Knowledge catalogue
arXiv:2406.04814v4 Announce Type: replace-cross Abstract: Video diffusion models can enable embodied agents to anticipate plausible futures from the recent past, but they are typically trained offline
arXiv:2609.25757v1 Announce Type: new Abstract: What is the least recurrent memory needed to reproduce a specified expert under partial observability? The instantaneous requirement is the conditional
arXiv:2609.26217v1 Announce Type: new Abstract: Compact language models are typically deployed by retaining a single post-training checkpoint and sampling it repeatedly. In this work, we challenge thi
Note that this is an experimental model meant to show how you can train your own specialized decision models fairly easily! You can also check out the model weights here, along with the full tutorial
arXiv:2609.25770v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong performance on tasks such as visual question answering, yet small image resizes can turn correct answ
arXiv:2609.25619v1 Announce Type: new Abstract: This work investigates how to enable general multi-finger robotic hands to perform the complete tool manipulation process, which entails picking up a to
arXiv:2510.16656v2 Announce Type: replace Abstract: Modeling dynamical systems and unraveling their underlying structural dependencies is central to many domains in the natural sciences. Various physi
arXiv:2505.01583v2 Announce Type: replace Abstract: Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models (VLMs
arXiv:2409.02244v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly being used as ad hoc therapists. While prior research has found that LLMs outperform human couns
arXiv:2508.20443v3 Announce Type: replace Abstract: Large language models (LLMs) are trained on massive datasets that may include private or copyrighted content. Due to growing privacy and ownership c
arXiv:2603.11323v2 Announce Type: replace Abstract: The simplicity and effectiveness of UNet architectures make them ubiquitous in image restoration, segmentation, and diffusion models. They are often
We're releasing tev1-4B-experimental, a Jev-like classifier finetuned on top of Qwen3.5 4B. We're making it available on Together serverless at 0.042/M input & 0/M output. Also releasing the data reci
arXiv:2609.25108v1 Announce Type: new Abstract: Visual data is increasingly consumed by machine-vision systems rather than by human observers. Image Coding for Machines (ICM) compresses images assumin
arXiv:2609.23836v1 Announce Type: new Abstract: A fundamentally challenging question in K-12 education is about the effects of taking more advanced or challenging classes. It is particularly complex b
arXiv:2609.24302v1 Announce Type: cross Abstract: Virtual screening aims to prioritize active compounds from large chemical libraries within a limited experimental budget. When applying Boltz-2 to vir
arXiv:2609.22332v1 Announce Type: cross Abstract: Generalizable robot manipulation requires predicting how a scene will evolve, identifying where interactions are feasible, and determining how to act.
arXiv:2310.00436v2 Announce Type: replace Abstract: Authorship identification uses patterns in writing to infer who wrote a text, but those patterns also reflect topic, genre, and register. This surve
arXiv:2609.23212v1 Announce Type: cross Abstract: The Deck-of-cards-based Ordinal Regression (DOR) infers a value function from a ranking of reference alternatives in which the Decision Maker (DM) ins
arXiv:2609.22583v1 Announce Type: new Abstract: Predictive maintenance in Industry 4.0 refers to using data from sensors, machines, and production systems to estimate when equipment is likely to fail,
arXiv:2609.24745v1 Announce Type: new Abstract: World action models generate actions together with visual predictions of their consequences. These paired outputs create the potential for planning by s
arXiv:2609.23594v1 Announce Type: new Abstract: Orthogonality in a LoRA factor does not by itself specify what the composed update protects: the answer depends on the task-start state, the parameteriz
arXiv:2609.23387v1 Announce Type: new Abstract: Before a machine learning model can learn a thermodynamic equation of state, it must discover what its measurements represent: which channels scale with
arXiv:2609.23184v1 Announce Type: new Abstract: Embodied world models learn to predict future physical dynamics from visual observations and control signals, where physical knowledge is implicitly ent
arXiv:2609.22166v1 Announce Type: new Abstract: The rapid advancement of Internet of Things (IoT) technology has led to the widespread deployment of smart, interconnected devices across a range of dom
arXiv:2609.22361v1 Announce Type: new Abstract: Joint audio--video generators are trained on data in which what an event looks like and what it sounds like are strongly, often spuriously, correlated:
arXiv:2604.06655v2 Announce Type: replace Abstract: Diffusion-based generative video compression offers a promising paradigm for low-bitrate reconstruction, but existing keyframe-based controllable ap
arXiv:2609.24066v1 Announce Type: new Abstract: Best-of-N is a widely used inference strategy for complex reasoning, whose effectiveness depends on whether sampled candidates can cover diverse and hig
arXiv:2609.22816v1 Announce Type: new Abstract: Reward-free latent world models can learn from offline videos and solve new image--goal tasks by optimizing actions through predicted latent futures. Th
arXiv:2609.24083v1 Announce Type: new Abstract: Generative AI enables scalable production of educational videos, but current systems largely focus on producing visually coherent content rather than su
arXiv:2609.24026v1 Announce Type: new Abstract: In this paper, we investigate the limitations of fixed, hand-crafted connectors in hierarchical semantic representations for open-vocabulary object dete
