Knowledge catalogue
arXiv:2606.03217v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning has become a widely used mechanism for eliciting multi-step reasoning in large language models by generating intermed
arXiv:2509.22854v2 Announce Type: replace Abstract: Implicit in-context learning (ICL) has newly emerged as a promising paradigm that simulates ICL behaviors in the representation space of large langu
arXiv:2603.16572v2 Announce Type: replace-cross Abstract: Agent skills extend local AI agents, such as Claude Code and OpenClaw, with additional functionality. Their growing popularity has led to dedi
arXiv:2606.00507v1 Announce Type: new Abstract: Recent advances in Speech Large Language Models (Speech LLMs) have significantly enhanced spoken language understanding and reasoning. However, their co
arXiv:2606.01899v1 Announce Type: cross Abstract: Wireless localization is a fundamental capability of sixth-generation (6G) networks. Conventional model-based methods require accurate modeling of the
MiniMax-M3 is a large language model capable of handling 1 million token contexts and multimodal inputs while maintaining efficient inference performance. Together AI's blog post discusses techniques
arXiv:2606.02427v1 Announce Type: cross Abstract: Existing evaluations of neural operators and in-context operator learning rely primarily on prediction error, but accurate output prediction does not
arXiv:2606.00105v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress on vision-language tasks, but they may also memorize and expose sensitive o
arXiv:2605.31105v1 Announce Type: new Abstract: Large language models (LLMs) with extended context lengths rely on the key-value (KV) cache to support attention over prior tokens. However, maintaining
arXiv:2510.07651v2 Announce Type: replace-cross Abstract: Large language models (LLMs) with extended context windows enable powerful applications but impose significant memory overhead, as caching all
arXiv:2605.29351v1 Announce Type: new Abstract: We study minimal attention-only transformers under all-token corruption and show they admit a two-stage empirical Bayes interpretation. A single attenti
arXiv:2512.17220v2 Announce Type: replace Abstract: Humans understand long and complex texts by relying on a holistic semantic representation of the content. This global view helps organize prior know
arXiv:2605.29141v1 Announce Type: cross Abstract: Traditional recommender systems (RecSys) primarily infer user preferences from implicit signals (such as clicks, watches, and purchases), often neglec
As AI agents handle increasingly complex tasks with extended context windows, the cost structure of LLM usage has shifted such that input tokens now represent the majority of price-equivalent expenses
arXiv:2605.28484v1 Announce Type: new Abstract: Composing finite-state transducers (FSTs) for context-dependent morphophonological rules -- consonant gradation, vowel harmony, possessive suffix assimi
arXiv:2605.27993v1 Announce Type: new Abstract: Object hallucination remains a primary obstacle to the reliable deployment of Multimodal Large Language Models (MLLMs). Current inference-time mitigatio
arXiv:2605.28073v1 Announce Type: cross Abstract: Story rewriting aims to adapt existing narratives to diverse reader preferences while preserving plot consistency and narrative coherence. Unlike conv
arXiv:2605.27243v1 Announce Type: new Abstract: Large vision-language models increasingly rely on long-context modeling to reason over documents, hour-level videos, and long-horizon agent trajectories
arXiv:2605.26159v1 Announce Type: cross Abstract: Large language models are increasingly used as orchestrators of external tools via the Model Context Protocol (MCP), but MCP is built for software ser
arXiv:2605.26678v1 Announce Type: new Abstract: Long-context language models are limited by the memory footprint of the key-value (KV) cache. Existing training-free KV compression methods usually rank
arXiv:2507.16679v3 Announce Type: replace-cross Abstract: In-Context Learning has shown great potential for aligning Large Language Models (LLMs) with human values, helping reduce harmful outputs and
arXiv:2605.26778v1 Announce Type: new Abstract: Retrieval-augmented generation promises to ground language model outputs in external evidence, yet the field has no reliable way to verify whether retri
arXiv:2605.24423v1 Announce Type: new Abstract: In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT
arXiv:2605.24331v1 Announce Type: new Abstract: Context or prompt-level reweighting has emerged as a central algorithmic lever in Reinforcement Learning with Verified Rewards (RLVR) for improving the
arXiv:2508.12538v2 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) has emerged as a universal standard that enables AI agents to seamlessly connect with external tools, signifi
arXiv:2605.22337v2 Announce Type: replace Abstract: The KV cache used in large language models has linearly growing time complexity, so LLMs face memory blow-up and reduced decoding efficiency when th
arXiv:2407.05682v2 Announce Type: replace Abstract: In-context learning (ICL) has been instrumental in adapting Large Language Models (LLMs) to downstream tasks using correct input-output examples. Re
arXiv:2605.24579v1 Announce Type: new Abstract: Long-context memory systems often fail under fixed budgets, but end-to-end evaluation does not reveal whether evidence was discarded during compression
arXiv:2605.23180v1 Announce Type: new Abstract: We propose to improve in-context learning (ICL) by optimizing the continuous embeddings of a fixed few-shot prompt at test time. The key observation is
