Knowledge catalogue
Learning from data as we observe it is easy for humans, but most machine learning models have limited ability to learn from new data that they have not seen during training. Prior-fitted networks (the
arXiv:2610.05940v1 Announce Type: new Abstract: Despite their impressive performance on a wide range of video understanding tasks, current Vision Language Models (VLMs) are predominantly designed for
arXiv:2610.04929v1 Announce Type: new Abstract: Robot agents must connect their intended actions to observed outcomes while retaining the context needed to revise their choices over repeated attempts.
arXiv:2610.05492v1 Announce Type: new Abstract: Vision-language-action (VLA) models have shown strong potential as generalist robot policies, but adapting them to unseen tasks often requires costly pa
arXiv:2610.02233v1 Announce Type: cross Abstract: Cross-context KV-cache reuse predicts a shared segment's keys and values under a new prefix instead of recomputing them, and has been reported to do s
arXiv:2610.02614v1 Announce Type: new Abstract: AI models serving a heterogeneous population must act on the principles appropriate to each user and context. While post-training has been shown to narr
arXiv:2610.01269v1 Announce Type: new Abstract: Bayesian Optimisation (BO) is a powerful framework for the optimisation of expensive black-box functions, but typically requires refitting a surrogate a
arXiv:2610.01831v1 Announce Type: new Abstract: Group attention, introduced by the time series forecasting model Chronos-2, attends over the variates of a group at a fixed patch index and serves both
arXiv:2609.39953v1 Announce Type: new Abstract: Omni-modal large language models (OmniLLMs) enable unified audio-video understanding, but their long multimodal token sequences make deployment computat
arXiv:2609.38958v1 Announce Type: new Abstract: Large language models (LLMs) have been rapidly improving in long-context tasks, powered by Chain-of-Thought (CoT) reasoning. However, the internal mecha
arXiv:2609.37195v1 Announce Type: new Abstract: Handwritten Text Recognition (HTR) systems have become an indispensable tool for the digitization of historical documents. Not only do they cut down tim
arXiv:2609.36012v1 Announce Type: new Abstract: General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL)
arXiv:2609.37660v1 Announce Type: new Abstract: We study nonpreemptive contextual queueing bandits in a single-server system. Each job is represented by a d-dimensional context vector; in each round,
arXiv:2609.36968v1 Announce Type: new Abstract: Unsupervised tabular anomaly detection (TAD) aims to identify anomalous rows in tabular data using normal training samples. While conventional methods r
Perplexity AI released a preview of its embedding model “pplx‑embed‑v2‑context‑9b” on Hugging Face on September 30, 2026 (7:07 PM local time). The Hugging Face repository page displays 3 122 views and
arXiv:2609.32663v1 Announce Type: new Abstract: The memory usage and decoding latency of LLM inference grow rapidly with context length. To reduce these costs, key-value (KV) cache compression methods
arXiv:2609.31381v1 Announce Type: new Abstract: Context projection replaces older tool observations with compact, addressable excerpts, reducing repeated input while potentially adding evidence-retrie
arXiv:2609.30243v1 Announce Type: new Abstract: Dedicated decision models such as Jev map unstructured language to probability distributions over finite choices, allowing their outputs to directly rou
arXiv:2609.29913v1 Announce Type: new Abstract: Many-shot in-context learning (ICL) enables large language models (LLMs) to adapt to complex tasks by conditioning on thousands of demonstration example
arXiv:2609.27590v1 Announce Type: new Abstract: Long-context evaluations often test whether a model can recover distant evidence, but recoverability does not guarantee behavioral influence. We test th
Knowledge graphs can give enterprise agents a shared understanding of how data, business rules and processes fit together. However, that context becomes harder to maintain when each new agent carries
arXiv:2609.25537v1 Announce Type: new Abstract: Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing latenc
arXiv:2609.26219v1 Announce Type: cross Abstract: Long-running LLM agent workflows often revise interior context spans while retaining long suffixes. Although suffix tokens remain unchanged, altered c
Must-read papers of the week ▪️ JEPA-Anything ▪️ Modality-Autoregressive World-Action Models ▪️ In-Context Robot Learning with VLM Agents ▪️ Dream-RSI: Recursive Self-Improvement through Evolving Worl
arXiv:2609.22452v1 Announce Type: new Abstract: Long-context understanding remains a fundamental challenge for large language models, as excessively long inputs often lead models to forget salient inf
arXiv:2609.17346v1 Announce Type: cross Abstract: To answer questions outside of their pre-training data, large language models (LLMs) need access to new information, which can be presented in the con
arXiv:2609.15126v1 Announce Type: cross Abstract: Scaling large language models efficiently has motivated sparse capacity mechanisms such as Mixture-of-Experts and, more recently, conditional memory:
arXiv:2609.13205v1 Announce Type: cross Abstract: Sparse long-context inference requires efficient token retrieval in both prefill and decode. Existing methods often use different retrieval strategies
arXiv:2609.11607v1 Announce Type: new Abstract: When forecasting a firm's future financial performance, alternative data - data collected from non-traditional sources such as consumer transactions, we
arXiv:2609.10810v1 Announce Type: new Abstract: Minimal-edit Grammatical Error Correction (GEC) is a challenging task for zero- and few-shot prompted Large Language Models (LLMs), which systematically
