b8833
Release b8833 of llama.cpp includes updates to the ggml-webgpu backend, fixing compiler warnings and refactoring FlashAttention encoding, along with workflow improvements and precision adjustments for
Knowledge catalogue
Release b8833 of llama.cpp includes updates to the ggml-webgpu backend, fixing compiler warnings and refactoring FlashAttention encoding, along with workflow improvements and precision adjustments for
arXiv:2601.21003v2 Announce Type: replace Abstract: Large Language Models usually put more emphasis on accuracy and therefore, will guess even when not certain about the prediction, which is especiall
arXiv:2601.07338v2 Announce Type: replace Abstract: Large Language Models (LLMs) have significantly advanced Machine Translation (MT), applying them to linguistically complex domains-such as Social Ne
arXiv:2604.14389v1 Announce Type: new Abstract: Automated fact-checking in dialogue involves multi-turn conversations where colloquial language is frequent yet understudied. To address this gap, we pr
arXiv:2604.13814v1 Announce Type: cross Abstract: Recent advances in artificial intelligence (AI) have shown promise in automating key aspects of Agile project management, yet their impact on team cog
arXiv:2604.14556v1 Announce Type: new Abstract: Video object insertion is a critical task for dynamically inserting new objects into existing environments. Previous video generation methods focus prim
In support of our mission to accelerate the developer journey on Google Cloud, we built Dev Signal: a multi-agent system designed to transform raw community signals into reliable technical guidance by
Data Driven Agent Design with Evals & Hill Climbing Algorithms this is a mental model dump i’ve been thinking through + iterating on as we’re building self-improvement infra around agents: - mining Tr
arXiv:2604.14552v1 Announce Type: cross Abstract: Modern datacenters increasingly rely on low-power, single-slot inference accelerators to balance performance, energy efficiency, and rack density cons
arXiv:2411.00361v4 Announce Type: replace Abstract: Hierarchical reinforcement learning (HRL) enables agents to solve complex, long-horizon tasks by decomposing them into manageable sub-tasks. However
arXiv:2602.22175v2 Announce Type: replace Abstract: Understanding and reasoning over long contexts is a crucial capability for language models (LMs). Although recent models support increasingly long c
arXiv:2604.14165v1 Announce Type: new Abstract: We present EviSearch, a multi-agent extraction system that automates the creation of ontology-aligned clinical evidence tables directly from native tria
arXiv:2604.14970v1 Announce Type: new Abstract: Hate, derogatory, and offensive speech remains a persistent challenge in online platforms and public discourse. While automated detection systems are wi
arXiv:2604.13048v1 Announce Type: cross Abstract: Modern cloud-native platforms expose thousands of time series metrics through systems like Prometheus, yet formulating correct queries in domain-speci
arXiv:2604.13888v1 Announce Type: new Abstract: The integration of Large Language Models (LLMs) into Geographic Information Systems (GIS) marks a paradigm shift toward autonomous spatial analysis. How
Tower of Babel is a GitHub repository by researcher Ethan Mollick that likely explores how AI language models handle multilingual tasks and cross-language communication, potentially investigating chal
in 1996 mitzenmacher showed that sampling two backends and picking the better one drops max load exponentially vs. random selection one extra comparison. that's the whole trick we built pinecone assis
ICLR 2026 is a major international conference on machine learning and deep learning where Apple's research team will present their latest work and innovations in representation learning. The conferenc
arXiv:2601.11227v2 Announce Type: replace Abstract: Output diversity is crucial for Large Language Models as it underpins pluralism and creativity. In this work, we reveal that controlling the languag
arXiv:2604.14034v1 Announce Type: cross Abstract: Recent advances in Generative Artificial Intelligence, particularly Large Language Models (LLMs), have stimulated growing interest in automating or as
Last week, Anthropic announced Project Glasswing alongside Claude Mythos Preview, a model they described as so powerful at finding vulnerabilities they couldn't release it. The announcement featured A
arXiv:2512.04578v3 Announce Type: replace Abstract: Legal general intelligence (GI) refers to artificial intelligence (AI) that encompasses legal understanding, reasoning, and decision-making, simulat
arXiv:2509.26007v2 Announce Type: replace-cross Abstract: Research on audio generation has progressively developed along both waveform-based and spectrogram-based directions, giving rise to diverse st
arXiv:2604.15190v1 Announce Type: cross Abstract: Simulating group-level user behavior enables scalable counterfactual evaluation of merchant strategies without costly online experiments. However, bui
arXiv:2604.14866v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated significant potential in medical image analysis, yet their application in intraoral photography remains
arXiv:2604.13699v1 Announce Type: cross Abstract: Large language models (LLMs) have enabled agentic AI systems for scientific discovery, but most approaches remain limited to textbased reasoning witho
arXiv:2604.14375v1 Announce Type: new Abstract: Catastrophic forgetting remains a primary hurdle in sequential task learning for artificial neural networks. We propose a silicon-native modular archite
arXiv:2601.15488v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit social biases, which can lead to harmful stereotypes and unfair outcomes. We propose extbf{Multi-Persona Thinki
arXiv:2604.14825v1 Announce Type: cross Abstract: We present Nautilus, a novel tensor compiler that moves toward fully automated math-to-kernel optimization. Nautilus compiles a high-level algebraic s
