Knowledge catalogue
arXiv:2608.16515v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves large language models by grounding generation in external evidence, but it also introduces a source trus
🆕 Context Engineering in 2026: Compaction, Memory & Cost https://www.youtube.com/watch?v=WP3hjUXd918 @Whats_AI, @samridhivaid and @omar_solano1 return! This workshop is about engineering the context w
arXiv:2608.13897v1 Announce Type: cross Abstract: Lossless compression of volumetric medical images is of paramount importance for clinical and research applications where data fidelity is essential.
DeepSeek V4 Pro (Aug 2026) has been released on the Together AI platform. The model employs a 1.6‑terabyte Mixture‑of‑Experts architecture with a 1‑million‑token context window and supports three dist
arXiv:2608.04956v1 Announce Type: new Abstract: Recent video models increasingly support generation, reference conditioning, and editing within a single model, yet typically expose them as separate op
arXiv:2608.03210v1 Announce Type: new Abstract: Foundation models have achieved remarkable success across diverse tasks, but they remain vulnerable. To investigate such vulnerabilities, semantic-shift
arXiv:2608.03234v1 Announce Type: new Abstract: Motion priors provide powerful guidance for learning naturalistic humanoid behaviors. However, existing methods typically learn a general, task-agnostic
arXiv:2608.01676v1 Announce Type: new Abstract: Sparse attention is widely deployed in long-context serving stacks, yet no framework audits how discarding blocks changes the influence of specific cont
arXiv:2607.19345v2 Announce Type: replace-cross Abstract: Large language models that generate step-by-step reasoning traces have achieved strong performance on complex tasks, and extending them to lon
arXiv:2607.28263v1 Announce Type: new Abstract: Transformer depth is not used uniformly: lower and middle layers build semantic representations, while upper layers increasingly specialize them for pre
arXiv:2607.23304v1 Announce Type: cross Abstract: Modern predictive systems are expected to adapt their behavior to the specific situation they are facing. A clinical model should not treat every pati
arXiv:2607.12896v1 Announce Type: new Abstract: Medical image segmentation foundation models are expected to generalize across diverse clinical scenarios, yet existing universal methods remain fragmen
arXiv:2607.08284v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated rapidly improving long-context capabilities, prompting a wave of benchmarks designed to evaluate them. Ho
arXiv:2607.07038v1 Announce Type: new Abstract: Medical image segmentation models can achieve strong benchmark performance while remaining sensitive to scanner, protocol, and institutional variation.
arXiv:2603.17484v2 Announce Type: replace Abstract: Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on l
arXiv:2603.24690v2 Announce Type: replace Abstract: In-context learning (ICL) enables fast task adaptation from demonstrations without per-task parameter updates but remains highly sensitive to exampl
// ReContext // Models now support 128K context windows and still fail to use evidence that is already in the prompt. Where is the gap? New paper introduces ReContext, a training-free inference harnes
arXiv:2607.01538v1 Announce Type: new Abstract: Language models (LMs) raise an intriguing alternative to vector-based retrieval: conditioning on an in-context corpus and directly generating a relevant
arXiv:2607.02073v1 Announce Type: new Abstract: Long-context reasoning requires models to locate, revise, and synthesize evidence distributed across lengthy inputs. Existing long-context RL methods us
arXiv:2607.00725v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) under a fixed reader-context budget forces a selection problem: of the evidence retrieved, only a fraction can be s
arXiv:2606.21649v2 Announce Type: replace Abstract: Existing embedding models are inherently static: they encode text segments in isolation, ignoring their surrounding context and temporal order. This
arXiv:2606.26171v1 Announce Type: cross Abstract: Recent image generation models achieve impressive quality in single-image synthesis, but often fail to maintain consistency across sequential outputs,
arXiv:2606.22072v1 Announce Type: new Abstract: Apparent emotion in natural images is often not visible from the face alone. The face may be small, hidden, or neutral, while posture and scene context
arXiv:2606.11473v1 Announce Type: cross Abstract: Prior-fitted networks (PFNs) are a promising class of tabular foundation models that perform in-context learning, whereby the entire labelled training
arXiv:2606.06758v1 Announce Type: new Abstract: Final-answer accuracy, retrieval recall, and citation overlap do not by themselves identify whether a long-context or retrieval-augmented language model
arXiv:2606.05332v1 Announce Type: new Abstract: Patch-based Time Series Foundation Models (TSFMs) suffer from context poisoning: structurally anomalous patches capture disproportionate attention and s
arXiv:2606.02780v1 Announce Type: new Abstract: The success of the transformer architecture as the backbone of modern LLMs is in large part due to its use of attention layers. An attention layer follo
arXiv:2606.03078v1 Announce Type: new Abstract: Effective document-level machine translation (DocMT) requires capturing long-range discourse dependencies. Recent work has explored retrieval-based and
arXiv:2606.03329v1 Announce Type: new Abstract: Long-context tasks require LLMs to identify and preserve answer-relevant information from large contexts. Chunk-wise memory agents address this issue by
arXiv:2602.07721v3 Announce Type: replace-cross Abstract: KV-cache retrieval is essential for long-context LLM inference, yet existing methods struggle with distribution drift and high latency at scal
