Knowledge catalogue
arXiv:2605.20408v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) effectively aligns Large Language Models (LLMs) with aggregate human preferences but often fails to ad
arXiv:2605.20296v1 Announce Type: new Abstract: Fine-tuning a language model for a target task routinely degrades capabilities the training data never explicitly threatened. We study this phenomenon,
arXiv:2605.21075v1 Announce Type: new Abstract: Earth observation (EO) foundation models (FMs) are increasingly trained on multisensor data, spanning multispectral imagery (MSI), synthetic aperture ra
Spent Tuesday watching @Google I/O thinking about a question. If you build on @Android, what just changed for you? Short answer: your screen belongs to Gemini now. After this week, Google owns the AI,
arXiv:2501.15151v5 Announce Type: replace Abstract: Spiking Neural Networks (SNNs) are the third generation of neural networks. They have gained widespread attention in object detection due to their l
arXiv:2605.20760v1 Announce Type: new Abstract: Automated segmentation of the vertebral column in Computed Tomography (CT) scans is a prerequisite for pathological assessment and surgical planning. Ho
Jem Aswad / Variety: Spotify and UMG plan to let Premium users create AI covers and remixes using music from participating UMG artists as a paid add-on, without giving a launch date — Spotify and Univ
Samantha Subin / CNBC: Spotify closes up 13% after announcing new features and 2030 guidance, forecasting a compound annual growth rate in the mid-teens and gross margins of 35%-40% — Spotify shares j
Spotify and Universal Music Group (UMG) just announced a licensing deal that will allow users to prompt the creation of AI-generated remixes and covers for streaming songs. The tool will be a paid add
Ivan Mehta / TechCrunch: Spotify Labs launches Studio, a NotebookLM-like desktop app to generate private, AI-powered podcasts, in research preview across 20+ markets — One of the common features for c
Ethan Millman / The Hollywood Reporter: Spotify partners with Live Nation to launch Reserved, a new feature that sets aside tickets for the most dedicated fans, starting with Premium users in the US —
Ivan Mehta / TechCrunch: Spotify says it has 1M+ subscriptions to Audiobook+, which is on track for $100M in ARR, and unveils an ElevenLabs-powered audiobook self-publishing tool — Alongside tools for
Studio by Spotify Labs is a new standalone AI app that generates a daily briefing, podcasts, and playlists on your PC using chatbot prompts. The AI-generated content draws from your Spotify listening
arXiv:2605.21244v1 Announce Type: new Abstract: Super-Resolution (SR) has advanced rapidly in recent years, with diffusion-based models achieving unprecedented fidelity at the cost of introducing new
Stable Audio 3.0 is now Day-0 supported in ComfyUI. Open-weight music models (fully licensed data)—from quick SFX and short tracks to longer, more musical pieces—inside the workflows you already use.
arXiv:2605.20478v1 Announce Type: new Abstract: LLM-curated tables can appear source-grounded while containing unsupported rows: the curator may recall entries from parametric memory and retroactively
arXiv:2605.20738v1 Announce Type: new Abstract: Remote sensing imagery typically arrives in the form of continuous data streams. Traditional detectors often forget previously learned categories when l
Starlink Mobile is coming soon to Panama with @MasMovilPanama and will keep customers connected where it wasn't possible before with apps, video, voice and messaging 🛰️📱 Panamá entra en una nueva era
SpaceX's Starship V3 is entering the countdown phase for its first flight test, as announced by Elon Musk on X (formerly Twitter). This represents a major milestone in SpaceX's development of its next
🚨 STARSHIP V3 UPGRADES SpaceX just unveiled Starship Version 3 Every major system redesigned: > payload tripled to 100 metric tons > all 33 Raptors now fire simultaneously > 3 grid fins instead of 4,
arXiv:2512.23943v2 Announce Type: replace-cross Abstract: U.S. discrimination law can impose liability on firms that fail to adopt a less discriminatory alternative (LDA): a decision policy that achie
arXiv:2605.20929v1 Announce Type: new Abstract: We propose STEAM (Spatial, Temporal, and Emergent congestion Awareness for MAPF), a training-free test-time enhancement framework for learning-based dec
arXiv:2605.20390v1 Announce Type: new Abstract: Model scaling has demonstrated remarkable success through large-scale training on diverse datasets. It remains an open question whether the same paradig
arXiv:2605.21324v1 Announce Type: cross Abstract: What can representational similarity matrices (RSMs) tell us about a neural code? As the popularity of these summary statistics grows, so too does the
arXiv:2605.21261v1 Announce Type: new Abstract: Training-free zero-shot composed image retrieval models are recently gaining increasing research interest due to their generalizability and flexibility
arXiv:2508.12247v2 Announce Type: replace Abstract: Recently, spatio-temporal time-series prediction has developed rapidly, yet existing deep learning methods struggle with learning complex long-term
arXiv:2605.20924v1 Announce Type: new Abstract: Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction inducti
arXiv:2605.21472v1 Announce Type: new Abstract: View-conditioned 3D generators such as SAM 3D, TRELLIS and Hunyuan3D produce high-quality object reconstructions from a single view, but real-world visu
arXiv:2605.21466v1 Announce Type: new Abstract: Although existing video editing methods are generally feasible, they often require many costly iterations and still struggle to deliver high-quality yet
streaming from modern agents is pretty complex! especially with - parallel tools / subagents - multimodal content - human in the loop events our new streaming primitives make all of this ergonomic! Ag