arXiv:2604.14965v1 Announce Type: new Abstract: Efficiently locating target objects in complex indoor environments with diverse furniture, such as shelves, tables, and beds, is a significant challenge
arXiv:2604.15272v1 Announce Type: cross Abstract: This paper presents Prism, the first symbolic superoptimizer for tensor programs. The key idea is sGraph, a symbolic, hierarchical representation that
arXiv:2506.03487v3 Announce Type: replace-cross Abstract: Reranking is fundamental to information retrieval and retrieval-augmented generation, with recent Large Language Models (LLMs) significantly a
arXiv:2604.14634v1 Announce Type: new Abstract: Multiple choice evaluation is widely used for benchmarking large language models, yet near ceiling accuracy in low option settings can be sustained by s
arXiv:2604.15151v1 Announce Type: new Abstract: Large language models have demonstrated strong performance on general-purpose programming tasks, yet their ability to generate executable algorithmic tr
arXiv:2604.14885v1 Announce Type: new Abstract: Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigate
arXiv:2603.21094v3 Announce Type: replace Abstract: Human annotation is central to NLP evaluation, yet subjective tasks often exhibit substantial variability across annotators. While large language mo
Renuka Kumar and Prashanth Ramagopal from the @Cisco team built a LangSmith + LangGraph powered framework for multi-agent coordination that behaves like a real-world software team. An inside look → ht
arXiv:2604.14616v1 Announce Type: new Abstract: Clinical value set authoring -- the task of identifying all codes in a standardized vocabulary that define a clinical concept -- is a recurring bottlene
arXiv:2604.14373v1 Announce Type: new Abstract: Rural environmental risks are shaped by place-based conditions (e.g., housing quality, road access, land-surface patterns), yet standard vulnerability i
arXiv:2604.13474v1 Announce Type: cross Abstract: We propose a novel end-to-end privacy-preserving framework, instantiated by three efficient protocols for different deployment scenarios, covering bot
arXiv:2502.21029v2 Announce Type: replace-cross Abstract: Reliable localization of people is fundamental for service and social robots that must operate in close interaction with humans. State-of-the-
arXiv:2604.14672v1 Announce Type: new Abstract: Large language models (LLMs) are being increasingly used in urban planning, but since gendered space theory highlights how gender hierarchies are embedd
Ethan Mollick observes that an AI system (likely Claude or another large language model) still declines to write sestinas, suggesting that certain behavioral constraints or limitations persist despite
arXiv:2512.24968v4 Announce Type: replace-cross Abstract: Generative AI can adversely impact news publishers by lowering consumer demand. It can also reduce demand for newsroom employees, and increase
arXiv:2506.09457v3 Announce Type: replace Abstract: Direct Alignment Algorithms (DAAs), such as Direct Preference Optimization (DPO) and Simple Preference Optimization (SimPO), have emerged as efficie
arXiv:2604.14550v1 Announce Type: cross Abstract: Generating synthesizable Verilog for large, hierarchical hardware designs remains a significant challenge for large language models (LLMs), which stru
🇺🇸 xAI just dropped a real-time speech-to-text model built for voice apps: high limits, multi-language support, the works. Priced at just 0.10–0.20/hour, crushing most competitors. Quiet release, loud
arXiv:2604.13057v1 Announce Type: new Abstract: For millions of users in developing economies who depend on mobile banking as their primary gateway to financial services, app quality directly shapes f
arXiv:2508.00555v2 Announce Type: replace-cross Abstract: Jailbreaking is an essential adversarial technique for red-teaming these models to uncover and patch security flaws. However, existing jailbre
arXiv:2604.13991v1 Announce Type: new Abstract: Large language models (LLMs) are prone to generating factually incorrect outputs. Recent work has applied conformal prediction to provide uncertainty es
Agent evals are drifting away from production reality. Most benchmarks use clean tasks, well-specified requirements, deterministic metrics, and retrospective curation. Production work is messier, with
arXiv:2601.13115v2 Announce Type: replace Abstract: Large Language Models (LLMs) have become a popular interface for human-AI interaction, supporting information seeking and task assistance through na
arXiv:2604.13346v1 Announce Type: new Abstract: Language-model agent systems commonly rely on reactive prompting, in which a single instruction guides the model through an open-ended sequence of reaso
arXiv:2604.13133v1 Announce Type: new Abstract: Thermodynamic cycles are pivotal in determining the efficacy of energy conversion systems. Traditional design methodologies, which rely on expert knowle
arXiv:2604.13068v1 Announce Type: new Abstract: When do large language models decide to hallucinate? Despite serious consequences in healthcare, law, and finance, few formal answers exist. Recent work
arXiv:2604.13634v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by letting draft tokens bypass full verification, but conventional frameworks suffer from fre
arXiv:2604.13804v1 Announce Type: new Abstract: The rapid evolution of multimodal large models has revolutionized the simulation of diverse characters in speech dialogue systems, enabling a novel inte
arXiv:2512.20481v4 Announce Type: replace-cross Abstract: To maintain coherence in language, the brain must satisfy key competing temporal demands: the gradual accumulation of meaning across extended
arXiv:2604.14044v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) excel in general vision-language tasks, their application to remote sensing change understanding is hinde
arXiv:2604.13075v1 Announce Type: new Abstract: Effective de-escalation is critical for law enforcement safety and community trust, yet traditional training methods lack scalability and realism. While