Knowledge catalogue
arXiv:2606.12396v1 Announce Type: new Abstract: Vision-language-action (VLA) models can describe scenes and reason about them in language, yet still struggle to ground their actions in the dense 3D wo
arXiv:2606.12263v1 Announce Type: new Abstract: While Latent Diffusion Models (LDMs) have revolutionized visual synthesis, they are increasingly exploited for unauthorized mimicry of individuals. Exis
arXiv:2606.10777v1 Announce Type: new Abstract: Uncertainty estimation is critical for deploying machine learning models in high-stakes settings. However, classical calibration only assesses the relia
Dario Amodei / @darioamodei: Dario Amodei says frontier models should face mandatory third-party testing for cyber, bio, and autonomy risks, in addition to overall transparency requirements — In addit
arXiv:2606.10612v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) is a powerful technique for creating high-fidelity 3D assets. However, the widespread sharing and iterative modification of
arXiv:2606.10669v1 Announce Type: cross Abstract: Concept-based models (CMs), deep neural networks that ground their predictions on representations aligned with human-understandable concepts (e.g., 'r
arXiv:2606.10642v1 Announce Type: new Abstract: Machine learning weather prediction (MLWP) models have achieved impressive forecasting performance at a small fraction of the computational costs requir
arXiv:2510.14836v3 Announce Type: replace Abstract: Spatial perception and reasoning are crucial for Vision-Language-Action (VLA) models to accomplish fine-grained manipulation tasks. However, existin
arXiv:2606.07714v1 Announce Type: cross Abstract: Suicide ideation detection models are typically evaluated using aggregate performance metrics, yet little is known about how they internally represent
arXiv:2606.09794v1 Announce Type: new Abstract: View-dependent appearance modeling remains a challenging problem in novel-view synthesis and reconstruction. Accurately representing complex angular eff
arXiv:2606.07522v1 Announce Type: cross Abstract: We propose an unsupervised method of resolving slang, unique entities, and folklore from online communities by isolating words in the lexicon that hav
arXiv:2606.09331v1 Announce Type: cross Abstract: Omni-modal retrieval promises a single embedding space for text, image, video, document, and audio inputs, but building such a unified retriever is di
arXiv:2507.22876v2 Announce Type: replace Abstract: The Satisfiability problem (SAT) is fundamental in computational complexity theory and has a wide range of industrial applications. Optimizing moder
arXiv:2606.07571v1 Announce Type: cross Abstract: Key-value (KV) caching for shared prefixes is essential for high-throughput large language model (LLM) serving, but it faces critical challenges in em
arXiv:2409.15723v3 Announce Type: replace Abstract: Large Language Models have achieved impressive performance across diverse applications, yet their training typically depends on centralized data col
arXiv:2606.09828v1 Announce Type: new Abstract: Video world models that maintain 3D spatial consistency across generated frames typically rely on explicit point cloud memory constructed in RGB space.
arXiv:2606.09215v1 Announce Type: new Abstract: World Action Models (WAMs) couple a video dynamics prior to the policy and have shown encouraging results on tabletop manipulation, but iterative denois
arXiv:2606.07660v1 Announce Type: new Abstract: Adapting foundation models to detect generative artifacts via gradient-based updates compromises their intrinsic representations. Under optimization on
arXiv:2606.09312v1 Announce Type: new Abstract: Tensor program optimization is essential for modern machine learning systems, but its search space is enormous. Existing auto-schedulers reduce measurem
arXiv:2606.08306v1 Announce Type: new Abstract: Network dynamics - including spreading, influence maximisation, and epidemic modelling - remain largely confined to the transductive paradigm, where mod
arXiv:2606.08094v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies are typically shipped as Python/PyTorch stacks that assume a workstation-class GPU, a mismatch for the hardware
arXiv:2605.25806v2 Announce Type: replace Abstract: Women's safety and security are paramount for a modern society. Crimes against women occur in daylight as well as in low-light conditions. Often, su
arXiv:2606.07303v1 Announce Type: new Abstract: Representation learning is central to modern machine learning, enabling transitions from handcrafted features to learned embeddings, latent spaces, foun
arXiv:2601.22574v2 Announce Type: replace-cross Abstract: Although Video Large Multimodal Models have achieved strong performance in video understanding, they still suffer from hallucination. Existing
arXiv:2606.06635v1 Announce Type: cross Abstract: Failures in language model reasoning emerge through distinct processes that leave identifiable signatures in the reasoning trace. We characterize thes
Our next generation of Apple Intelligence is centered around our users, integrated deeply into our operating systems, and powered by a bold new architecture with privacy at its core. At the heart of t
arXiv:2510.11014v2 Announce Type: replace-cross Abstract: Autonomous robots often view rooms only partially, through a doorway, where the walls and scene structure hide the geometry and task-relevant
arXiv:2505.10892v2 Announce Type: replace Abstract: Post-training LLMs with RLHF and preference optimization methods (e.g., DPO, IPO) has greatly improved alignment, yet these approaches assume a sing
Narrative violation: according to @Stanford research, local models can answer 71.3% of real-world chat and reasoning queries accurately, up from 23.2% in 2023. Obviously at a fraction of the cost and
arXiv:2606.07030v1 Announce Type: cross Abstract: We analyse error patterns of raw waveform acoustic models on TIMIT phone recognition beyond the overall phone error rate (PER). PER is decomposed acro