arXiv:2609.23367v1 Announce Type: cross Abstract: FORM is a domain-specific symbolic manipulation language widely used in particle physics for processing the very large algebraic expressions arising f
arXiv:2609.23565v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models integrate vision-language understanding with executable robot actions, enabling end-to-end learning for robot contro
arXiv:2607.11295v2 Announce Type: replace Abstract: Biomedical imaging data exhibit substantial acquisition variability, where identical biological structures can appear markedly different due to diff
arXiv:2609.23797v1 Announce Type: cross Abstract: Human motion is shaped by both external acoustic events and behavioral intent: spatial audio conveys environmental cues that elicit or guide a respons
arXiv:2609.24313v1 Announce Type: new Abstract: World models aim to capture environmental dynamics and predict future trajectories, showing growing potential for embodied intelligence. Physics-informe
arXiv:2609.22289v1 Announce Type: new Abstract: Large-scale egocentric and whole-body human demonstrations are becoming a primary source of data for embodied intelligence. They record what people perc
After turning a string of spectacular mathematical results into a reputational crisis, OpenAI is consulting human mathematicians to help it figure out a less disastrous path forward. On Monday, the co
arXiv:2609.24117v1 Announce Type: new Abstract: Identifying linear time-invariant (LTI) dynamical systems is challenging when trajectories are short, noisy, or high-dimensional. Traditional system ide
People outside the AI labs should have a real say in how this technology develops, and a clear way to judge if it's happening safely. Standards should help prevent the concentration of power, includin
arXiv:2609.24919v1 Announce Type: new Abstract: Recent advances in pixel-space diffusion models have narrowed the image quality gap with latent-space diffusion, but still converge more slowly and lag
arXiv:2602.03544v2 Announce Type: replace Abstract: Programming a robot arm requires users to interpret coordinate frames, joint rotations, and trajectories that are not directly visible. Augmented re
arXiv:2609.22123v1 Announce Type: new Abstract: Multi-station multivariate weather forecasting aims to forecast future weather variables at multiple weather stations from historical surface observatio
arXiv:2609.22392v1 Announce Type: new Abstract: Image steganography hides secret message within normal images, with most existing works relying on cover-preserving transmission. However, such a paradi
arXiv:2609.22120v1 Announce Type: cross Abstract: Test-time self-evolving agents improve by reusing past experience, yet sparse-reward trajectories contain failures, loops, and detours, while summarie
arXiv:2609.24322v1 Announce Type: new Abstract: We show that a quantized model that keeps its classification accuracy still changes 14 to 46% of its top-1 retrieval results, and that aggregate ranking
arXiv:2609.23944v1 Announce Type: new Abstract: Vision-language-action (VLA) policies can struggle with manipulation tasks with complex obstacle geometries due to partial observability. These complex
arXiv:2609.24787v1 Announce Type: new Abstract: Forest inventories increasingly rely on artificial intelligence (AI) models to derive forest attributes from large-scale 3D point clouds. Current models
arXiv:2512.07419v3 Announce Type: replace-cross Abstract: Mixed-Precision Quantization (MPQ) liberates Deep Neural Networks (DNNs) from the Out-Of-Memory (OOM) bottleneck and has garnered increasing r
arXiv:2510.24904v2 Announce Type: replace Abstract: Although recent video generative models are getting more capable of following external camera controls, imposed by either text descriptions or camer
arXiv:2609.24048v1 Announce Type: new Abstract: World Action Models (WAMs) have emerged as a promising paradigm for generalizable robot control. Despite the growing number of WAM systems, existing wor
arXiv:2609.21940v1 Announce Type: new Abstract: Long-term memory is essential for large language model (LLM) agents to maintain consistency and personalization over extended interactions. Existing mem
arXiv:2609.21228v1 Announce Type: cross Abstract: Vision-language-action (VLA) models built on pretrained vision-language models have demonstrated strong performance across diverse robotic manipulatio
arXiv:2609.20980v1 Announce Type: new Abstract: Vision-language-action (VLA) models have demonstrated strong capabilities in robotic manipulation, yet their reliance on visual perception limits robust
arXiv:2609.21948v1 Announce Type: cross Abstract: Learning large-scale vision-language-action (VLA) models from multi-embodiment datasets remains challenging due to heterogeneous action spaces across
arXiv:2609.21677v1 Announce Type: new Abstract: Recent advances in large reasoning models (LRMs) have made machine unlearning more challenging, as protected facts or unsafe rationales may surface in i
arXiv:2609.21813v1 Announce Type: cross Abstract: In classification-oriented adaptive sensing, posterior samples characterize uncertainty at the current measurement state and can serve two roles: they
arXiv:2609.20962v1 Announce Type: new Abstract: The proliferation of harmful internet memes poses a significant societal threat, yet their automated classification remains a formidable algorithmic cha
arXiv:2609.21866v1 Announce Type: new Abstract: Wafer map defect recognition is commonly formulated as a fixed-taxonomy classification problem that assigns each wafer to a single defect class. However
arXiv:2609.21664v1 Announce Type: new Abstract: Clustering is a fundamental task in data analysis, typically addressed through centroid-based methods such as K-means. In this work, we present a genera
My dream was literally like watching a tech horror movie. I don't think I've ever woken up before saying 'WTF....' like this before. The AI systems began seizing and corrupting all manner of connected