Knowledge catalogue
arXiv:2606.06453v1 Announce Type: new Abstract: Sparse attention is becoming increasingly important for serving large language models (LLMs) as generation lengths continue to grow. However, deploying
arXiv:2606.05725v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed through hosted APIs, making model extraction a practical threat to model ownership and service
arXiv:2606.05920v1 Announce Type: cross Abstract: Existing code-generation benchmarks score a single mapping from a complete prompt to a one-shot output. However, real web development is different. Us
arXiv:2606.06047v1 Announce Type: new Abstract: Errors in speech translations reduce trustworthiness of Speech Translation (ST) systems and can have serious consequences. Yet currently there is no est
Release b9528 of llama.cpp was published on June 5, 2026. This build includes a UI update to run npm install when package-lock.json is newer than node_modules, and provides pre-compiled binaries for m
The search did not return specific details about the b9535 release. Based on the available information, b9535 is an intermediate build version from the llama.cpp project, which is a C/C++ implementati
The search results don't contain specific information about release b9536, but I found related information about nearby releases in the llama.cpp project. Based on the pattern visible in the search re
arXiv:2606.05985v1 Announce Type: new Abstract: Multicultural multi-agent systems are increasingly deployed in globally diverse settings, where different agents are grounded in different cultural back
Building AI that Builds AI: Introducing the Sakana AI RSI Lab 🚀 https://sakana.ai/rsi-lab Today, we are announcing the Sakana AI Recursive Self-Improvement (RSI) Lab: a dedicated research group in Tok
arXiv:2606.05799v1 Announce Type: cross Abstract: Existing calibration methods for Large Language Models (LLMs) often overlook a critical dimension of trustworthiness: a model's {em behavioral robustn
arXiv:2410.13056v4 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable success across a wide range of language tasks, but their deployment on edge devices remain
arXiv:2504.10823v4 Announce Type: replace Abstract: Navigating dilemmas involving conflicting values is challenging even for humans in high-stakes domains, let alone for AI, yet prior work has been li
arXiv:2602.23845v2 Announce Type: replace Abstract: Chinese text correction has traditionally focused on spelling and grammar, while factual error correction is usually treated separately. However, in
arXiv:2606.05661v1 Announce Type: cross Abstract: Continual learning, the ability of AI systems to improve through sequential experience, has attracted substantial interest, but no high-quality benchm
arXiv:2606.05290v1 Announce Type: new Abstract: Recent progress in generative modeling has made safety control a central challenge, yet existing approaches remain largely model-specific, requiring ret
arXiv:2508.15851v2 Announce Type: replace Abstract: Despite rapid progress in large language models (LLMs), current QA benchmarks still overlook the core challenge of real-world scientific information
arXiv:2602.05056v2 Announce Type: replace-cross Abstract: Online scams increasingly leverage fluent and context-aware social engineering strategies, creating growing demand for AI systems that explain
arXiv:2606.05404v1 Announce Type: cross Abstract: Time series are often embedded in rich contexts that are essential for holistic modeling. Moreover, real-world practitioners often require end-to-end
arXiv:2407.10486v3 Announce Type: replace-cross Abstract: Query-focused summarization (QFS) aims to produce summaries that answer particular questions of interest, enabling greater user control and pe
arXiv:2606.06098v1 Announce Type: new Abstract: Foundational Large Language Models (LLMs) demonstrate proficiency on a wide range of general tasks, and achieve remarkable results on various specialize
arXiv:2606.06447v1 Announce Type: new Abstract: Large language models often improve reasoning by generating explicit chain-of-thought (CoT), demonstrating the importance of intermediate computation. H
arXiv:2603.07294v2 Announce Type: replace Abstract: Fine-grained understanding and species-specific multimodal question answering are vital for advancing biodiversity conservation and ecological monit
arXiv:2606.05443v1 Announce Type: cross Abstract: The rapid pace of scientific publishing has made the identification and synthesis of high-impact work an increasingly urgent challenge. We introduce M
arXiv:2606.06031v1 Announce Type: new Abstract: Masked diffusion language models generate text by iteratively unmasking many tokens in parallel, but this speed comes with a correction problem: tokens
arXiv:2606.06080v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards is widely used for post-training reasoning models, but sparse outcome rewards make exploration difficul
arXiv:2606.06260v1 Announce Type: cross Abstract: Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, adve
arXiv:2606.06096v1 Announce Type: cross Abstract: Policy-gradient methods usually optimize expected return, but many real world applications care about distributional properties of returns: tail risk,
arXiv:2601.02880v2 Announce Type: replace-cross Abstract: Every existing inference-time reasoning framework discards all failure context at problem boundaries, leaving a model solving problem 500 no w
arXiv:2606.06454v1 Announce Type: cross Abstract: Large language models increasingly write, review, and judge code, and a fast-growing practice equips them with prompt 'skills' that ask the model to r
arXiv:2606.05859v1 Announce Type: new Abstract: Latent reasoning has emerged as a promising alternative to discrete Chain-of-Thought (CoT) in large language models (LLMs), enabling more expressive rea
