Knowledge catalogue
Remember when Framework made the first laptop where you can easily upgrade its entire internal video card in three minutes flat? The company's getting into the external graphics game, too. As promised
arXiv:2505.18128v4 Announce Type: replace Abstract: We introduce Frankentexts, a long-form narrative generation paradigm that treats an LLM as a composer of existing texts rather than as an author. Gi
arXiv:2604.18159v1 Announce Type: new Abstract: Empathy is essential for fostering natural interactions in spoken dialogue systems, as it enables machines to recognize the emotional tone of human spee
arXiv:2604.18328v1 Announce Type: new Abstract: We present FregeLogic, a hybrid neuro-symbolic system for SemEval-2026 Task 11 (Subtask 1), which addresses syllogistic validity prediction while reduci
arXiv:2604.16800v1 Announce Type: new Abstract: Addressing the issues of severe noise and high frequency structural degradation in visible images under low-light conditions, this paper proposes a Near
arXiv:2604.17298v1 Announce Type: new Abstract: Video Scene Graph Generation aims to obtain structured semantic representations of objects and their relationships in videos for high-level understandin
arXiv:2604.16918v1 Announce Type: new Abstract: Reinforcement Learning (RL) has achieved impressive success in post-training Large Language Models (LLMs) and Vision-Language Models (VLMs), with on-pol
Friendly Machines is happening next Tuesday! We’re exploring how Hermes by @NousResearch and Claude are used to build useful agents: – live demos – Q&A with @NousResearch team – discuss your workflows
arXiv:2604.16648v1 Announce Type: new Abstract: In this work, we present FRIGID, a framework with a novel diffusion language model that generates molecular structures conditioned on mass spectra via i
arXiv:2604.17231v1 Announce Type: new Abstract: Unrecovered e-waste represents a significant economic loss. Hard disk drives (HDDs) comprise a valuable e-waste stream necessitating robotic disassembly
arXiv:2507.03052v2 Announce Type: replace Abstract: As large language models (LLMs) grow in size, efficient compression techniques like quantization and sparsification are critical. While quantization
arXiv:2604.17455v1 Announce Type: new Abstract: Visual prompting has emerged as a powerful method for adapting pre-trained models to new domains without updating model parameters. However, existing pr
arXiv:2601.16397v2 Announce Type: replace Abstract: Deploying multimodal large language models (MLLMs) for clinical summarization demands not only fluent generation but also transparency about where e
arXiv:2602.14928v4 Announce Type: replace-cross Abstract: We extend the Prometheus framework for unsupervised phase transition discovery from two-dimensional classical systems to three-dimensional cla
arXiv:2604.17110v1 Announce Type: new Abstract: Clinical AI development has traditionally followed a collaborative paradigm that depends on close interaction between clinicians and specialized AI team
Multicloud resilience is no longer a buzzword. As enterprises wrestle with surging AI adoption and mounting compliance pressures, digital sovereignty has become the new battleground for control over i
Today, we're excited to announce Claude Cowork in Amazon Bedrock. You can now run Cowork and Claude Code Desktop through Amazon Bedrock, directly or using an LLM gateway. In this post, we walk through
arXiv:2601.04278v2 Announce Type: replace Abstract: Although machine unlearning is essential for removing private, harmful, or copyrighted content from LLMs, current benchmarks often fail to faithfull
arXiv:2604.17968v1 Announce Type: cross Abstract: Although large language models (LLMs) are increasingly used as annotators at scale, they are typically treated as a pragmatic fallback rather than a f
arXiv:2604.16504v1 Announce Type: new Abstract: Manual digitisation of structured handwritten documents is slow and costly. We benchmark 17 leading frontier multi-modal large language models and open-
arXiv:2604.17941v1 Announce Type: cross Abstract: Recent work has increasingly explored neuron-level interpretation in vision-language models (VLMs) to identify neurons critical to final predictions.
