Knowledge catalogue
Following up on my previous post about my budget server setup (Intel N100 + RTX 5060 Ti 16GB), a few of you asked for a deeper dive into my actual inference config and real-world agentic performance.
arXiv:2608.13900v1 Announce Type: cross Abstract: Large language model (LLM) agents are evolving from conversational assistants into autonomous systems that execute long-horizon tasks through reasonin
arXiv:2608.14380v1 Announce Type: new Abstract: Many real-world tasks require LLM agents to interact with their environments over long execution horizons. Errors that occur early in execution may prop
arXiv:2608.14396v1 Announce Type: cross Abstract: The alternating direction method of multipliers (ADMM), as a landmark algorithm, has attracted tremendous research attention and extensive practical a
arXiv:2608.13940v1 Announce Type: new Abstract: AI research agents (AIRA) can now propose, implement, and evaluate their own machine learning experiments, but progress on frontier tasks is throttled b
Alibaba's open-weight AI models accumulated 3 billion global downloads in the past 6 months — more than Meta Llama, more than Google Gemma, more than every Chinese domestic competitor combined. The mo
arXiv:2608.14320v1 Announce Type: new Abstract: The anchoring effect is a cognitive bias in which an initial reference value shifts a later judgment toward itself. This effect is well established in h
Anthropic has clarified how it's planning to apply invisible watermarks to Claude-generated text in order to comply with Europe's AI transparency rules. On Friday, Anthropic announced that Claude's te
John Gruber / Daring Fireball: Anthropic's text watermark alters word probabilities to embed a fingerprint, which could degrade Claude's writing, despite its claim of no impact on quality — When I wro
arXiv:2608.14492v1 Announce Type: new Abstract: The Muon optimizer shows clear benefits versus alternatives when pretraining neural networks. However, it is used less frequently for parameter-efficien
arXiv:2608.13622v1 Announce Type: new Abstract: Open-ended real-world interaction admits multiple valid behaviors: an agent may answer directly, ask for clarification, provide progress updates, or con
arXiv:2608.13865v1 Announce Type: new Abstract: As AI-generated image edits proliferate, the platforms meant to curb the resulting disinformation treat detectability as a single, undifferentiated prop
arXiv:2608.14227v1 Announce Type: new Abstract: Preprocessing invariance is an appealing goal for spectral foundation models: a frozen model should remain useful when laboratories preprocess spectra d
[SYCL] support OP OPT_STEP_ADAMW, OPT_STEP_SGD (#25268) fix conflict fix conflict of ops.md fix conflict of ops.md update the ops.md Co-authored-by: Neo Zhang Jianyu jianyu.zhang@intel.com Website: ht
sycl: fix thread/block count in quantized cpy kernel launches (#27160) Adjusts the thread/block count to be proportional to the size of the quant, reducing under/over subscription. Largest perf improv
ci : push release tag explicitly in release.yml (#27261) Add a 'Create and push git tag' step to the release job, right before the 'Create release' step. The tag is created with git tag and pushed wit
cuda : skip UMA override for HIP builds (#27083) AMD APUs report accurate memory via hipMemGetInfo. Using MemAvailable over-promises on small-carveout systems. fixes #18159 Website: https://llama.app
arXiv:2402.01591v4 Announce Type: replace-cross Abstract: Spatial sound reasoning is a fundamental human skill, enabling us to navigate and interpret our surroundings based on sound. In this paper we
arXiv:2608.14003v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chain-of-thought generation, but incur substantial computatio
arXiv:2608.13576v1 Announce Type: cross Abstract: Brain-computer interface (BCI) research relies on multistage computational pipelines, yet progress remains constrained by fragmented data formats, het
arXiv:2608.14063v1 Announce Type: new Abstract: Machine learning is rapidly reshaping constitutive modeling, offers new ways to learn material behavior directly from experimental data, and challenges
Hello all, I'm fairly new to the whole Llm space and could really use some guidance from people who've done similar work. Im building a pipeline to extract structured data from large-batch of invoices
arXiv:2608.13722v1 Announce Type: new Abstract: This paper describes the University of Florida Gators submission to the WMT26 Low-Resource Indic Language Translation shared task. We adapt the retrieva
arXiv:2608.13854v1 Announce Type: new Abstract: Code translation must preserve executable behavior across many programming languages, yet neural code translation has largely focused on a few popular l
If you're running Ollama, llama.cpp, or vLLM behind nginx or HAProxy for more than a single user, you've probably hit this: nginx treats a 10-token prompt and a 10k-token prompt as identical 'one requ
arXiv:2608.14014v1 Announce Type: new Abstract: Two old market sayings hold that news is already priced in by the time it is published, and that the rumor is bought while the news is sold. Both place
arXiv:2608.14179v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable reasoning and generative capabilities, motivating their use as universal reasoning engines for percep
arXiv:2608.14391v1 Announce Type: cross Abstract: Recent video generators can fabricate realistic depictions of wars, disasters, public emergencies, and other real-world crises, creating substantial r
arXiv:2603.09868v2 Announce Type: replace Abstract: Accurately quantifying terrestrial carbon exchange is essential for climate policy and carbon accounting, yet models must generalize to ecosystems u