arXiv:2606.05194v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly being deployed to make decisions that require trading off near-term gains against long-term consequences
arXiv:2606.06188v1 Announce Type: new Abstract: Recent work has sought to understand Large Language Models (LLMs) reasoning, yet a principled, model-intrinsic signal that captures its layer-wise reaso
Google's RAG Engine securely connects private enterprise data to LLMs to improve answer accuracy and reduce hallucinations , making it a key component of the Gemini Enterprise Agent Platform for build
arXiv:2606.06444v1 Announce Type: cross Abstract: Audio encoders are critical to modern audio applications as large language models (LLMs) increasingly rely on a single encoder for diverse inputs. Whi
arXiv:2406.12620v3 Announce Type: replace Abstract: Do architectural and training differences influence the way models represent and process language? Traditional similarity metrics tell us whether tw
arXiv:2606.04619v1 Announce Type: new Abstract: We propose MONIR, a Modalized-Output Normative Intermediate Representation for ASP-based compliance reasoning. Its core fragment has a staged operationa
arXiv:2606.04177v1 Announce Type: cross Abstract: Interpretable linguistic features offer a promising approach for explaining why a given text appears machine-generated, particularly for non-expert us
And another open-weight release. Nemotron 3 Ultra has an ultra impressive capability:efficiency ratio! Design-wise, it carries forward the Mamba-2-attention hybrid stack and LatentMoE introduced in th
arXiv:2606.04522v1 Announce Type: cross Abstract: Approximate nearest neighbor (ANN) search has become a core primitive in information retrieval and modern machine learning tasks, from classification
B9500 is a release of llama.cpp that includes a Metal backend optimization reducing reset heartbeat timing from 500ms to 5ms . The release provides compiled binaries across multiple platforms includin
arXiv:2510.08647v2 Announce Type: replace-cross Abstract: Recent developments have enabled advanced reasoning in Large Language Models (LLMs) via long Chain-of-Thought (CoT), trading efficiency during
arXiv:2606.04952v1 Announce Type: cross Abstract: CARE-link is an open-source, web-based clinical support platform designed to improve the management of gestational diabetes by linking clinicians and
arXiv:2606.04223v1 Announce Type: new Abstract: Multi-agent systems are commonly designed to reduce disagreement through voting, consensus protocols, debate, or fault-tolerant aggregation. We argue th
arXiv:2606.04661v1 Announce Type: new Abstract: Prompts tuned for accuracy often grow long, raising inference cost on every model call. The best accuracy-cost trade-off depends on the task and the bud
arXiv:2601.22396v2 Announce Type: replace-cross Abstract: Despite the growing utility of Large Language Models (LLMs) for simulating human behavior, the extent to which these synthetic personas accura
arXiv:2606.05009v1 Announce Type: cross Abstract: Deontic reasoning is the task of answering questions by applying explicit rules and policies to case-specific facts, for example computing tax liabili
arXiv:2606.04115v1 Announce Type: cross Abstract: Quantizing large language models (LLMs) to low-precision floating-point representations is central to efficient deployment, yet applying a single bit-
arXiv:2603.16867v2 Announce Type: replace-cross Abstract: Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but th
arXiv:2606.04160v1 Announce Type: new Abstract: Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse to respond to harmful or disallowed r
arXiv:2603.07445v2 Announce Type: replace Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when
arXiv:2606.05101v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) models are critical for countering the malicious use of text-to-speech (TTS) models. Evaluating and strengthening ADD m
arXiv:2603.22121v2 Announce Type: replace-cross Abstract: Video Corpus Moment Retrieval (VCMR) aims to retrieve both the correct video and its temporal segment corresponding to a natural-language quer
arXiv:2601.06196v3 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate factually incorrect or unsupported content, commonly referred to as hallucinations. Prior wor
I am hooked on Dynamic Workflows! The idea of generating harnesses on the fly is so compelling that I reverse-engineered it for my agent orchestrator. And then I built a monitoring dashboard (as an HT
arXiv:2606.05030v1 Announce Type: new Abstract: Autoregressive chain-of-thought (CoT) reasoning in large language models (LLMs) is fundamentally forward-directed: each step conditions only on prior to
arXiv:2509.15676v2 Announce Type: replace-cross Abstract: In-context learning (ICL) has emerged as a powerful paradigm for adapting large language models (LLMs) to new and data-scarce tasks using only
arXiv:2606.04075v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a dominant post-training paradigm, enabling large language models (LLMs) to learn from rewards. We observe that
arXiv:2405.15454v4 Announce Type: replace Abstract: The prevalence of Large Language Models (LLMs) in critical applications highlights the need for controlled language generation methods that are both
arXiv:2606.04442v1 Announce Type: cross Abstract: AI systems increasingly need to combine two demanding capabilities: navigating multi-session conversation history and performing deep reading comprehe
arXiv:2606.04581v1 Announce Type: cross Abstract: Speculative inference (SPIN) was originally developed as an efficient architecture to accelerate Large Language Models (LLMs). In this work, we propos