arXiv:2601.03682v2 Announce Type: replace Abstract: Recent studies reveal that large language models (LLMs) exhibit limited logical reasoning abilities in mathematical problem-solving, instead often r
arXiv:2604.16462v1 Announce Type: new Abstract: High-resolution Multimodal Large Language Models (MLLMs) face prohibitive computational costs during inference due to the explosion of visual tokens. Ex
The main stage at Google Cloud Next is where the vision is set. This year, we’re bridging the gap between those massive 'Cloud-scale' announcements and your local terminal. We are thrilled to announce
arXiv:2604.17153v1 Announce Type: new Abstract: Transforming legal text into executable decision logic is a longstanding challenge in legal informatics. With the rise of LLMs, this task has gained ren
arXiv:2603.14389v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed a leap in Large Language Model (LLM) reasoning, yet its optimization dynamics re
arXiv:2603.04592v3 Announce Type: replace Abstract: Standard Large Language Models (LLMs) are predominantly designed for static inference with pre-defined inputs, which limits their applicability in d
arXiv:2604.16572v1 Announce Type: new Abstract: Wi-Fi Channel State Information (CSI) enables device-free human activity recognition, but existing multi-user approaches assume a fixed set of known use
arXiv:2603.01455v2 Announce Type: replace-cross Abstract: While multimodal large language models have demonstrated impressive short-term reasoning, they struggle with long-horizon video understanding
arXiv:2604.16758v1 Announce Type: new Abstract: We present a system for automated detection, localization, and scoring of arrow punctures on 40,cm indoor archery target faces, trained on only 48 annot
arXiv:2604.18227v1 Announce Type: new Abstract: Feature selection is a fundamental machine learning and data mining task, involved with discriminating redundant features from informative ones. It is a
arXiv:2604.17277v1 Announce Type: new Abstract: Physical neural networks offer a transformative route to edge intelligence, providing superior inference speed and energy efficiency compared to convent
fun off-the-cuff harness + agent engineering sesh with @dexhorthy @vaibcode @GeoffreyHuntley - a lot of good harness/agent design we’re doing today is still good context engineering, remember tool cal
arXiv:2601.21191v2 Announce Type: replace Abstract: What statistical properties might support learning abstract grammatical knowledge from linear input? We address this question by examining the stati
arXiv:2604.16426v1 Announce Type: new Abstract: As modern deep learning architectures grow in complexity, representational ambiguity emerges as a critical barrier to their interpretability and reliabl
arXiv:2604.18547v1 Announce Type: cross Abstract: Verification of model outputs is rapidly emerging as a key primitive for both training and real-world deployment of large language models (LLMs). In p
arXiv:2604.16436v1 Announce Type: cross Abstract: This paper develops an end-to-end fuzzy encoder-decoder architecture for enhancing vision-based multi-modal deep spiking Q-networks in autonomous driv
arXiv:2604.16533v1 Announce Type: new Abstract: Physics-aware recurrent convolutional networks (PARC) have demonstrated strong performance in predicting nonlinear spatiotemporal dynamics by embedding
Sam Altman posted a positive endorsement of someone named Gabe on X, praising their talent and leadership abilities while expressing confidence in their capabilities. The post suggests Altman views Ga
arXiv:2604.17241v1 Announce Type: new Abstract: Implicit spatial relations and deep semantic structures encoded in object attributes are crucial for procedural planning in embodied AI systems. However
Our new GEAR program, powered by Google Skills, equips every professional with the hands-on AI training needed to build and launch enterprise-ready agents at scale. Anyone can join GEAR for access to
arXiv:2604.17721v1 Announce Type: new Abstract: We address the challenge of point cloud registration using color information, where traditional methods relying solely on geometric features often strug
arXiv:2604.17307v1 Announce Type: new Abstract: Detecting face forgeries using CLIP has recently emerged as a promising and increasingly popular research direction. Owing to its rich visual knowledge
arXiv:2502.05708v3 Announce Type: replace-cross Abstract: We present GRaF, Generalizable Radio-Frequency (RF) Radiance Fields, a framework that models RF signal propagation to synthesize spatial spect
arXiv:2604.18092v1 Announce Type: new Abstract: Small language models fine-tuned for graph property estimation have demonstrated strong in-distribution performance, yet their generalization capabiliti
arXiv:2411.06812v2 Announce Type: replace-cross Abstract: This paper introduces the concept of ``generative midtended cognition'', exploring the integration of generative AI with human cognition. The
arXiv:2604.16796v1 Announce Type: new Abstract: Generative semantic communication (SemCom) harnesses pretrained generative priors to improve the perceptual quality of wireless image transmission. Exis
arXiv:2604.17091v1 Announce Type: new Abstract: Long-horizon large language model (LLM) agents are fundamentally limited by context. As interactions become longer, tool descriptions, retrieved memorie
arXiv:2602.23665v3 Announce Type: replace-cross Abstract: We present Geodesic Semantic Search (GSS), a retrieval system that learns node-specific Riemannian metrics on citation graphs to enable geomet
arXiv:2601.00921v2 Announce Type: replace Abstract: Quantum methods are increasingly proposed for healthcare, but translational biomarker studies demand transparent benchmarking and robust small-datas
arXiv:2601.09173v4 Announce Type: replace-cross Abstract: Representational similarity analysis and related methods have become standard tools for comparing the internal geometries of neural networks a
arXiv:2604.16487v1 Announce Type: new Abstract: CLIP retrieval is typically framed as a pointwise similarity problem in a shared embedding space. While CLIP achieves strong global cross-modal alignmen
arXiv:2604.18260v1 Announce Type: new Abstract: Multimodal large language models have demonstrated remarkable capabilities in 2D vision, motivating their extension to 3D scene understanding. Recent st
arXiv:2506.07160v3 Announce Type: replace Abstract: Recent progress in large language models (LLMs) has boosted mathematical reasoning, yet geometry remains challenging where auxiliary construction is
arXiv:2601.21278v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) are good at recognizing the global location of a photograph -- their geolocation prediction accuracy rivals the
A long stretch of humid heat followed by a powerful thunderstorm is a familiar weather pattern in the tropics, but it’s also becoming more common in midlatitude regions such as the US Midwest. A recen
Given the significant progress over the past year, this year’s festival will likely mark a tipping point. Submissions are still open! The Runway AI Festival returns this June to NY and LA to celebrate
arXiv:2604.16590v1 Announce Type: new Abstract: Accurate weather and climate prediction relies on data assimilation (DA), which estimates the Earth system state by integrating observations with models
Solar added approximately 600 terawatt-hours of generation globally in 2025—the largest increase ever recorded in a single year for any power technology. Solar was the single biggest contributor to gl
arXiv:2604.16377v1 Announce Type: new Abstract: Large Language Models (LLMs) trained on massive code corpora are now increasingly capable of generating code that is hard to distinguish from human-writ