arXiv:2608.13751v1 Announce Type: new Abstract: Large pre-trained models have become foundational components of modern machine learning systems. Yet adapting these models to novel categories typically
arXiv:2607.14975v2 Announce Type: replace Abstract: Channel foundation models (CFMs) are commonly evaluated in model-specific pipelines that differ in data, radio configurations, partitions, adaptatio
arXiv:2608.13766v1 Announce Type: new Abstract: Vision-language models (VLMs) remain unreliable on chart questions that require reasoning over visual quantities, and this weakness is usually attribute
arXiv:2608.13889v1 Announce Type: new Abstract: Neural networks for seismic fault segmentation are often borrowed from computer vision and medical imaging domains where they train under relatively muc
arXiv:2608.14016v1 Announce Type: cross Abstract: Live game commentary is scarce: it exists for professional esports broadcasts and almost nowhere else. We present a content-based video narration syst
arXiv:2608.13990v1 Announce Type: new Abstract: Driven by the attention economy, short-video Recommender Systems (RSs) are primarily optimized to maximize user engagement by promoting videos that capt
🆕 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:2608.14546v1 Announce Type: new Abstract: With the rapid advancement of image editing models and their widespread application across various domains, there is an increasingly urgent need to depl
arXiv:2603.21114v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) perform strongly on isolated spatial tasks, but whether their predictions remain persistent and mutually co
arXiv:2608.14385v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models have been widely adopted in real-time interactive applications such as coding assistants, real-time audio-video intera
arXiv:2607.15740v2 Announce Type: replace-cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important
Guys, could someone smarter than me explain what makes Deepseek Harness so efficient? I run it with local Qwen 3.8 (Q6). I tried Opencode/Openchamber (my favourite so far), Pi agent and Hermes. New Qw
Note: I use a Mac Studio M3U with 512 GB RAM, so this is not for everyone. I have been using antirez/ds4 with DS4 Flash for a few weeks now. Top quality, I am really impressed. This combination just d
DeepSeek V4 Pro 0813 and Claude Fable 5 were benchmarked on DeepSWE. A cascading strategy that starts with Pro 0813 and escalates to Fable only when it fails solves 82.7 % of tasks at an average cost
defenders can see the future, and have a narrow window to uplevel their cybersecurity practices now. key is to uplevel fundamentals and apply the best AI tools. what we’re doing at OpenAI, and where o
arXiv:2608.13565v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale large language models (LLMs) while preserving computational efficiency through sparse activation. Despite t
arXiv:2608.14430v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training provides a direct way to align diffusion models with human preferences and task-specific rewards. However, c
arXiv:2608.14303v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for code generation, yet they remain vulnerable to prompts that elicit insecure implementations. Exis
The QAD (Quantization‑Aware Distillation) pipeline for Nemotron 3.5 Lightning leverages NVIDIA Model Optimizer to aggressively compress the model with W4A16/NVFP4 quantization while keeping accuracy c
arXiv:2608.13786v1 Announce Type: cross Abstract: Large language model (LLM) chatbots are increasingly used to answer clinical questions with citations to relevant clinical studies. Prior research has
arXiv:2608.13568v1 Announce Type: cross Abstract: Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal, instant, and zero-setup, but noisy: it cannot te
arXiv:2608.13566v1 Announce Type: cross Abstract: Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks (e.g., SWE-bench and LiveCodeBench) as eviden
arXiv:2608.13783v1 Announce Type: new Abstract: Top-1 accuracy on ImageNet-1k remains the most commonly reported metric in visual recognition. Quality issues with the dataset have been repeatedly repo
arXiv:2608.13799v1 Announce Type: new Abstract: This paper presents an event-driven learning and benchmarking framework for the Dynamic Multi-Depot Vehicle Routing Problem with progressively revealed
arXiv:2608.01856v2 Announce Type: replace Abstract: Bi-temporal remote-sensing disaster change captioning often needs to identify sparse and spatially localized changes across large pre- and post-even
arXiv:2601.03391v3 Announce Type: replace-cross Abstract: Image restoration has traditionally required training specialized models on thousands of paired examples per degradation type. Large pre-train
arXiv:2608.14406v1 Announce Type: new Abstract: Textile-integrated capacitive sensors offer flexible and conformable tactile sensing for wearable electronics and human-robot interaction; however, the
arXiv:2608.13867v1 Announce Type: cross Abstract: AI coding agents are commonly evaluated as models but deployed as systems. Their reliability depends not only on model capability, but on the harness,
arXiv:2608.14312v1 Announce Type: new Abstract: Reinforcement learning (RL) for terminal agents needs executable training environments with reliable rewards and useful difficulty. Fixed recipes such a
arXiv:2505.04491v3 Announce Type: replace Abstract: State estimation is one of the fundamental problems in robotics. For soft continuum robots, this task is particularly challenging because their stat
arXiv:2608.13608v1 Announce Type: new Abstract: Agentic 'Continual Learning Harnesses', systems that pair an LLM with retrieval or memory to improve from feedback without retraining, have shown growin