Knowledge catalogue
arXiv:2606.11740v1 Announce Type: cross Abstract: We study whether grounded reasoning supervision from abundant 2D medical images can improve 3D medical VQA when both input types are aligned through a
Very pleased to hear Anthropic have walked back this policy https://simonwillison.net/2026/Jun/11/anthropic-walks-back-policy/ BREAKING NEWS: Anthropic's latest model will NOT help you if it thinks yo
arXiv:2606.12028v1 Announce Type: new Abstract: Generalizable robot manipulation requires not only task-level reasoning over unseen scenes, but also reliable grounding of visual plans into embodiment-
arXiv:2606.11627v1 Announce Type: cross Abstract: Recent work has shown that on-policy distillation can internalize privileged context, such as system prompts or task hints, into a student model so th
arXiv:2606.11906v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong performance in language-conditioned robotic manipulation, yet their robustness to linguistic varia
arXiv:2606.10782v1 Announce Type: cross Abstract: The adoption and integration of heterogeneous stacks in most of today's open-source based networks brings clear benefits like interoperability and ava
arXiv:2606.10066v1 Announce Type: cross Abstract: Medical vision-language models (VLMs) are evaluated on public benchmarks whose images and question-answer pairs have been freely downloadable for year
arXiv:2606.09967v1 Announce Type: new Abstract: We present ABot-Earth 0.5, a generative 3D framework designed to synthesize vast, seamless 3D environments from ubiquitous, geospatially referenced sate
arXiv:2606.10481v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples. Empirical privac
arXiv:2606.10988v1 Announce Type: new Abstract: While recent advancements in generative AI have substantially accelerated static 3D model creation workflows, the synthesis of category-agnostic 3D anim
arXiv:2602.13807v2 Announce Type: replace Abstract: Time series anomaly detection is critical in many real-world applications, where effective solutions must localize anomalous regions and support rel
As vertically integrated platforms start to dominate they lock out third party access to the most valuable portions of the platform. Of course, Anthropic is has the right to implement whatever policy
arXiv:2602.04935v3 Announce Type: replace-cross Abstract: Adapting LLM agents to domain-specific tool calling remains notably brittle under evolving interfaces. Prompt and schema engineering is easy t
arXiv:2507.19137v2 Announce Type: replace-cross Abstract: Prior research indicates that users prefer assistive technologies whose personalities align with their own. This has sparked interest in autom
arXiv:2606.10716v1 Announce Type: cross Abstract: Pre-trained language models (PLMs) have achieved strong performance in keyphrase extraction (KPE), largely due to their ability to generate rich conte
arXiv:2606.11033v1 Announce Type: cross Abstract: Recent efforts to extend large language models (LLMs) to speech inputs typically rely on cascaded ASR-LLM pipelines, end-to-end speech-language models
arXiv:2606.10135v1 Announce Type: cross Abstract: Transitioning bidirectional video diffusion models into an autoregressive paradigm improves the interactivity of video world models, but existing caus
arXiv:2606.10329v1 Announce Type: cross Abstract: As one of the most destructive natural disasters, earthquakes have struck many countries around the world in recent years, causing serious economic lo
arXiv:2606.09876v1 Announce Type: new Abstract: Large language models often express high confidence in answers that are wrong. Standard calibration remedies typically act globally or at the score leve
arXiv:2509.19936v2 Announce Type: replace Abstract: Human gaze estimation is essential for applications such as human-computer interaction, social robotics, and assistive systems. However, achieving a
arXiv:2606.10607v1 Announce Type: cross Abstract: Causal discovery aims to uncover causal structures from observational data, which is crucial for real-world decision-making. However, different causal
arXiv:2606.11063v1 Announce Type: new Abstract: AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model. This part
Coding agents break when models are 'almost' bug-free. But almost valid JSON is just not the same valid JSON. Fun piece here from @akshay_pachaar shows why SFT can't fix this, and how GRPO trains agai
arXiv:2606.10722v1 Announce Type: new Abstract: We study dense-to-sparse continual training as a way to construct channel-sparse large language models from dense checkpoints. Starting from a Qwen2.5-8
arXiv:2606.10119v1 Announce Type: cross Abstract: Current-status data arise when an event time is observed only through an indicator of whether it occurred before an examination time. This paper studi
arXiv:2606.10842v1 Announce Type: new Abstract: We describe ConvMemory v2, an opt-in token-evidence reranker that sits after the lightweight ConvMemory v1 reranker and reorders only v1's protected top
arXiv:2606.09953v1 Announce Type: cross Abstract: Head computed tomography (CT) typically uses sub-millimeter in-plane resolution but 2-5 mm through-plane spacing, creating substantial anisotropy that
arXiv:2606.11019v1 Announce Type: cross Abstract: Learning-based motion planners, despite recent progress, often suffer from temporal inconsistency. Small perturbations across frames can accumulate in
DiffusionGemma is an experimental open model from Google DeepMind that uses text diffusion for exceptionally fast generation, moving beyond sequential token-by-token processing to generate entire bloc
arXiv:2606.10395v1 Announce Type: new Abstract: The recent receptance weighted key value (RWKV) model combines RNN-style recurrence, offering a linear-complexity alternative to Transformers' quadratic
arXiv:2606.10656v1 Announce Type: new Abstract: Forecasting the future evolution of dynamic scenes is crucial in autonomous driving. However, existing feed-forward paradigms are primarily designed for
arXiv:2606.11106v1 Announce Type: cross Abstract: A global shortage of trained sonographers limits prenatal ultrasound screening in low- and middle-income countries, where over half of pregnant women
arXiv:2606.10219v1 Announce Type: cross Abstract: AI efficiency at scale is becoming critical in finance as market data volumes surge across equities, ETFs, FX, options, and high-frequency trading str
arXiv:2606.10167v1 Announce Type: new Abstract: Recent learning-based path planners use neural networks to process visual map representations and approximate heuristics for classical search algorithms
arXiv:2606.09928v1 Announce Type: cross Abstract: The Forward-Forward (FF) algorithm offers a biologically inspired alternative to backpropagation by replacing gradient-based credit assignment with lo
arXiv:2606.10147v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) can listen and see, but how do audio and visual signals actually travel through the network to shape an answer?