arXiv:2506.21039v3 Announce Type: replace Abstract: Long-horizon goal-conditioned tasks pose fundamental challenges for reinforcement learning (RL), particularly when goals are distant and rewards are
Shares of the financial services and human resources software company Workday Inc. rose more than 10% in late trading after it reported first-quarter earnings and revenue that came in higher than expe
arXiv:2605.20917v1 Announce Type: new Abstract: Subterranean (SubT) environments have been a frontier for autonomous robotics, driven by the push for automation of mining operations and the interest i
Subword boundaries are the second meaningful effect. Adding end-of-subword markers as input embeddings produces a large gain throughout training (H3): end-boundaries leak future bytes (whitespace alwa
arXiv:2605.20373v1 Announce Type: cross Abstract: Building humanoid robots capable of generalizable whole-body loco-manipulation in the real world remains a fundamental challenge. Existing methods eit
arXiv:2605.20413v1 Announce Type: new Abstract: High-dimensional biological data often exhibit a severe mismatch between feature dimensionality and sample size, making reliable classification difficul
arXiv:2605.20619v1 Announce Type: new Abstract: Scalarization is widely used in multi-objective optimization owing to its simplicity and scalability. In many applications, the goal is to generate solu
arXiv:2605.21132v1 Announce Type: new Abstract: Understanding surgical workflow in real time is fundamental for intelligent surgical embodiment, where AI systems continuously perceive and respond as s
arXiv:2603.26603v2 Announce Type: replace-cross Abstract: The migration of Large Language Models (LLMs) from cloud clusters to edge devices promises enhanced privacy and offline accessibility, but thi
arXiv:2605.20919v1 Announce Type: new Abstract: Sutra is a typed, purely functional programming language whose compiled forward pass is a PyTorch neural network. The compiler beta-reduces the whole pr
arXiv:2605.21333v1 Announce Type: new Abstract: Natively trained spiking language models struggle to combine Transformer-like language quality, stable multi-domain pre-training, and high activation sp
arXiv:2605.20347v1 Announce Type: new Abstract: Labeling a training set is often expensive and susceptible to errors, making the design of robust loss functions for label noise an important problem. T
arXiv:2605.20908v1 Announce Type: new Abstract: Concept-based (CB) models provide interpretability and support test-time human intervention, while standard neural networks (NN) offer strong task perfo
arXiv:2605.20356v1 Announce Type: new Abstract: Full-duplex spoken dialogue models (SDMs) can listen and speak simultaneously, enabling interaction dynamics closer to human conversation than turn-base
arXiv:2603.21033v2 Announce Type: replace-cross Abstract: Geotechnical site characterisation relies on sparse, heterogeneous borehole data, where uncertainty quantification and interpretability matter
arXiv:2605.20234v1 Announce Type: new Abstract: Prior-Data Fitted networks (PFNs) have been very successful in tabular contexts, handling prediction tasks in context. However, they are designed for si
Bloomberg: Taiwan is seeking to detain three people for forging documents to export Nvidia-powered Super Micro servers to China, Hong Kong, and Macau, breaking US rules — Taiwanese officials are seeki
arXiv:2506.08277v3 Announce Type: replace-cross Abstract: Recent voxel-wise multimodal brain encoding studies have shown that multimodal large language models (MLLMs) exhibit a higher degree of brain
arXiv:2605.20916v1 Announce Type: new Abstract: Implicit sentiment analysis is challenging because sentiment toward an aspect is often inferred from events rather than expressed through explicit opini
arXiv:2605.20731v1 Announce Type: new Abstract: Text-to-image models produce graphic design at production scale, but their supervision comes from photo-style preference data with a single overall verd
Since its earliest days back in office, the Trump administration has been going after researchers who study and try to counter hate speech, harassment, propaganda, and disinformation online. Now, some
arXiv:2510.06063v2 Announce Type: replace-cross Abstract: Modern enterprises generate vast streams of time series metrics when monitoring complex systems, known as observability data. Unlike conventio
arXiv:2605.20290v1 Announce Type: cross Abstract: Recent generative video models achieve impressive visual quality but remain constrained by limited physical consistency and controllability. Existing
arXiv:2605.21443v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly being explored for video game quality assurance, especially gameplay glitch detection. Most existing eval
arXiv:2509.07674v2 Announce Type: replace Abstract: Explainability, in particular, the ability for robots to explain why they have made a decision or behaved in a certain way, is a critical tool in he
Ten years ago, I walked into Tesla as an intern — January 2015, back when all we built was the Model S. I never imagined I'd one day lead the Fremont factory where we are building some of the most ama
arXiv:2605.20822v1 Announce Type: new Abstract: In this work, we address the challenge of Scene Change Detection (SCD), where the goal is to identify variations between two images of the same location
arXiv:2605.20876v1 Announce Type: new Abstract: Terminal agents extend Large Language Models with the ability to execute tasks directly in command-line environments, but their progress is bottlenecked
arXiv:2605.20304v1 Announce Type: new Abstract: Soft mobile robots have emerged as a promising area of research with potential applications in various disciplines including but not limited to search-a
arXiv:2410.18915v4 Announce Type: replace-cross Abstract: Consider two problems about an unknown probability distribution p: 1. How many samples from p are required to test if p is supported on n elem