Knowledge catalogue
arXiv:2608.21100v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) extend model capabilities beyond text, they also make safety alignment increasingly challenging. Multimod
arXiv:2503.20546v2 Announce Type: replace-cross Abstract: We consider the problem of estimating the expected causal effect E[Y|do(X)] for a target variable Y when treatment X is set by intervention, f
arXiv:2608.20680v1 Announce Type: new Abstract: We study reinforcement learning (RL) in Continuous-Time Jump Markov Decision Processes (CTJMDPs) featuring general discrete state spaces (which need not
arXiv:2505.11821v3 Announce Type: replace Abstract: Reinforcement Learning (RL) approaches have been wildly used to enhance the reasoning capabilities of Large Language Model (LLM) agents in long-hori
arXiv:2608.20389v1 Announce Type: new Abstract: A production agent harness must discover and rank, from a growing library of skills, the one most appropriate for a user's task. At small scale this sel
arXiv:2608.20368v1 Announce Type: new Abstract: Knowledge and innovations are shaped by using the quality and credibility of the scientific research. Yet, distinguishing between impactful, high-qualit
Mark Anderson / Bloomberg: Researchers detail the growing use of AI in cyberattacks across many Chinese state-linked groups, primarily using open-weight models like Kimi K3 and DeepSeek — Chinese hack
arXiv:2608.20812v1 Announce Type: new Abstract: We develop constructive approximation and learning guarantees for shallow neural models with infinite-dimensional inputs observed through finitely many
arXiv:2608.20784v1 Announce Type: cross Abstract: Imitation learning for robotics depends on human demonstrations, some of which people may later ask to remove. Retraining without them is the natural
arXiv:2608.21308v1 Announce Type: new Abstract: Test-Time Training (TTT) enables long-context processing via continuous weight updates during inference, but current methods struggle to balance the exp
arXiv:2608.20418v1 Announce Type: cross Abstract: We introduce Malaria-Instruct, a curated instruction-following dataset derived from the ChEMBL Legacy Malaria corpus for Malaria virtual screening, an
arXiv:2608.20430v1 Announce Type: new Abstract: World Action Models (WAMs) improve planning by incorporating future world evolution into action generation, yet existing methods allocate a fixed imagin
arXiv:2608.20656v1 Announce Type: cross Abstract: Traffic sensors commonly record flow, speed, and occupancy, but standard traffic flow forecasting benchmarks and models rarely exploit all three raw m
arXiv:2608.21032v1 Announce Type: new Abstract: Vehicle-to-Everything (V2X) cooperation enables beyond-line-of-sight perception, mitigating occlusions in single-vehicle sensing. However, existing V2X
arXiv:2608.20404v1 Announce Type: cross Abstract: The discovery of governing partial differential equations (PDEs) directly from spatiotemporal data has emerged as a powerful tool for understanding th
arXiv:2608.21066v1 Announce Type: new Abstract: Deploying autonomous systems in safety-critical domains demands guaranteed robustness against physically plausible geometric perturbations rather than a
arXiv:2608.21024v1 Announce Type: new Abstract: Modern neural network training increasingly uses matrix-aware optimizers, yet their conditioned matrix step is typically added directly to the weight, j
arXiv:2608.21117v1 Announce Type: new Abstract: Root cause analysis aims to identify the mechanisms responsible for anomalies in complex dynamical systems. In this paper, we study root cause analysis
arXiv:2608.20805v1 Announce Type: new Abstract: Long-form video understanding remains challenging for video agents due to the mismatch between query demands and evidence acquisition strategies. Althou
arXiv:2608.20839v1 Announce Type: new Abstract: Watermarking diffusion language models (DLMs) requires mechanisms compatible with iterative parallel unmasking rather than autoregressive decoding. Exis
arXiv:2608.20630v1 Announce Type: new Abstract: SQL systems increasingly expose AI functions for tasks such as classification, extraction, filtering, ranking, retrieval, joining, and summarization. De
OpenAI Group PBC Chief Executive Sam Altman is worried that artificial intelligence technology will end up being controlled by just a handful of companies or people in future, resulting in nobody else
arXiv:2608.20904v1 Announce Type: new Abstract: Virtual scenario-based testing is a key enabler for validating automated driving systems (ADS) and intelligent transport systems (ITS). However, executi
arXiv:2608.20818v1 Announce Type: cross Abstract: The matrix-aware optimizer Muon improves large model training by balancing updates across singular directions, yet its scaling behavior and end-to-end
arXiv:2608.21023v1 Announce Type: new Abstract: Word alignment has traditionally been studied between sentences, but many cross-lingual tasks increasingly require correspondences across full documents
arXiv:2508.15813v2 Announce Type: replace-cross Abstract: A big issue in modern LLM applications is they tend to feed long context to LLM, which results in high inference cost and latency, and may exc
arXiv:2608.20341v1 Announce Type: new Abstract: Frontier coding agents backed by large language models with context windows from hundreds of thousands to millions of tokens are restructuring the Softw
arXiv:2602.00663v3 Announce Type: replace Abstract: Optimizing molecules to achieve desired properties is a central bottleneck across the chemical sciences, particularly in the pharmaceutical industry
arXiv:2608.20359v1 Announce Type: new Abstract: Large language models (LLMs) are deployed for increasingly complex tasks involving planning and multi-step decision making, but high-quality performance
arXiv:2608.20396v1 Announce Type: new Abstract: Language development is characterized by a gradual convergence of children's speech toward adult patterns. Measuring this process has traditionally requ