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:2606.11023v1 Announce Type: cross Abstract: Sequential recommendation aims to predict users' next interaction with items by analyzing their historical behavior. However, the limited quality of i
arXiv:2602.07413v3 Announce Type: replace Abstract: Contemporary visuo-motor dexterity models often rely on expressive policy classes with diffusion and transformer backbones to achieve strong perform
The Keyword: Google introduces DiffusionGemma, an experimental 26B-parameter open model that uses text diffusion for faster text generation compared to autoregressive models — Our newest open experime
arXiv:2606.09951v1 Announce Type: new Abstract: During the training of large Transformer models, attention masks regulate the scope and direction of information flow across a sequence. Numerous mask v
arXiv:2606.10276v1 Announce Type: cross Abstract: For natural human-robot interaction, a robot must understand human intent expressed not only through language but also through nonverbal signals such
arXiv:2606.10363v1 Announce Type: new Abstract: World Action Models (WAMs) have emerged as a new powerful paradigm for embodied intelligence, learning action-relevant visual dynamics that significantl
This article recaps presentations from Ray Day NYC featuring case studies from Discord, Cubist, and Coinbase on scaling AI workloads using the Ray distributed computing framework, with a focus on Torc
arXiv:2606.09848v1 Announce Type: cross Abstract: As generative and agentic AI becomes embedded in everyday products, practitioners face a persistent challenge: how to design human-AI coordination --
arXiv:2606.09960v1 Announce Type: cross Abstract: We present HydraCIL, a decoupled continual learning model based on prototype-guided multi-head classifiers, targeting sustainable deployment in embedd
arXiv:2510.04491v3 Announce Type: replace Abstract: Despite rapid progress in building conversational AI agents, robustness is still largely untested. Small shifts in user behavior, such as being more
In good faith and with no judgment (mistakes happen), I truly hope that Anthropic will hear the feedback and change course on this. Anthropic is a company that has been raising awareness about AI mani
arXiv:2606.10677v1 Announce Type: new Abstract: Long-term LLM agents need persistent memory that can track changing facts and provide relevant evidence across sessions. Existing memory systems often s
arXiv:2606.10046v1 Announce Type: cross Abstract: Flow-matching transformers achieve strong audio separation, yet their attention dynamics are opaque. We adapt established causal-intervention principl
arXiv:2606.09842v1 Announce Type: cross Abstract: Applying Human Pose Estimation (HPE) in real world environments remains a challenging task, this paper explores and surveys real time HPE approaches a
arXiv:2606.11156v1 Announce Type: cross Abstract: Recent one-step generative models accelerate sampling by learning deterministic flow maps of the underlying dynamics. These methods rely on learning f
arXiv:2606.09964v1 Announce Type: cross Abstract: The NISQ era places stringent constraints on quantum computation, where noise and decoherence fundamentally limit performance. In classical deep learn
arXiv:2606.10358v1 Announce Type: cross Abstract: Learning Bayesian network (BN) structure from sparse discrete data is hard: when each instance records only a few variables, most variable pairs lack
arXiv:2606.10651v1 Announce Type: new Abstract: We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding
arXiv:2606.10209v1 Announce Type: new Abstract: Large language models deployed as autonomous agents for enterprise workflows face a key challenge: verbose tool responses from enterprise systems can ca
arXiv:2507.17188v2 Announce Type: replace-cross Abstract: This paper investigates secure communications in rate-splitting multiple access (RSMA) enabled heterogeneous UAV networks, where multiple UAVs
arXiv:2606.10294v1 Announce Type: cross Abstract: Deploying neural networks on unconventional hardware demands architectures that co-optimize task accuracy and platform-specific constraints such as en
arXiv:2606.10173v1 Announce Type: cross Abstract: As AI systems move into operating systems, privacy no longer turns only on whether a model runs locally. A local assistant may assemble email, calenda
arXiv:2509.24710v2 Announce Type: replace-cross Abstract: Score-based diffusion models are a highly effective method for generating samples from a distribution of images. We consider scenarios where t