Knowledge catalogue
arXiv:2608.15405v1 Announce Type: cross Abstract: Afterlife Delegation Protocol is a speculative design project that asks what death becomes when a will can act eternally. We design a speculative prot
arXiv:2608.15591v1 Announce Type: new Abstract: Large Language Model (LLM) agents deployed in production environments face a fundamental tension: the agent's behavior is frozen at deployment time, whi
arXiv:2608.15403v1 Announce Type: cross Abstract: You will die eventually. Your agents may not. An AI agent operating on decentralized blockchain infrastructure has no concept of death; it can only go
arXiv:2608.16178v1 Announce Type: cross Abstract: Operational telemetry is predominantly engineered for human reading: systems repeatedly serialize verbose prose, static keys, and redundant context ac
arXiv:2608.14765v1 Announce Type: new Abstract: Data cleaning without a trusted clean reference is challenging because unusual values may represent either genuine errors or valid observations. This pa
arXiv:2608.15389v1 Announce Type: new Abstract: LLM-based Text-to-SQL progress is reported across heterogeneous benchmarks, backbones, and inference protocols, making cross-system comparison fragile.
arXiv:2602.12276v2 Announce Type: replace Abstract: Test-time scaling has become a standard way to improve performance and boost reliability of neural network models. However, its behavior on agentic,
'Agents = model + harness + context' is a much better mental model than treating the LLM as the entire product. The model provides capability, but the harness determines tools, permissions and behavio
Robbie Whelan / Wall Street Journal: AI inference chip startup Etched raised 700M led by its new server rack customer Jane Street at a 21B valuation, up from 10.3B after raising 300M in July — Etched,
'AI is a new kind of camera. It's a camera that allows you to not only record the real world, but technically any world that you want.' Runway CEO Cristóbal Valenzuela is already changing how Hollywoo
The AI industry’s boldest promise right now is that AI will soon improve itself, with almost no need for human oversight. LLMs can already write code, generate synthetic data for training, and optimiz
arXiv:2608.15636v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in the field of embodied AI, but their high computational cost and limit
Juro Osawa / The Information: Alibaba says its new open-source multimodal model, Qwen3.8-27B, passed 1M+ downloads within a few days of release, making it one of its fastest-growing models — Alibaba G
arXiv:2608.15456v1 Announce Type: new Abstract: Remote sensing (RS) foundation models provide transferable Earth observation representations across sensors, resolutions, and geographies, yet most rema
arXiv:2608.15776v1 Announce Type: cross Abstract: Despite the powerful multi-scale modeling methods and high-throughput infrastructures established in the materials community, real material computatio
arXiv:2608.15605v1 Announce Type: new Abstract: This study investigates the challenge of ambiguity faced by Vision-Language Models (VLMs) in understanding spatial semantics. Spatial cognition, shaped
arXiv:2608.15979v1 Announce Type: new Abstract: Large language models produce outputs presented as discoveries - new proofs, conjectures, or molecules. Whether such an output that appears creative is
Amazon Bedrock AgentCore payments is now generally available, enabling AI agents to autonomously transact at scale with built-in spending guardrails, protocol-agnostic payment orchestration, and produ
arXiv:2608.15559v1 Announce Type: cross Abstract: Anomaly detection in dynamic graphs underpins financial fraud analysis, intrusion detection, and platform integrity, where automated decisions require
arXiv:2608.14778v1 Announce Type: new Abstract: Hepatocellular carcinoma (HCC) is the third leading cause of cancer-related mortality worldwide, with early detection improving survival from 70%. The s
arXiv:2608.15153v1 Announce Type: cross Abstract: Differentially private federated learning must balance privacy protection against model accuracy and training efficiency. Static gradient clipping app
arXiv:2608.14587v1 Announce Type: new Abstract: Background: Recent advances in information retrieval (IR) leverage both dense and sparse representations, large language models (LLMs), and specialized
arXiv:2608.16873v1 Announce Type: new Abstract: High-fidelity finite-element simulations can provide accurate numerical predictions for side-branch resonators, but large simulation datasets are expens
arXiv:2608.14661v1 Announce Type: new Abstract: Time-lapse electrical resistivity tomography (TL-ERT) provides spatially distributed information on subsurface hydrologic changes. However, inversion of
arXiv:2608.16887v1 Announce Type: new Abstract: This paper investigates an increasingly important topic in generative modeling: pixel-space diffusion models. Although numerous studies have explored th
arXiv:2608.15417v1 Announce Type: cross Abstract: Governments use laws, institutions, funding programs and nonbinding guidance to shape how AI is developed and used. Comparing these national approache
arXiv:2608.15721v1 Announce Type: new Abstract: This report describes our submission to the Big Cross-Modal Attenuation Correction (BIC-MAC) 2026 Challenge for CT-less PET attenuation correction throu
arXiv:2608.15117v1 Announce Type: new Abstract: Analytical models of peak VRAM consumption for LLM inference decompose memory into weight-storage, KV-cache, and activation terms parameterized by step
arXiv:2608.15196v1 Announce Type: new Abstract: Recent works in AI-generated image detection have shown that careful training data alignment can improve generalization by removing spurious correlation
arXiv:2608.16690v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are widely used for automated annotation, yet their per-class accuracy varies widely (e.g., 12%-98% across the
