Knowledge catalogue
arXiv:2604.16883v1 Announce Type: new Abstract: In long-context decoding for LLMs and LMMs, attention becomes increasingly memory-bound because each decoding step must load a large amount of KV-cache
arXiv:2604.04804v2 Announce Type: replace Abstract: Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficie
arXiv:2603.13740v3 Announce Type: replace Abstract: We introduce Sky2Ground, a three-view dataset designed for varying altitude camera localization, correspondence learning, and reconstruction. The da
ChatGPT's updated image generation capabilities (Images 2.0) can now create visual content in presentation formats, including slides and infographics, as demonstrated by user @yuguang_yang. This enhan
arXiv:2604.17627v1 Announce Type: new Abstract: Serving large language models under latency service-level objectives (SLOs) is a configuration-heavy systems problem with an unusually failure-prone sea
arXiv:2411.09593v2 Announce Type: replace-cross Abstract: The human brain receives nutrients and oxygen through an intricate network of blood vessels. Pathology affecting small vessels, at the mesosco
arXiv:2604.16517v1 Announce Type: cross Abstract: Large vision-language models (VLMs) achieve strong performance on multimodal tasks but often suffer from hallucination and poor grounding in knowledge
Snowflake Inc. is expanding its push into enterprise artificial intelligence with a set of updates to its Snowflake Intelligence and Cortex Code offerings, positioning its platform as a centralized co
This post presents survey or observational data about user preferences for AI interaction modes, showing that approximately 70% of users prioritize speed, 22% prefer accuracy over speed, and 8% use vo
So the EU wants to ban teens from social media — except for LGBTQ+ content? What a nuanced way to “protect children” online. 🚨 BREAKING: Hungary violated EU law when it banned children from accessing
arXiv:2505.13660v2 Announce Type: replace-cross Abstract: This paper introduces a new constraint-free concave dual formulation for the Wasserstein barycenter. Tailoring the vanilla dual gradient ascen
arXiv:2604.18135v1 Announce Type: new Abstract: Large-scale dataset distillation requires storing auxiliary soft labels that can be 30-40x larger on ImageNet-1K and 200x larger on ImageNet-21K than th
arXiv:2604.18058v1 Announce Type: new Abstract: We introduce Sonata, a compact latent world model for six-axis trunk IMU representation learning under clinical data scarcity. Clinical cohorts typicall
Rachel Metz / Bloomberg: Source: a handful of unauthorized users in a private Discord channel have been accessing Anthropic's Mythos model since the day the company announced it — A small group of una
arXiv:2604.17748v1 Announce Type: new Abstract: Source-Free Domain Adaptation (SFDA) seeks to adapt a source model, which is pre-trained on a supervised source domain, for a target domain, with only a
Sam Sabin / Axios: Sources: CISA doesn't have access to Mythos Preview, even as some other government agencies use it; Anthropic says it briefed CISA before Mythos' unveiling — The Cybersecurity and I
Yueqi Yang / The Information: Sources: Kalshi plans to offer crypto trading in the US, offering perpetual futures, putting it in competition with exchanges like Coinbase — Prediction market Kalshi pla
arXiv:2604.17888v1 Announce Type: new Abstract: Generalizable grasping with high-degree-of-freedom (DoF) dexterous hands remains challenging in tiered workspaces, where occlusion, narrow clearances, a
With an IPO looming for Elon Musk's SpaceX / xAI / X combo platter of companies, SpaceX has announced an odd arrangement to either acquire the automated programming platform Cursor for 60 billion or p
New York Times: SpaceX says it's working with Cursor to build “the world's most useful models” and it has the right to acquire Cursor for 60B or pay 10B for the partnership — The potential acquisition
SpaceXAI and @cursor_ai are now working closely together to create the world’s best coding and knowledge work AI. The combination of Cursor’s leading product and distribution to expert software engine
arXiv:2406.06543v2 Announce Type: replace-cross Abstract: Deep learning has driven significant technological advancements, but its high energy consumption limits its use on battery-operated edge devic
arXiv:2604.16429v1 Announce Type: cross Abstract: We introduce Mosaic, a probabilistic weather forecasting model that addresses two principal sources of spectral degradation in ML-based weather predic
arXiv:2506.18141v3 Announce Type: replace Abstract: We identify semantically coherent, context-consistent network components in large language models (LLMs) using coactivation of sparse autoencoder (S
arXiv:2604.17350v1 Announce Type: cross Abstract: Time series forecasting is traditionally dominated by sequence-based architectures such as recurrent neural networks and attention mechanisms, which p
arXiv:2601.21159v2 Announce Type: replace Abstract: High-resolution remote sensing images contain densely distributed objects with pronounced scale variations and complex boundaries, which impose high
arXiv:2604.17385v1 Announce Type: new Abstract: Spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, remains a core challenge fo
arXiv:2603.27437v2 Announce Type: replace Abstract: Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This
arXiv:2604.17873v1 Announce Type: new Abstract: Video Large Language Models (Vid-LLMs) have demonstrated remarkable performance in video understanding tasks, yet their robustness under conversational
arXiv:2601.04029v2 Announce Type: replace Abstract: Large Audio-Language Models (LALMs) as judges have emerged as a prominent approach for evaluating speech generation quality, yet their ability to as
