Knowledge catalogue
arXiv:2605.06997v1 Announce Type: new Abstract: Long chain-of-thought reasoning and agentic tool-calling produce traces spanning tens of thousands of tokens, yet Transformer KV caches grow linearly wi
arXiv:2605.07417v1 Announce Type: cross Abstract: Modern Deep Learning (DL) workloads are increasingly deployed in safety-critical domains, such as automotive systems and hyperscale data centers, wher
arXiv:2605.07488v1 Announce Type: new Abstract: The scaling of Large Multimodal Models (LMMs) is constrained by the quality-quantity trade-off inherent in synthetic data. Previous approaches, such as
arXiv:2605.07299v1 Announce Type: cross Abstract: Existing Multimodal Large Language Models (MLLMs) remain primarily reactive, failing to continuously perceive environments or proactively assist users
arXiv:2512.09629v2 Announce Type: replace Abstract: We present an end-to-end framework for planning supported by verifiers. An orchestrator receives a human specification written in natural language a
arXiv:2605.07247v1 Announce Type: new Abstract: Scalable AI agents training relies on interactive environments that faithfully simulate the consequences of agent actions. Manually crafted environments
arXiv:2602.01003v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a key training step for improving mathematical reasoning in large language models (LLMs), but it often
arXiv:2512.15567v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly applied to scientific research, yet prevailing science benchmarks probe decontextualized knowledge and
arXiv:2605.06669v1 Announce Type: cross Abstract: Educational LLM tutors face a core AI alignment challenge: they must follow user intent while preserving pedagogical constraints and safety policies.
Ever wished your agent could read PDFs, images, and Office documents as easily as plain text? Or combine the safety of a secure sandbox with the full power of Bash access? We built exactly that. Meet
arXiv:2512.12602v4 Announce Type: replace Abstract: In this paper, we introduce Exact Flow Linear Attention~(EFLA), an exact-flow formulation of delta-rule linear attention. We show that the delta-rul
arXiv:2603.06859v2 Announce Type: replace-cross Abstract: Removing an agent from a cooperative team to measure its contribution seems natural, yet in multi-agent LLM systems this evaluation distorts t
arXiv:2605.07485v1 Announce Type: cross Abstract: Extrapolation to out-of-distribution conditions is a fundamental challenge for physics-constrained deep generative models. Existing methods apply phys
arXiv:2605.07675v1 Announce Type: new Abstract: We introduce FactoryBench, a benchmark for evaluating time-series models and LLMs on machine understanding over industrial robotic telemetry. Q&A pairs
Falcon 9 is vertical at pad 40 in Florida ahead of tomorrow’s launch of Dragon’s 34th Commercial Resupply Services mission to the @Space_Station. Teams are keeping an eye on weather, which is currentl
arXiv:2605.07208v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used to brainstorm and evaluate research ideas, yet assessing such judgments is fundamentally difficult be
arXiv:2601.00889v2 Announce Type: replace Abstract: FANOS{} is a PyTorch optimizer that augments RMS-preconditioned momentum with a scalar feedback controller over update energy. The public reference
arXiv:2605.08044v1 Announce Type: cross Abstract: Recent byte-level language models (LMs) match the performance of token-level models without relying on subword vocabularies, yet their utility is limi
arXiv:2605.06982v1 Announce Type: new Abstract: Embedding models in natural language processing (NLP) increasingly rely on deep architectures such as BERT, while simpler models such as Word2Vec provid
arXiv:2509.24789v4 Announce Type: replace Abstract: The evaluation of time series forecasting models is hindered by a lack of high-quality benchmarks, leading to overestimated assessments of progress.
arXiv:2605.07145v1 Announce Type: cross Abstract: Vision-language models (VLMs) have shown strong potential for scientific image understanding, but general-purpose models often lack the domain-specifi
Fine-tuning on your proprietary data is the highest leverage thing you can do. Prompts get copied overnight. A model trained on your data, your evals, your edge cases is a strong moat. OpenAI is windi
arXiv:2603.19254v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in financial research workflows, where their role is evolving from single-model assistance fo
arXiv:2506.14951v4 Announce Type: replace-cross Abstract: The loss landscapes of neural networks contain minima and saddle points that may be connected in flat regions or appear in isolation. We ident
arXiv:2510.03245v2 Announce Type: replace-cross Abstract: State-of-the-art attribution methods rely on adversarial sample generation that applies an all-pass filter across the frequency spectrum, disc
arXiv:2605.07273v1 Announce Type: cross Abstract: Multimodal RAG systems increasingly rely on vision-language retrievers to ground visual queries in external textual evidence. Existing adversarial stu
arXiv:2605.07544v1 Announce Type: new Abstract: When you read a paper about a new Vision-Language Model today, it can be easy to forget how strange this idea would have sounded not so long ago. Teachi
arXiv:2605.07861v1 Announce Type: new Abstract: Makeup transfer aims to apply the makeup style of a reference portrait to a source portrait while preserving identity and background. Early methods form
arXiv:2605.07133v1 Announce Type: cross Abstract: Graph Anomaly Detection (GAD) is a critical task in graph machine learning with vital applications in financial fraud detection and social platform go
arXiv:2605.06734v1 Announce Type: cross Abstract: Fast Weight Programmers (FWPs) encode temporal dependencies through dynamically updated parameters rather than recurrent hidden states. Quantum FWPs (
arXiv:2605.07817v1 Announce Type: cross Abstract: Human visual reasoning is governed by active vision, a process where metacognitive control drives top-down goal-directed attention, dynamically routin
arXiv:2605.07329v1 Announce Type: new Abstract: We introduce GC-ART (Global Curve Adaptive Rational Tone-mapping), a lightweight differentiable pre-processing module for robust image classification. G
arXiv:2502.17500v3 Announce Type: replace-cross Abstract: This paper investigates in depth the fundamental properties of the two-parameter generalized Euler logarithm and its inverse, the associated d
arXiv:2605.07982v1 Announce Type: new Abstract: Ensuring safe, policy-compliant outputs from large language models requires real-time content moderation that can scale across multiple safety dimension
arXiv:2605.08022v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) have been proposed as biologically plausible and energy-efficient alternatives to conventional Artificial Neural Networ
arXiv:2410.06347v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) in robotics faces significant hurdles regarding sample efficiency and generalization across varying goals. While O
Criminal hackers have used artificial intelligence to develop a working zero-day exploit, the first confirmed case of its kind, according to a report released today by Google LLC’s Google Threat Intel
arXiv:2605.07366v1 Announce Type: new Abstract: Adaptive rank allocation for LoRA, allocating more parameters to important layers and fewer to unimportant ones, consistently improves efficiency under
arXiv:2605.06755v1 Announce Type: cross Abstract: Reinforcement learning is widely used to improve the reasoning ability of large language models, especially when answers can be automatically checked.
