but yeah this is a bit different) So I've been doing independent audio research for a while now. The u
I worked at Google DeepMind and now at Anthropic. This is a common sentiment amongst my peers. (I write this in personal capacity.) There is not yet a viable scientific plan to solve risks from recurs
arXiv:2609.07581v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies are commonly adapted to new manipulation settings through additional gradient updates, which limits rapid deployme
A recap of August 2026 launches for AI builders across Amazon Bedrock, Amazon Bedrock AgentCore, and Strands: million-token context for OpenAI models, cross-Region inference, agents that run for up to
arXiv:2505.21465v2 Announce Type: replace Abstract: Currently, a prevalent approach for enhancing Vision-Language Models (VLMs) performance is to encode both the high-resolution version and the thumbn
Gary Marcus has urged caution regarding Generative AI by proposing a boycott and highlighted this stance in a short post shared on Twitter (@GaryMarcus). He suggests that if just 1 % of people who fol
If they truly believe the risk is that high, and I think they do, then we need 100x more research and understanding of it. That requires them to openly share their models, datasets, training code, and
arXiv:2609.06131v1 Announce Type: cross Abstract: Environmental identification in wireless sensing is essential for 6G integrated sensing and communication (ISAC) systems to achieve reliable situation
arXiv:2609.06279v1 Announce Type: cross Abstract: Learning-based manipulation requires supervision that is both semantically meaningful and physically executable, but current data pipelines often prov
arXiv:2609.06051v1 Announce Type: new Abstract: The sensitivity of visual recognition models to changes in image scale is well established, yet the factors governing this sensitivity across heterogene
arXiv:2508.06990v2 Announce Type: replace Abstract: Semantic navigation requires an agent to navigate toward a specified target in an unseen environment. Employing an imaginative navigation strategy t
arXiv:2609.07408v1 Announce Type: cross Abstract: This study investigates the classification of individuals as healthy or at risk of Parkinson's disease using machine learning (ML) models, focusing on
arXiv:2602.04761v2 Announce Type: replace Abstract: Gradient-variation online learning has drawn increasing attention due to its deep connections to game theory and optimization. It has been studied e
arXiv:2606.15277v2 Announce Type: replace-cross Abstract: Graph-based recommendation models effectively capture high-order collaborative signals from user--item interaction graphs. Federated learning
arXiv:2509.19994v3 Announce Type: replace Abstract: Multimodal pre-trained models (e.g., ImageBind), which align distinct data modalities into a shared embedding space, have shown remarkable success a
arXiv:2609.07493v1 Announce Type: new Abstract: In this paper, we propose a class-wise dimension (channel) selection framework for Multivariate Time Series Classification (MTSC). Rather than applying
In my latest op-ed for @TIME, I discuss why the OpenAI Hugging Face cyber incident represents a turning point for AI safety. If we want to prevent more autonomous cyberattacks from threatening critica
arXiv:2609.08463v1 Announce Type: cross Abstract: We apply transfer learning (TL) to construct data-driven models of inclusive electron-nucleus cross sections. Starting from an ensemble of deep neural
arXiv:2609.06649v1 Announce Type: new Abstract: Reward hacking during reinforcement learning from verifiable rewards (RLVR) can induce reward seeking and broad misalignment in language models. Studyin
arXiv:2609.07349v1 Announce Type: new Abstract: Real-time urban governance depends not only on knowing where people are, but on how they move between places, directional flows that could be convention
arXiv:2609.07874v1 Announce Type: new Abstract: Multimodal large language models often capture visual-linguistic correlations but struggle to predict how local visual interventions propagate and affec
arXiv:2609.05569v1 Announce Type: new Abstract: The autonomous localization of fugitive gas emissions using small Unmanned Aircraft Systems (sUAS) constitutes a fundamentally ill-posed inverse problem
arXiv:2609.05523v1 Announce Type: new Abstract: This paper presents a one-stage learning framework that maps monocular roadside-camera images directly to vehicle states in a ground-fixed coordinate fr
arXiv:2609.06983v1 Announce Type: cross Abstract: Generalized Nash Equilibrium Problems (GNEPs) often arise in multi-agent engineering applications that require distributed algorithms. Unlike traditio
arXiv:2508.17708v2 Announce Type: replace Abstract: X-ray micro-computed tomography (micro-CT) provides non-destructive three-dimensional (3D) imaging of porous material microstructures. In situ exper
arXiv:2310.16295v2 Announce Type: replace-cross Abstract: Neural network have achieved remarkable successes in many scientific fields. However, the interpretability of the neural network model is stil
arXiv:2609.05946v1 Announce Type: new Abstract: Interpretability and fairness are two of the most emphasized dimensions in trustworthy artificial intelligence (AI). Various explainable AI methods have
arXiv:2609.08786v1 Announce Type: new Abstract: Hyperspectral unmixing decomposes mixed pixels into material endmembers and their abundances from contiguous spectral observations. In modular sensing p
arXiv:2509.15611v2 Announce Type: replace-cross Abstract: Machine learning algorithms often assume that training samples are independent. When data points are connected by a network, the induced depen
arXiv:2507.21831v2 Announce Type: replace-cross Abstract: LLMs are seeing widespread use for task automation, including automated coding in the social sciences. However, even though researchers have p
arXiv:2609.06546v1 Announce Type: cross Abstract: Although machine learning can be used to predict the evolution of physical systems from data, a formulation that learns only the system state at each
arXiv:2609.08722v1 Announce Type: cross Abstract: Pigment deposition in paper marbling displaces the pattern already present, coupling the appearance of each gesture to later actions. We recover execu
Investigating how one AI agent works might not be enough, since there are emerging properties when these agents collaborate as tribes Thinking about this for years. I believe we're at the point of no
arXiv:2609.08375v1 Announce Type: new Abstract: Industrial process monitoring is fundamental to the safety and economic performance of modern process plants. Current practice remains a one-task-one-mo
arXiv:2505.17966v3 Announce Type: replace-cross Abstract: This paper evaluates single-view mesh reconstruction models for their potential in enabling instant digital twin creation for real-time planni
arXiv:2609.07226v1 Announce Type: cross Abstract: This paper proposes a general framework for stable and effective iterative audio separation with mixture consistency by extending source separation mo
It's crazy how far small models can be pushed. Robbyant just open-sourced LingBot-World 2.0 Small, a 1.3B world model that generates an interactive world in real time on a single consumer GPU. Same pa
arXiv:2609.06018v1 Announce Type: new Abstract: Ideal point estimation is widely used to analyze and visualize political data. However, selecting the corresponding spatial model involves various trade
arXiv:2609.07915v1 Announce Type: new Abstract: Large vision models provide useful representations for remote-sensing segmentation but are often too expensive for deployment at the satellite or field
arXiv:2609.06955v1 Announce Type: new Abstract: Predicting hand--object interaction fields requires locating the nearest object-surface point for each hand joint, often from small and partially occlud
arXiv:2609.08755v1 Announce Type: new Abstract: Many emerging video language modeling tasks require systems to move beyond clip-level abstraction and model visual content as it unfolds over extended t