arXiv:2605.22907v1 Announce Type: new Abstract: Real-world long video understanding requires models to perform continuous tracking, information integration and memory retention over massive temporal s
arXiv:2605.20730v1 Announce Type: new Abstract: In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks through demonstrations, yet it suffers from escalating inference cos
arXiv:2502.18915v3 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, they are of
arXiv:2602.16608v2 Announce Type: replace Abstract: Transformer models achieve state-of-the-art performance across domains and tasks, yet their deeply layered representations make their predictions di
arXiv:2512.14700v2 Announce Type: replace-cross Abstract: Online harassment is a widespread social and public health concern, yet most computational approaches for detecting and addressing harassment
arXiv:2601.15014v2 Announce Type: replace-cross Abstract: We study in-context learning for nonparametric regression with alpha-Holder smooth regression functions, for some alpha>0. We prove that, with
arXiv:2602.07570v2 Announce Type: replace-cross Abstract: Understanding how humans and artificial intelligence systems process complex narrative videos is a fundamental challenge at the intersection o
arXiv:2605.19514v1 Announce Type: new Abstract: Many works make the eye-catching claim that Transformers are Turing-complete. However, the literature often conflates two distinct settings: (i) a fixed
Databricks has launched the Context Engineer Associate certification, described as the industry's first credential specifically designed for professionals building reliable AI agent systems. The certi
arXiv:2605.18165v1 Announce Type: new Abstract: Unlike autoregressive models, which generate one token at a time, dLLMs denoise a chunk of [MASK] tokens jointly and sample one or more tokens per step;
arXiv:2602.11699v3 Announce Type: replace Abstract: Nonsensical and anomalous sentences have been instrumental in the development of computational models of semantic interpretation. A core challenge i
arXiv:2410.13846v3 Announce Type: replace-cross Abstract: Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. M
arXiv:2503.14800v3 Announce Type: replace-cross Abstract: Effective long-term memory management is crucial for language models handling extended contexts. We introduce the Enhanced Ranked Memory Augme
arXiv:2605.16360v1 Announce Type: cross Abstract: Efficient long-context inference in Large Language Models (LLMs) is severely constrained by the Key-Value (KV) cache memory wall, yet existing pruning
Autonomous security operations company Torq Ltd. today announced that it has acquired Jit.io Ltd., a cybersecurity startup whose technology generates AI-driven context graphs to inform security invest
arXiv:2604.02268v2 Announce Type: replace Abstract: Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a rel
arXiv:2605.15054v1 Announce Type: new Abstract: Vision-language models (VLMs) have recently emerged as a promising paradigm for video anomaly detection (VAD) due to their strong visual reasoning abili
arXiv:2605.13113v1 Announce Type: cross Abstract: Text-to-image (T2I) generative models are increasingly used to produce content for education, media, and public-facing communication, and are starting
arXiv:2605.12156v1 Announce Type: new Abstract: Automatic misinformation detection performs well when deception is visible in what an article explicitly states. However, some misinformation articles r
arXiv:2605.12185v1 Announce Type: new Abstract: Large language models accumulate extensive parametric knowledge through pre-training. However, knowledge conflicts occur when outdated or incorrect para
arXiv:2605.09268v1 Announce Type: cross Abstract: Users interacting with Large Language Models (LLMs) in a multi-turn conversation routinely refine their requests or pivot to new topics. LLMs, however
Cool idea from Nous Research. What if you could speed up long-context pretraining with a subquadratic wrapper that you remove before deployment? That is the idea behind Lighthouse Attention. The metho
arXiv:2605.10230v1 Announce Type: new Abstract: Molecular optimization seeks to improve a molecule through small structural edits while preserving similarity to the starting compound. Recent language-
arXiv:2511.01292v2 Announce Type: replace-cross Abstract: Pretrained Transformers can perform in-context learning (ICL) from a few demonstrations, but this ability can fail sharply when the test distr
arXiv:2605.10235v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have expanded the context window to beyond 128K tokens, enabling long-document understanding and multi-s
arXiv:2605.10114v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents (e.g., OpenClaw) increasingly rely on reusable skill libraries to solve artifact-rich tasks such as document-cen
Aisha Malik / TechCrunch: Threads is testing a Meta AI integration similar to X's Grok, letting users mention Meta AI in a post or a reply to get more context, in five countries — Threads is testing a
arXiv:2603.22586v2 Announce Type: replace Abstract: In-context learning (ICL) enables task adaptation at inference time by conditioning on demonstrations rather than updating model parameters. Althoug
arXiv:2605.07719v1 Announce Type: cross Abstract: Long-context inference increasingly operates over CPU-resident KV caches, either because decoding-time KV states exceed GPU memory capacity or because
Cursor is an AI-powered code editor that analyzes entire conversation threads to understand context before generating solutions and automatically creating pull requests for team review. This feature s
arXiv:2605.06920v1 Announce Type: cross Abstract: We propose incentive-aligned mechanisms for in-context credit assignment: the task of assigning credit for AI-generated content (e.g. code, news artic