arXiv:2605.28854v1 Announce Type: new Abstract: Large language models (LLMs) exhibit remarkable flexibility: they can adapt to novel tasks from in-context examples without any parameter updates, a cap
arXiv:2605.29610v1 Announce Type: cross Abstract: In scene graph generation, a central challenge is modeling polysemous predicates whose meanings shift across contexts. Prior approaches address this i
arXiv:2605.27450v1 Announce Type: cross Abstract: Modern industrial recommender systems use a deep ranking model to score N candidates against the same user and context features. Standard implementati
Took some inspiration from @vboykis and converted my first ever talk into a blog post. I talk about the role of agentic search in context engineering. Together we build an intuition on the strengths a
arXiv:2605.23928v1 Announce Type: new Abstract: We present Context, the intelligence layer of the Magarshak Architecture, which replaces reactive query-response chatbots with proactive goal-directed a
arXiv:2605.23170v1 Announce Type: cross Abstract: Position-controlled evaluation is standard for retrieval tasks such as Needle-in-a-Haystack and RULER, but mainstream reasoning benchmarks do not cont
arXiv:2605.23081v1 Announce Type: new Abstract: Efficient attention algorithms are critical to mitigate the quadratic cost of attention in long-context workloads. Prior work utilises block-scaled quan
Unified AI service management lives or dies on context — and that context demands consolidating fragmented tools, data and operations into a single foundation. That consolidation imperative is now the
arXiv:2605.18856v1 Announce Type: cross Abstract: Long-context inference is increasingly constrained by the KV cache: resident memory grows with context length, and decoding becomes limited by repeate
arXiv:2605.15514v1 Announce Type: cross Abstract: We identify intrinsic limitations of Rotary Positional Embeddings (RoPE) in Transformer-based long-context language models. Our theoretical analysis a
arXiv:2601.22868v3 Announce Type: replace Abstract: Anomaly detection usually assumes that abnormality is an intrinsic property of an observation. A defect is a defect, and a rare object is rare, rega
arXiv:2602.17739v3 Announce Type: replace-cross Abstract: Long-context DNA models are limited by token-mixing cost and by how compression allocates representational budget across the genome. Existing
arXiv:2605.09867v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit a strong capacity for in-context learning: Given labeled examples, they can generate good predictions without par
arXiv:2602.02494v2 Announce Type: replace Abstract: Clinical brain-to-text interfaces are designed for paralysed patients who cannot provide extensive training recordings. Pre-training improves data-e
arXiv:2605.10377v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning often assumes a fixed execution team, yet many decentralized systems must operate with varying numbers of
arXiv:2605.08217v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) have borrowed the long context paradigm from natural language processing under the premise that feeding more histo
arXiv:2605.08505v1 Announce Type: cross Abstract: We study the long-context limit of softmax self-attention with a fixed query and a random context of n i.i.d. keys on the sphere, viewing the inverse
arXiv:2605.08563v1 Announce Type: new Abstract: When an LLM agent fails a multi-step tool-augmented task and retries, the failed attempt typically remains in its context window -- contaminating the ne
arXiv:2505.22842v4 Announce Type: replace Abstract: Transformer-based language models rely on positional encoding (PE) to handle token order and support context length extrapolation. However, existing
arXiv:2604.25313v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) models frequently produce answers grounded in parametric memory rather than the retrieved context, undermining the
arXiv:2409.01579v2 Announce Type: replace-cross Abstract: Retrieved documents containing noise will hinder RAG from detecting answer clues and make the inference process slow and expensive. Therefore,
arXiv:2604.24647v1 Announce Type: cross Abstract: Long-context reasoning is a critical capability of large language models (LLMs), enabling applications such as long-document understanding, summarizat
arXiv:2604.23972v1 Announce Type: cross Abstract: Knowledge graphs (KGs) are increasingly used to support large lan guage model (LLM) reasoning, but standard triplet-based KGs treat each relation as g
arXiv:2505.02922v3 Announce Type: replace Abstract: Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and band
arXiv:2601.16746v3 Announce Type: replace-cross Abstract: LLM agents have demonstrated remarkable capabilities in software development, but their performance is hampered by long interaction contexts,
arXiv:2604.22575v1 Announce Type: new Abstract: Scaling context length is reshaping large-model development, yet full-attention Transformers suffer from prohibitive computation and inference bottlenec
arXiv:2511.07752v3 Announce Type: replace Abstract: Contextual predictability shapes how we choose and encode words in production. The effects of a word's predictability given preceding or past contex
arXiv:2604.16395v2 Announce Type: replace-cross Abstract: Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting fo
arXiv:2604.19769v1 Announce Type: cross Abstract: Key-value (KV) caching is critical for efficient inference in large language models (LLMs), yet its memory footprint scales linearly with context leng
arXiv:2604.18758v1 Announce Type: new Abstract: Low-resource machine translation requires methods that differ from those used for high-resource languages. This paper proposes a novel in-context learni