Knowledge catalogue
arXiv:2604.26230v1 Announce Type: new Abstract: I developed a new version of Latent Semantic Scaling (LSS) employing word2vec as a masked language model. Unlike original spatial models, it assigns pol
arXiv:2604.26926v1 Announce Type: new Abstract: In Orabona and Pal [2016], we introduced the shifted KT potentials, to remove the ln ln T factor in the parameter-free learning with expert bound. In th
arXiv:2409.06624v4 Announce Type: replace-cross Abstract: Large Language Models (LLM) often need to be Continual Pre-Trained (CPT) to obtain unfamiliar language skills or adapt to new domains. The hug
arXiv:2603.25980v2 Announce Type: replace-cross Abstract: Transition states, the first-order saddle points on the potential energy surfaces, govern the kinetics and mechanisms of chemical reactions an
arXiv:2506.05878v2 Announce Type: replace Abstract: We present a feasibility-seeking approach to neural network training. This mathematical optimization framework is distinct from conventional gradien
arXiv:2604.25979v1 Announce Type: cross Abstract: We present a quantitative analysis of character-pair substitution ratios in the Voynich manuscript, testing whether Currier's A/B language distinction
arXiv:2604.25943v1 Announce Type: cross Abstract: Efficient and stable solution of partial differential equations (PDEs) is central to scientific and engineering applications, yet existing numerical s
arXiv:2604.25963v1 Announce Type: new Abstract: Vehicle platooning has attracted increasing attention as a promising approach to improve traffic efficiency, energy consumption, and roadway safety thro
arXiv:2604.25933v1 Announce Type: cross Abstract: As large language models (LLMs) increasingly generate and process clinical text, scalable evaluation has become critical. LLM-as-a-Judge (LaaJ), which
arXiv:2604.07387v2 Announce Type: replace-cross Abstract: We present a design automation framework for analog circuit sizing that produces calibrated, topology-specific analytical equations from raw c
arXiv:2604.26703v1 Announce Type: cross Abstract: Standard density functional theory (DFT) routinely misclassifies the electronic ground state of correlated and structurally complex compounds, predict
arXiv:2604.25972v1 Announce Type: cross Abstract: In multi-agent reinforcement learning (MARL), the integration of a communication mechanism, allowing agents to better learn to coordinate their action
arXiv:2510.08049v3 Announce Type: replace-cross Abstract: Although Large Language Models (LLMs) exhibit advanced reasoning ability, conventional alignment remains largely dominated by outcome reward m
arXiv:2505.17342v2 Announce Type: replace Abstract: Safe Reinforcement Learning (SafeRL) is the subfield of reinforcement learning that explicitly deals with safety constraints during the learning and
arXiv:2505.10924v4 Announce Type: replace-cross Abstract: Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emul
arXiv:2604.26319v1 Announce Type: new Abstract: Stance detection identifies the attitude of a text author toward a given target. Recent studies have explored various LLM-based strategies for this task
arXiv:2604.26676v1 Announce Type: cross Abstract: We introduce a toolkit for uncovering spurious correlations between recording characteristics and target class in speech datasets. Spurious correlatio
arXiv:2511.19543v2 Announce Type: replace Abstract: Object handover is a common form of interaction that is widely present in collaborative tasks. However, achieving it efficiently remains a challenge
AI-led process modernization is redefining how enterprises deploy AI — moving beyond broad rollouts to embedding intelligence into specific, governed business processes that actually scale. But the li
arXiv:2604.26779v1 Announce Type: cross Abstract: RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central
arXiv:2604.26348v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image generation, yet their training is predominantly driven by full-reference objectives that en
arXiv:2509.11058v2 Announce Type: replace Abstract: Zero-Shot Video Anomaly Detection (ZS-VAD) requires temporally localizing anomalies without target domain training data, which is a crucial task due
Actual feedback we’ve gotten over the last few years: 2019: The what? For what? Why spend time on this? Maybe you should try doing something else. 2020: Why would you keep spending time on this? Will
arXiv:2601.11568v2 Announce Type: replace-cross Abstract: Training Large Language Models (LLMs) is highly memory-intensive due to optimizer state overhead. The FRUGAL framework mitigates this with gra
arXiv:2603.16496v2 Announce Type: replace Abstract: Large language model (LLM) agents increasingly rely on external memory to support long-horizon interaction, personalized assistance, and multi-step
arXiv:2604.26340v1 Announce Type: new Abstract: LoRA-MoE has emerged as an effective paradigm for parameter-efficient fine-tuning, combining the low training cost of LoRA with the increased adaptation
arXiv:2603.19470v2 Announce Type: replace-cross Abstract: Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and furthe
arXiv:2508.19900v2 Announce Type: replace Abstract: Offline reinforcement learning (RL) enables learning effective policies from fixed datasets without any environment interaction. Existing methods ty
arXiv:2604.26492v1 Announce Type: cross Abstract: Visual data compression is shifting from human-centered reconstruction to machine-oriented representation coding. In this setting, an image is often m
arXiv:2604.26326v1 Announce Type: cross Abstract: Reinforcement learning (RL) has unlocked complex reasoning abilities in large language models (LLMs). However, most RL algorithms suffer from performa
arXiv:2604.26571v1 Announce Type: new Abstract: Municipal solid waste incineration is increasingly central to urban waste management, yet its sustainability benefit depends on controlling carbon emiss