arXiv:2609.07334v1 Announce Type: new Abstract: The Asset Administration Shell (AAS) is a cornerstone of Industry 4.0 and the Digital Product Passport, providing standardized digital representations o
arXiv:2609.08574v1 Announce Type: cross Abstract: Long context language models now advertise windows of one million tokens, but two habits limit how much of that window is used. Attention heads with n
Security data platform company Gravwell Inc. today released Gravwell 5.10, an update that puts five artificial intelligence agents inside a customer’s deployment. The agents collect the context an inv
arXiv:2609.05764v1 Announce Type: cross Abstract: The key-value (KV) cache is the dominant memory bottleneck in long-context large language model (LLM) decoding: every step reads it entirely, so decod
arXiv:2609.10395v1 Announce Type: new Abstract: This paper describes the Rosetta system for Subtask 1 (Context-Aware English-to-Dialectal Arabic Dialogue Translation) of the AlexandriaX shared task, p
arXiv:2609.06772v1 Announce Type: cross Abstract: Ensemble fuzzing runs multiple fuzzers on a target while a scheduler allocates CPU time among them. Existing schedulers base these decisions on compac
arXiv:2503.15895v2 Announce Type: replace Abstract: This paper investigates whether sequential context improves goal-conditioned Reinforcement Learning in sparse-reward manipulation tasks. While Hinds
arXiv:2609.08080v1 Announce Type: new Abstract: Ensuring safety in reinforcement learning under nonstationarity requires anticipating changes in risk before they lead to unsafe behavior. Existing appr
I've been running Claude Code as my daily driver and wanted Ollama models in the loop without giving up the harness. So I built gremlord, a small Go binary that points the unmodified claude binary at
arXiv:2609.08981v1 Announce Type: new Abstract: A growing body of work establishes that large language models are not mere statistical memorizers, but are capable of in-context learning: performing in
An update to my previous post on running Flash-Next with the expert cache and MTP. I found another useful improvement on the same dual-3090 setup: replacing the CUDA top-k fallback used by my build. O
arXiv:2609.05152v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances language models with external knowledge, but the lengthy retrieved context inflates the input and degrades
arXiv:2606.12807v2 Announce Type: replace Abstract: Summaries of real-world events can become outdated as contexts evolve and new information arrives. A common response is to generate a new summary fr
So after all my work, yeah, Raymond did it better, so I ported his work over, extended it turboX, extended it multiple other models (he had only Qwen models), and benchmarked the crap out of it to mak
Hiya, NInfer is amazng for Qwen, but lacking for real-world-use. As adoption of issues/pr's was not really what I needed, I created a fork and hit it for this week with 3 concurrent claude code sessio
This is very similar to how we think about context management in Deep Agents: compaction should reduce what is sent to the model, not erase the underlying work history. In Deep Agents, the logic is: -
arXiv:2609.01772v1 Announce Type: new Abstract: Meme understanding goes beyond recognizing visual content or literal text; it requires implicit cultural knowledge and pragmatic inference that most vis
This was my first serious attempt at tuning a local LLM. I started because Qwen3.8-27B IQ3 was fast on my RTX 5080 but the coding quality disappointed me, and the Q4 profiles I tried in LM Studio were
arXiv:2602.18493v2 Announce Type: replace-cross Abstract: Long-context LLMs and Retrieval-Augmented Generation defer state tracking and evidence consolidation to query time, which is brittle when fact
arXiv:2608.30689v1 Announce Type: new Abstract: Autoregressive large models have recently advanced Text-to-SVG generation from simple icons to complex, long-context graphics, yet standard autoregressi
arXiv:2608.30315v1 Announce Type: cross Abstract: Token embeddings are the basic representational units that connect discrete tokens with continuous computation in language models. Although modern lan
arXiv:2608.29847v1 Announce Type: cross Abstract: Text-to-image models learn associations between concepts - in the case of this paper, people's professions, which we refer to as roles - and visual at
arXiv:2510.03204v2 Announce Type: replace Abstract: Web agents powered by large language models (LLMs) must process lengthy web page observations to complete user goals; these pages often exceed tens
arXiv:2512.16391v2 Announce Type: replace-cross Abstract: Attention is the dominant source of latency during long-context LLM inference, an increasingly popular workload with reasoning models and RAG.
arXiv:2607.17486v2 Announce Type: replace-cross Abstract: As large language models (LLMs) process increasingly longer prompts, computation and KV-cache memory costs have emerged as major bottlenecks i
arXiv:2608.28070v1 Announce Type: new Abstract: Automated detection of surface micro-defects on industrial components, such as copper tubes, is critically important for quality assurance but remains c
I used the quantized n-gram to INT4, it's 32 GB, memory-mapped from disk. I confirmed that it works great on 150-160k context, and i was watching all the time my VRAM usage while doing single thread l
Setup: MacBook Pro M5 Max, 128 GB unified, macOS 26.5.2 · llama.cpp b10686 (Metal, 12 threads, batch 2048, flash-attn, kv-unified, ngram-mod spec decode) · Qwen3.8-Flash-Next UD-Q2_K_XL (Unsloth), 78.
Hey! I forked NInfer (a from-scratch C++20/CUDA inference engine for Qwen models) and added two things: tensor-parallel across two GPUs, and YaRN ×4 rope scaling. Together they let Qwen3.8-27B NVFP4 r
arXiv:2608.27036v1 Announce Type: new Abstract: Large Language Models (LLMs) can be trained to perform chain-of-thoughts reasoning in order to improve the reliability of their responses. In this work,