Knowledge catalogue
arXiv:2510.15047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call explorat
arXiv:2609.08162v1 Announce Type: new Abstract: How can vision-language-action (VLA) models adapt to new environments where world dynamics shift? While recent research has combined world modeling and
arXiv:2609.06261v1 Announce Type: new Abstract: Vision foundation models trained on Internet-scale RGB datasets enable remarkable capabilities across a range of tasks, from text-to-video generation to
Anyone still denying the risks posed by unregulated AI should read this thread. It’s time to pump the brakes & take action NOW. We need: - Mandatory safeguards - A comprehensive testing regime - Urgen
arXiv:2609.05461v1 Announce Type: cross Abstract: Reward-free latent world models plan by scoring candidate actions with distances in a frozen latent space: an action is preferred if its predicted fut
arXiv:2609.07884v1 Announce Type: new Abstract: Recent work, such as Vision Banana, shows that lightweight instruction tuning can enable an image generator to achieve state-of-the-art performance acro
arXiv:2609.06656v1 Announce Type: new Abstract: Modern power systems are growing increasingly complex as they integrate diverse generation sources to meet rising demand, making accurate load forecasti
arXiv:2609.07012v1 Announce Type: cross Abstract: Pushbroom satellite imaging couples limited spatial resolution with platform attitude instability. Platform jitter produces spatially varying motion b
arXiv:2609.06726v1 Announce Type: new Abstract: We present B2TFPose, a training-free zero-shot method for 6DoF pose estimation of unseen objects from RGB images. Using a single frozen DINOv3 vision tr
arXiv:2609.06353v1 Announce Type: new Abstract: Understanding collaborative behavior in children is important for analyzing social participation, peer interaction, shared attention, and engagement dur
arXiv:2504.15928v3 Announce Type: replace Abstract: Artificial intelligence (AI) shows remarkable potential in medical imaging diagnostics, yet most current models require retraining when applied acro
arXiv:2609.07753v1 Announce Type: new Abstract: Synthetic Aperture Radar (SAR) is an important modality in a wide range of imaging applications due to its versatile, long range and near all weather op
arXiv:2609.08730v1 Announce Type: new Abstract: While 3D Gaussian Splatting (3DGS) has emerged as a powerful representation for real-time novel view synthesis, rendering high-fidelity scenes often rel
arXiv:2609.06820v1 Announce Type: cross Abstract: Active mapping requires a robot to select camera viewpoints that efficiently reconstruct an unknown 3D scene. To reason about unobserved regions, rece
arXiv:2609.06055v1 Announce Type: new Abstract: Most end-to-end autonomous-driving systems learn by imitating human driving logs, leaving their learned behavior constrained by the quality and behavior
arXiv:2609.06779v1 Announce Type: new Abstract: Drug repurposing aims to identify new therapeutic uses for existing compounds and, compared with de novo drug discovery, offers a faster and more cost-e
arXiv:2609.08850v1 Announce Type: new Abstract: Text-guided Video Temporal Grounding (VTG) aims to localize the relevant segments in an untrimmed video based on text queries, yet collecting dense temp
arXiv:2609.08855v1 Announce Type: new Abstract: Machine learning emulators have become essential for accelerating expensive Earth-system simulations, but most existing approaches remain passive foreca
arXiv:2505.20961v2 Announce Type: replace-cross Abstract: Sound source localization (SSL) is a critical technology for determining the position of sound sources in complex environments. However, exist
arXiv:2609.07145v1 Announce Type: new Abstract: Planning six-degree-of-freedom (6-DoF) grasps for unseen objects in cluttered tabletop scenes from a single-view depth image requires accurate and effic
arXiv:2609.07137v1 Announce Type: new Abstract: Recent image-to-3D generation models built on flow-matching diffusion Transformers (DiT) can produce high-fidelity meshes, yet their post-training strat
arXiv:2609.07853v1 Announce Type: new Abstract: Semantic and goal-oriented communication is increasingly studied for 6G, but generalization beyond seen data remains a key weakness under tight rate bud
arXiv:2609.06208v1 Announce Type: new Abstract: Understanding human attention is fundamental for scene interpretation, yet existing approaches often rely on heavily trained models that lack interpreta
arXiv:2609.06823v1 Announce Type: new Abstract: The next generation of artificial intelligence systems will likely be natively temporal and multimodal in both inputs and outputs: able to converse, per
arXiv:2512.15560v3 Announce Type: replace Abstract: The text encoder is a critical component of text-to-image and text-to-video diffusion models, fundamentally determining the semantic fidelity of the
arXiv:2609.07670v1 Announce Type: new Abstract: The growing realism and accessibility of manipulated and generated faces threaten the trustworthiness of digital media. To detect such forgeries, deepfa
arXiv:2609.06557v1 Announce Type: new Abstract: Large language models (LLMs) are often considered fragile under aggressive sparsification, and maintaining reliable performance typically requires stick