arXiv:2604.25965v1 Announce Type: cross Abstract: Deep learning models are widely deployed in safety-critical domains, but remain vulnerable to adversarial attacks. In this paper, we study the adversa
arXiv:2602.08826v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been widely applied to emotional support conversation (ESC). However, complex multi-turn support remains cha
arXiv:2604.00706v2 Announce Type: replace Abstract: Assessing the veracity of a claim made online is a complex and important task with real-world implications. When these claims are directed at commun
arXiv:2604.26522v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents exhibit systemic failures in compositional generalization, limiting their robustness in interactive environments
In corporate parlance, any metric on a chart that shows rapid, significant growth over a short period of time is known as a “hockey stick.” On Wednesday, Stripe Inc. Chief Executive Patrick Collison s
arXiv:2601.17617v3 Announce Type: replace-cross Abstract: LLM-powered search agents are increasingly being used for multi-step information seeking tasks, yet the IR community lacks empirical understan
Starting today, agents can now be Cloudflare customers. They can create a Cloudflare account, start a paid subscription, register a domain, and get back an API token to deploy code right away. Humans
AgentTrove is a newly released agentic dataset containing 1.7 million samples, designed to address the shortage of agentic datasets available on Hugging Face Hub. The dataset aims to support training
This post by Ethan Mollick likely discusses how advanced AI systems like hypothetical future GPT versions could autonomously execute complex, real-world tasks with minimal human direction, using a hum
arXiv:2604.25326v2 Announce Type: replace-cross Abstract: Speculative decoding enhances the inference efficiency of large language models (LLMs) by generating drafts using a small draft language model
AI automates tasks, not jobs, and when a task gets cheaper, demand for the job grows. AI cannot automate jobs end-to-end because it lacks autonomy and cannot operate without supervision. There is stil
IBM Research describes how artificial intelligence and accelerated computing are being applied to high-speed racing design, likely through collaboration with racing teams or manufacturers like Dallara
音声AIの素早さと賢さを両立できるか？ 私たち人間は会話の中で、言いたいことを全部まとめてから話し始めるのではなく、話しながら考えを整理していきます。応答の速い Speech-to-Speech モデルは、この「話しながら考える」を実現しましたが、そのぶん思考が浅くなりがちです。かといって知識豊富な LLM を挟むカスケード型では、遅延が生じるため「話しながら」が成立しません。 そこで Sakan
AI workflow automation is emerging as a critical solution for private markets as they undergo a structural shift. What was once the exclusive domain of institutional investors is now opening to thousa
This article from Latent Space discusses a pivotal shift in AI development toward inference—the computational process of running trained models—suggesting this represents a critical turning point comp
arXiv:2604.26567v1 Announce Type: new Abstract: Despite the rapid progress in data-driven 3D vision, aerial geometric 3D vision remains a formidable challenge due to the severe scarcity of large-scale
Alert fatigue occurs when security teams receive excessive alerts, causing them to miss critical threats due to desensitization and reduced response effectiveness. This represents a significant busine
alignment failure Fun fact - if you have a recent commit that mentions OpenClaw in a json blob, Claude Code will either refuse your request or bill you extra money. This is an empty repo, I'm just cal
alignment in 2016: obviously any real AI will be made inside a faraday cage magnetically suspended in a 10×10×10 cube of telekill alloy alignment in 2026: yeah we can not make it stop talking about go
I'm currently wearing a pair of smart glasses called the Even Realities G2. Another two pairs, from Rokid, sit on my desk. A few feet away, I've got the Meta Ray-Ban Display charging alongside their N
Allen AI released the OlmPool research series on Hugging Face, featuring early 7-8B parameter language model checkpoints trained on 150 billion tokens. The research explores how minor architectural mo
Annie Palmer / CNBC: Alphabet's stock climbed 10% on Thursday and 34% in April, its best month since 2004; Meta's stock plunged 8.5% on Thursday, its steepest drop since October — Alphabet's stock sur
Google LLC’s parent company Alphabet Inc. delivered a stunning earnings beat as it reported its first-quarter financial results today, with sales also surpassing expectations thanks to rampant growth
arXiv:2604.26337v1 Announce Type: new Abstract: Conceptual aircraft design is traditionally an expert-mediated iterative process in which a human designer proposes a configuration, runs low-order phys
arXiv:2604.26473v1 Announce Type: new Abstract: As with every emerging technology, new tools in the hands of artists reshape the nature of artwork creation. Current frameworks for robotics in arts dep
Shares of Amazon.com Inc. edged higher in late trading today after the company reported better-than-expected first-quarter earnings and revenue, as cloud computing sales topped analysts’ expectations.
arXiv:2604.26103v1 Announce Type: cross Abstract: All current LLM serving systems place the GPU at the center, from production-level attention-FFN disaggregation to NVIDIA's Rubin GPU-LPU heterogeneou
arXiv:2604.25920v1 Announce Type: cross Abstract: Despite their strong linguistic capabilities, Large Language Models (LLMs) are computationally demanding and require substantial resources for fine-tu
Financial Times: Analysis: Meta, Alphabet, Microsoft, and Amazon's combined capex hit a record 130B in Q1, and it is set to reach 725B in 2026, up 77% from $410B in 2025 — Meta stock drops on capex in