arXiv:2601.06498v2 Announce Type: replace Abstract: Due to the limited generalization and interpretability of deep learning classifiers, The final vetting of rare celestial object candidates still rel
arXiv:2604.18420v1 Announce Type: cross Abstract: Smooth functions on graphs have wide applications in manifold and semi-supervised learning. In this paper, we study a bandit problem where the payoffs
arXiv:2604.17287v1 Announce Type: new Abstract: Copy-move forgery, where a region within an image is duplicated to hide or fabricate content, remains a persistent threat to visual media integrity. We
arXiv:2604.17397v1 Announce Type: new Abstract: Autoregressive video diffusion is emerging as a promising paradigm for streaming video synthesis, with step distillation serving as the primary means of
arXiv:2509.24328v2 Announce Type: replace Abstract: LLMs have low GPU efficiency and high latency due to autoregressive decoding. Speculative decoding (SD) mitigates this using a small draft model to
arXiv:2601.04638v2 Announce Type: replace Abstract: Medical consultations are intrinsically speech-centric. However, most prior works focus on long-text-based interactions, which are cumbersome and pa
arXiv:2604.17771v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance on natural language to SQL (NL2SQL) benchmarks, yet their reported accuracy may be inflate
arXiv:2512.21204v2 Announce Type: replace Abstract: Human infants, with only a few hundred hours of speech exposure, acquire basic units of new languages, highlighting a striking efficiency gap compar
arXiv:2604.18284v1 Announce Type: new Abstract: Pre-trained vision models have found widespread application across diverse domains. Prompt tuning-based methods have emerged as a parameter-efficient pa
arXiv:2602.11698v2 Announce Type: replace Abstract: Recursive (looped) Transformers decouple computational depth from parameter depth by repeatedly applying shared layers, providing an explicit archit
arXiv:2511.08983v2 Announce Type: replace Abstract: Recent advances in large reasoning models have been driven by reinforcement learning and test-time scaling, accompanied by growing interest in laten
arXiv:2511.05152v2 Announce Type: replace Abstract: Deformable Gaussian Splatting (GS) accomplishes photorealistic dynamic 3-D reconstruction from dense multi-view video (MVV) by learning to deform a
SPLC funded a large number of false flag “right wing” organizations and events. Total scam. 🚨BREAKING: DOJ charges the Southern Poverty Law Center (SPLC) with wire fraud, false statements, and conspir
arXiv:2511.11391v3 Announce Type: replace Abstract: Phase-time arrays, which integrate phase shifters (PSs) and true-time delays (TTDs), have emerged as a cost-effective architecture for generating fr
arXiv:2604.16607v1 Announce Type: new Abstract: With the rise of generative language models, machine-generated text detection has become a critical challenge. A wide variety of models is available, bu
arXiv:2604.16995v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a promising paradigm for training reasoning-oriented models by leveraging rule-based reward signals. However,
arXiv:2604.16511v1 Announce Type: cross Abstract: We present SQL Query Engine, an open-source, self-hosted service that translates natural language questions into validated PostgreSQL queries through
arXiv:2604.17880v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have achieved great success on general robotic tasks, but still face challenges in fine-grained spatiotemporal man
arXiv:2604.17068v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) enable parallel text generation by iteratively denoising a fully masked sequence, unmasking a subset of masked t
arXiv:2601.04052v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have demonstrated impressive capabilities in generalized robotic control; however, they remain notoriously
arXiv:2601.07155v2 Announce Type: replace Abstract: Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from large language models to smaller student models; however,
arXiv:2604.17887v1 Announce Type: new Abstract: Inverse Dynamics Models (IDMs) map visual observations to low-level action commands, serving as central components for data labeling and policy executio
arXiv:2506.08013v2 Announce Type: replace Abstract: Multi-task learning for dense prediction is limited by the need for extensive annotation for every task, though recent works have explored training
arXiv:2604.18177v1 Announce Type: new Abstract: Benchmarks are often used as a standard to understand LLM capabilities in different domains. However, aggregate benchmark scores provide limited insight
arXiv:2604.16774v1 Announce Type: new Abstract: Long-horizon language model systems increasingly rely on persistent memory, yet many current designs still treat memory primarily as a static store: wri
arXiv:2601.04740v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly applied in specialized domains such as finance and healthcare, where they introduce unique safety risk
arXiv:2604.17611v1 Announce Type: new Abstract: Parkinson's disease (PD) is a progressive disorder in which symptom burden and functional impairment evolve over time, making severity staging essential
arXiv:2604.18401v1 Announce Type: new Abstract: General agents have given rise to phenomenal applications such as OpenClaw and Claude Code. As these agent systems (a.k.a. Harnesses) strive for bolder
arXiv:2604.17358v1 Announce Type: new Abstract: While recent Spoken Language Models (SLMs) have been actively deployed in real-world scenarios, they lack the capability to discern Third-Party Interrup
arXiv:2509.10692v3 Announce Type: replace Abstract: This paper presents a motion planning and risk analysis framework for enhancing human-robot collaboration with a Multi-Rotor Aerial Vehicle. The pro