arXiv:2606.06556v1 Announce Type: new Abstract: Generalist robot intelligence is often framed as a policy-scaling problem: collect more robot demonstrations, train larger Vision-Language-Action (VLA)
arXiv:2606.06834v1 Announce Type: new Abstract: High-grade gliomas integrate into neural circuits through functional synapses with neurons, raising the question of which noncoding elements shape synap
arXiv:2602.03160v2 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with the diverse spectrum of human values remains a central challenge: preference-based methods often fail to
arXiv:2606.06475v1 Announce Type: cross Abstract: Recent advancements in reasoning language models have been driven by Reinforcement Learning (RL) fine-tuning. Most often, these rely on the Group Rela
arXiv:2508.10875v3 Announce Type: replace Abstract: Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By gener
arXiv:2606.05758v1 Announce Type: new Abstract: Many modern vision-language models (VLMs) build on autoregressive decoding of discrete tokens. While text-based output interfaces enable scalable pretra
arXiv:2606.05737v1 Announce Type: new Abstract: Diffusion-based vision-language-action (VLA) models often inherit the image-generation view: actions are generated by iterative denoising. We argue that
arXiv:2606.06014v1 Announce Type: cross Abstract: Latent world models (LWMs) have strengthened end-to-end autonomous driving by forecasting compact scene dynamics for downstream planning. However, exi
arXiv:2606.06474v1 Announce Type: new Abstract: Discrete diffusion language models generate text by iteratively denoising an entire response in parallel. At each step, they predict tentative tokens fo
arXiv:2606.04164v1 Announce Type: cross Abstract: Data samples used for training often differ from those encountered during fine-tuning and deployment, and while ML models show promise, their performa
arXiv:2603.03482v2 Announce Type: replace-cross Abstract: Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities. However, e
arXiv:2506.06006v3 Announce Type: replace-cross Abstract: Can unified vision-language models (VLMs) perform forward dynamics prediction (FDP), i.e., predicting the future state (in image form) given t
arXiv:2606.04486v1 Announce Type: cross Abstract: Watermarking methods for language models have been studied extensively in the autoregressive setting, where tokens are generated sequentially. These w
arXiv:2601.21868v2 Announce Type: replace-cross Abstract: Understanding the stability and long-time behavior of generative models is a fundamental problem in modern machine learning. This paper provid
arXiv:2512.14099v3 Announce Type: replace Abstract: Motivated by discrete diffusion's success in language-vision modeling, we explore its potential for multi-view generation, a task dominated by conti
we're taking an early bet on open models specifically, because they're SO much cheaper one point of reference: an app outputting 10M tokens/day costs roughly 250/day on Opus 4.8 versus ~24/day for Min
arXiv:2407.05312v2 Announce Type: replace Abstract: Diffusion models have demonstrated impressive image generation capabilities. Personalized approaches, such as textual inversion and Dreambooth, enha
arXiv:2604.06052v2 Announce Type: replace Abstract: Text-to-image diffusion models exhibit remarkable generative capabilities, yet their internal operations remain opaque, particularly when handling p
arXiv:2606.02947v1 Announce Type: cross Abstract: Supervised fine-tuning is the predominant approach for adapting autoregressive vision-language models to downstream tasks. Recent work has shown that
arXiv:2506.03087v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) have become essential tools for analyzing graph-structured data in domains such as drug discovery and financial a
arXiv:2606.03307v1 Announce Type: cross Abstract: Graph foundation models (GFMs) emerged as a dominant paradigm in graph representation learning by leveraging large-scale pre-training for cross-domain
arXiv:2606.03188v1 Announce Type: new Abstract: Recent World Action Models (WAMs) have demonstrated impressive capabilities in embodied decision-making. However, whether their effectiveness stems from
arXiv:2606.03119v1 Announce Type: cross Abstract: Guidance methods, such as classifier-free guidance (CFG) and auto-guidance (AG), have advanced noise-to-data generation in diffusion models. Recently,
arXiv:2512.10999v3 Announce Type: replace Abstract: Knowledge Base Question Answering (KBQA) challenges models to bridge the gap between natural language and strict knowledge graph schemas by generati
arXiv:2606.03982v1 Announce Type: new Abstract: Quantities with measurement units, such as 110 cm and 1.2 m, require language models (LMs) to combine a numeral with a symbolic unit scale. Here, we stu
arXiv:2606.03979v1 Announce Type: cross Abstract: The past few decades have witnessed significant advances in the design of machine learning algorithms, from early studies on task-specific shallow mod
arXiv:2602.03681v2 Announce Type: replace Abstract: The quadratic computational complexity of softmax transformers has become a bottleneck in long-context scenarios. In contrast, linear attention mode
arXiv:2606.03986v1 Announce Type: new Abstract: Previous work has evaluated physics reasoning in foundation models using synthetic or semi-synthetic scenes and visual question-answering tasks. However
arXiv:2606.03556v1 Announce Type: new Abstract: Vision-language-action (VLA) models are gaining attention in robotics, yet their robustness to adversarial attacks remains largely unexplored. Existing
arXiv:2606.03075v1 Announce Type: new Abstract: Vision-Language Models (VLMs) inherit the auto-regressive generation paradigm and cache the keys and values (KV) of all previous tokens to accelerate in