arXiv:2608.15052v1 Announce Type: new Abstract: Andy is an autonomous mathematical research agent that solves and verifies submitted problems, formulates new research problems, and constructs rigorous
Anthropic: Anthropic details two experiments showing how Claude can accelerate protein design and analytical chemistry, and says it plans an access program for scientists — Summary: In this post, we s
arXiv:2608.16143v1 Announce Type: cross Abstract: We present AnyTalk, a novel method for generating 3D speech animations for arbitrary characters without requiring any animation data. While existing a
arXiv:2608.16347v1 Announce Type: new Abstract: Direct communication between AI systems relies on natural language as an intermediate layer, incurring encoding/decoding overhead, token cost, and laten
arXiv:2608.15578v1 Announce Type: cross Abstract: Large audio-language models (LALMs) make it possible to interact with language models through speech, music, and environmental sound, but they also in
arXiv:2608.15634v1 Announce Type: new Abstract: How can common ground between societies in conflict be identified when citizens' acceptability of peace agreements is shaped by contested narratives? Su
arXiv:2608.14670v1 Announce Type: cross Abstract: Passive, device-free person identification offers an alternative to camera- and wearable-based biometrics, yet existing wireless approaches rely large
arXiv:2608.14866v1 Announce Type: cross Abstract: Objective: Small-sample molecular classification requires feature selectors that identify predictive, stable, and nonredundant subsets for binary and
arXiv:2608.16351v1 Announce Type: new Abstract: Dexterous grasp generation that considers arm-related constraints is crucial in real-world scenarios involving arm environment collision avoidance, work
arXiv:2608.14770v1 Announce Type: cross Abstract: An estimated 138 million children remain in child labour worldwide, and the monitoring systems used by affected sectors, built on periodic household v
arXiv:2608.15419v1 Announce Type: new Abstract: Articulated-object reconstructions recover explicit geometry and kinematics, but their parts often remain semantically anonymous and must be controlled
As models become more capable, the risks associated with developing and testing them internally also grow. We temporarily paused reinforcement learning (RL) training on our latest models intended for
arXiv:2608.16554v1 Announce Type: new Abstract: Answer-only reinforcement learning (RL) trains reasoning models to solve fully specified problems, but many realistic queries omit a premise needed for
arXiv:2608.15949v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled their use as conversational recommender systems (CRS), demonstrating strong recommendatio
arXiv:2406.13049v3 Announce Type: replace-cross Abstract: Personalized phishing is difficult to defend against because messages can be tailored to a target's work, interests, and social context. Large
arXiv:2608.16118v1 Announce Type: new Abstract: How should we assess whether large language models can perform mathematical invention? I argue that this question is currently underspecified: mathemati
arXiv:2608.16381v1 Announce Type: new Abstract: Agentic systems often organize execution and state around a single conversation, model invocation, or agent instance, even when real work spans many cal
arXiv:2608.16152v1 Announce Type: cross Abstract: We study resonance prediction in dispersive media, formulated as nonlinear spectral problems for volume integral operators. The main idea is to use as
arXiv:2608.16098v1 Announce Type: cross Abstract: Multivariate time-series forecasting faces a structural dilemma: sharing one temporal predictor across variables is parameter-efficient but forces het
arXiv:2608.15546v1 Announce Type: new Abstract: Most LLM-based automated algorithm design methods optimize a designated component within a human-specified scaffold, fixing overall organization and com
arXiv:2608.16885v1 Announce Type: new Abstract: Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks. Most hiera
arXiv:2608.16285v1 Announce Type: cross Abstract: Audio-Visual Segmentation (AVS) is a fundamental task in multimodal perception that performs pixel-level segmentation of sounding objects in videos by
arXiv:2608.15369v1 Announce Type: cross Abstract: Lossy audio compression algorithms traditionally rely on psychoacoustic modeling and frequency-domain representations (e.g., MP3, AAC, and Opus) to di
arXiv:2608.14673v1 Announce Type: new Abstract: Chapter 6 of OpenAI's *Ten Advances in Mathematics and Theoretical Computer Science* claims an exponential parallel-repetition theorem for all finite tw
arXiv:2608.15932v1 Announce Type: new Abstract: As state-of-the-art machine translation models saturate standard benchmarks, the field needs more challenging evaluations to distinguish between models
arXiv:2608.15692v1 Announce Type: new Abstract: Automated biometric analysis of fetal brain MRI enables reproducible, observer-independent quantitative assessment, yet existing methods are often restr
arXiv:2608.16535v1 Announce Type: new Abstract: Manual cephalometric landmark annotation is important for craniofacial assessment but is labor-intensive and difficult to scale. We introduce CephViT, a
arXiv:2608.14681v1 Announce Type: cross Abstract: Words recur constantly in natural language use, yet it remains unclear whether language models reactivate prior representations or re-evaluate repeate
arXiv:2608.16541v1 Announce Type: cross Abstract: Objective assessment of learning remains a fundamental challenge in education. Electroencephalography (EEG) provides a direct, non-invasive window int
arXiv:2602.22456v2 Announce Type: replace-cross Abstract: Requirements are inherently interconnected through various types of dependencies. Identifying these dependencies is essential, as they underpi