arXiv:2608.20916v1 Announce Type: new Abstract: Vision foundation models (VFMs) offer strong generalization capabilities for domain-adaptive object detection (DAOD). However, existing VFM-based method
arXiv:2608.21203v1 Announce Type: new Abstract: Technology change management in large financial institutions depends on risk assessments that are accurate, consistent, and auditable. In practice, many
arXiv:2607.27984v2 Announce Type: replace Abstract: Agentic systems generate outputs faster than human review. We contrast two LLM evaluator specialization strategies: specialized judge weights, or ru
arXiv:2608.20441v1 Announce Type: new Abstract: Selecting the optimal neural-operator prediction during deployment is challenging when high-fidelity reference solutions are unavailable. We demonstrate
arXiv:2608.20858v1 Announce Type: cross Abstract: Transportation networks, in particular multi-class transportation networks (i.e., networks with mixed vehicle types), are complex systems that are cha
arXiv:2608.20663v1 Announce Type: new Abstract: Public datasets for agricultural disease detection are usually judged fit for use from reported metrics, which say nothing about whether the annotation
arXiv:2512.00418v3 Announce Type: replace-cross Abstract: Significant Others (SOs) stabilize identity, regulate emotion, and support narrative meaning-making, yet many people today lack access to such
arXiv:2608.20421v1 Announce Type: cross Abstract: Large language models (LLMs) are now embedded in scientific, educational, and governance workflows, with debates centering on their capabilities, mech
arXiv:2509.20377v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has significantly improved the performance of large language models (LLMs) on knowledge-intensive tasks i
arXiv:2601.09487v2 Announce Type: replace Abstract: The rapid evolution of Large Language Models (LLMs) has fostered diverse paradigms for automated slide generation, ranging from code-driven layouts
arXiv:2504.05978v4 Announce Type: replace Abstract: Reinforcement learning (RL) is a powerful framework for decision-making in uncertain environments, but it often requires large amounts of data to le
It’s SO DAMN CLOSE. My harness has brought such a sense of calm whenever I sit and get some work done. Can't wait to get this out there. AMA, and yes, I've created a coding and cross domain harness an
arXiv:2608.21044v1 Announce Type: new Abstract: Class-incremental learning is commonly instantiated as a single-model paradigm, where a unified model sequentially adapts to an unbounded stream of sess
Agentic AI workloads exhibit extreme variability—telemetry from over 163,000 sessions shows more than 97 % have unique workload trajectories, rendering traditional multi‑design CPU fleets ineffective.
Ina Fried / Axios: Source: AI researcher Luke Metz, who returned to OpenAI from TML earlier this year, joins Meta's Superintelligence Labs and will report to Alexandr Wang — Prominent AI researcher Lu
arXiv:2608.20925v1 Announce Type: cross Abstract: Reference-based metrics remain the standard choice in machine translation evaluation, partly because quality estimation methods often correlate less w
Dan Primack / Axios: Source: robotics startup Generalist, which released its GEN-1 model to complete physical tasks in April, raised ~200M led by 8VC, after raising 400M in June — Generalist has quiet
Bloomberg: Sources: ByteDance is merging coding platform Trae and agent-building tool Coze into Doubao, and plans to launch Doubao Work to compete with Tencent's WorkBuddy — ByteDance Ltd. is consolid
Bloomberg: Sources: Nvidia-backed neocloud Lambda is in talks to raise up to 3B at a 12B+ valuation; its revenue this year is estimated to reach 1.5B+ — Lambda Inc., an AI cloud-computing provider bac
SpaceX, in partnership with Nvidia, has designed a space-optimized Vera Rubin NVL72 system for launch to orbit in Q4 next year, with significant scale in 2028 The first CPU built for agents is going t
arXiv:2608.20802v1 Announce Type: new Abstract: Human motion forecasters are increasingly accurate and fast, but reliable deployment requires uncertainty estimates that are structured, calibrated, and
arXiv:2608.21307v1 Announce Type: new Abstract: Analytic continual learning has emerged as a strong exemplar-free alternative to gradient-based class-incremental learning because it replaces iterative
arXiv:2608.20754v1 Announce Type: new Abstract: Promptable segmentation models provide a reusable interface, but direct transfer to automatic infrared small-target segmentation (IRSTD) exposes a misma
arXiv:2608.20602v1 Announce Type: cross Abstract: Many consumer smartphones, stereo cameras, and light field cameras record multiple synchronized viewpoints in a single exposure event. However, novel
arXiv:2608.20632v1 Announce Type: new Abstract: Efficient-transformer research often motivates token pruning and adaptive computation with the claim that not all tokens require equal computational eff
arXiv:2511.22648v2 Announce Type: replace Abstract: A spatially aware dictionary-free eigenfunction discovery (SADFED) framework is proposed for identification of low-rank Koopman models from data wit
arXiv:2504.18882v3 Announce Type: replace-cross Abstract: Neuroimaging provides essential tools for characterizing brain activity, structure, and connectivity through modalities that capture complemen
arXiv:2608.21208v1 Announce Type: cross Abstract: This paper investigates cross-agent specification portability using Oracle-to-PostgreSQL migration as a controlled software transformation task. The s
arXiv:2608.21175v1 Announce Type: cross Abstract: Safe and efficient shape-aware navigation in heterogeneous crowds and robot fleets remains challenging. Traditional approaches often assume homogeneou
arXiv:2608.20831v1 Announce Type: cross Abstract: Aspect-based sentiment analysis (ABSA) quadruple extraction requires jointly predicting target, aspect, opinion, and sentiment over reviews that often