arXiv:2605.07689v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is a standard algorithm for reinforcement learning from verifiable rewards, but its group-mean-centered advant
arXiv:2605.07961v1 Announce Type: new Abstract: Federated fine-tuning (FFT) has emerged as a privacy-preserving paradigm for collaboratively adapting large language models (LLMs). Built upon federated
arXiv:2605.07999v1 Announce Type: cross Abstract: Multiphoton photoreduction enables high-fidelity fabrication of complex 3D microstructures, yet reliable process-structure-property (PSP) prediction r
arXiv:2605.07357v1 Announce Type: new Abstract: Reasoning-acting frameworks enhance large language models (LLMs) by interleaving reasoning with actions for dynamic information acquisition. However, ex
Grok just completely changed the game for real-time financial research. We just got the preview to 'Grok Skills,' and they look 10x more powerful than Claude Skills. In seconds, you can create workflo
arXiv:2605.07053v1 Announce Type: cross Abstract: Benchmarks like GSM8K are popular measures of mathematical reasoning, but leaderboard gains can overstate true capability due to memorization of fixed
Executive Summary Since our February 2026 report on AI-related threat activity, Google Threat Intelligence Group (GTIG) has continued to track a maturing transition from nascent AI-enabled operations
arXiv:2605.07209v1 Announce Type: cross Abstract: We introduce a proxy-analyzer framework for detecting hallucinations in large language models. Instead of looking inside the generating model, our sys
arXiv:2605.07397v1 Announce Type: new Abstract: After a somewhat rocky start, geometry and topology have established a foothold in machine learning. Message passing, either on graphs or higher-order c
arXiv:2605.07766v1 Announce Type: new Abstract: Many vision applications require identity consistency beyond strict biometric recognition, especially under non-frontal views or when facial cues are mi
HiDream-Studio v.01 was open-sourced on May 8, 2026, releasing the HiDream-O1-Image model (8B parameters) with both undistilled and distilled variants. HiDream-O1-Image is a unified image generative f
arXiv:2605.07512v1 Announce Type: new Abstract: Class-incremental learning aims to continuously acquire new knowledge while preserving previously learned information, thereby mitigating catastrophic f
arXiv:2605.07707v1 Announce Type: new Abstract: HTN planning is a variation of classical planning where, instead of searching for a linear sequence of actions, an algorithm decomposes higher-level tas
arXiv:2605.07266v1 Announce Type: cross Abstract: Wireless foundation models are rapidly emerging as a key enabler of AI-native communication systems, yet a fundamental question remains unanswered: ho
In early 2026, ChatGPT expanded its user base across broader demographics and industry sectors, moving beyond early adopters to mainstream adoption. The report likely documents growth metrics, new use
This guide from OpenAI outlines strategies and best practices for enterprises implementing and scaling artificial intelligence across their organizations. It likely covers topics such as infrastructur
arXiv:2605.05340v2 Announce Type: replace-cross Abstract: As Vision-Language Models (VLMs) are increasingly deployed as autonomous cognitive cores for embodied assistants, evaluating their privacy awa
arXiv:2605.07492v1 Announce Type: new Abstract: The past year has seen over 20 open-source document parsing models, yet thefield still benchmarks almost exclusively on OmniDocBench, a 1,355-pagemanual
arXiv:2605.06747v1 Announce Type: new Abstract: Progress in embodied intelligence increasingly depends on scalable data infrastructure. While vision and language have scaled with internet corpora, lea
arXiv:2605.07177v1 Announce Type: cross Abstract: Existing multimodal search agents process target entities sequentially, issuing one tool call per entity and accumulating redundant interaction rounds
🤯 i need all of you to stop what you're doing and look at this @webassembly + transformers.js + @googlegemma powered robot, running completely offline I think Reachy is the one who needs chess lessons