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 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:2609.06051v1 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: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:2609.05523v1 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:2609.07915v1 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:2609.07816v1 Announce Type: new Abstract: Linear attention is increasingly used in frontier language models for efficient long-context inference and constant-memory decoding. Its fixed-size recu
arXiv:2604.05819v2 Announce Type: replace Abstract: Interpreting the decisions of complex computer vision models is crucial to establish trust and accountability, especially in safety-critical domains
arXiv:2609.05559v1 Announce Type: cross Abstract: We introduce autonomous, intent-preserving Design for Manufacturing (DFM) redesign of CAD parts: given an engineer's CAD model, the method returns a v
arXiv:2609.07876v1 Announce Type: cross Abstract: Recent methods in language model interpretability employ techniques such as sparse autoencoders to decompose residual stream contributions into linear
arXiv:2609.08084v1 Announce Type: new Abstract: Monocular depth estimation is a ubiquitous yet highly ill-posed computer vision task, with downstream applications in scene reconstruction, computationa
arXiv:2609.06874v1 Announce Type: cross Abstract: High-resolution volumetric medical imaging is critical for clinical diagnosis, yet acquisition is often limited by scanner hardware, scan time, and fo
A few posts tagged with 'new model' present models that are finetunes. My opinion : I'd rather have the 'new model' tag reserved for new 'major' releases, like a new Qwen model, Deepseek V4 -> Deepsee
arXiv:2609.08059v1 Announce Type: cross Abstract: Acidophilic proteins that remain stable and functional under highly acidic conditions, are important for industrial biocatalysis, acid-related bioproc
arXiv:2609.06602v1 Announce Type: new Abstract: In recent years, diffusion stochastic differential equation (SDE) inversion and inversion-free methods have become prevalent for training-free image edi
arXiv:2609.08683v1 Announce Type: new Abstract: Adversarial robustness in computer vision is still largely achieved through adversarial training or test-time adversarial purification, both of which in
arXiv:2609.05727v1 Announce Type: new Abstract: We develop Newton Matching, a unified framework for fine-tuning and sampling in generative modeling. The target is piproptomu e^{au r}, where r is the r
arXiv:2609.06288v1 Announce Type: new Abstract: Training-free image editing steers diffusion or flow-matching generative models at inference time by modifying prompt-conditioned denoising velocities.
arXiv:2602.00110v2 Announce Type: replace Abstract: Visual transformers have driven major progress in remote sensing image analysis, particularly in object detection and segmentation. Recent vision-la
arXiv:2609.06338v1 Announce Type: new Abstract: Accelerated MRI reconstruction recovers images from undersampled k-space. However, different acceleration factors produce distinct artifact patterns. Ex
arXiv:2609.06490v1 Announce Type: new Abstract: Recursive Super-Resolution (SR) extends fixed-scale SR to extreme magnification by repeatedly feeding predictions back into the same model, analogous to
arXiv:2609.06080v1 Announce Type: new Abstract: Deeply phenotyped cohorts combine clinical, imaging, molecular, and wearable observations across timescales from seconds to years. This breadth can reve
arXiv:2609.06436v1 Announce Type: new Abstract: High-resolution 3D asset generation is vital in various 3D applications. Existing state-of-the-art diffusion-based models remain constrained by fixed re
read the whole thread. although i don’t 100% agree with certain bits it is compelling and informed from the inside perspective that definitely deserves to be heard. I resigned from Anthropic today. I
arXiv:2609.06685v1 Announce Type: cross Abstract: We derive an exact gradient-step representation of the RoPE-softmax forward pass. For every deterministic RoPE-softmax attention head with arbitrary a
arXiv:2609.08496v1 Announce Type: new Abstract: Sign language video generation demands precise hand and facial articulation, yet modern video diffusion models, trained predominantly on spoken-language
arXiv:2609.05533v1 Announce Type: new Abstract: Long-horizon manipulation is partially observable: the information needed to choose the next action may appear only in observations from minutes earlier
arXiv:2609.09143v1 Announce Type: new Abstract: Image tokenizers define the ``visual language'' of unified multimodal models, yet are commonly studied through isolated metrics or generation-/understan
arXiv:2609.06651v1 Announce Type: new Abstract: Diffusion models have general generative abilities but struggle to align with specific objectives. Fine-tuning can improve alignment, yet its training c
arXiv:2609.08505v1 Announce Type: new Abstract: Reliable video generation requires more than high-quality frames to form a coherent story: a model must maintain a persistent state, transporting visual
arXiv:2609.06668v1 Announce Type: new Abstract: Multimodal graphs couple node attributes in different modalities, such as text and images, with relational structure, enabling topological structure and
arXiv:2609.09054v1 Announce Type: new Abstract: Task vectors enable post-training model editing by identifying semantically meaningful directions in weight space, typically computed as the difference
arXiv:2609.08981v1 Announce Type: new Abstract: A growing body of work establishes that large language models are not mere statistical memorizers, but are capable of in-context learning: performing in