Knowledge catalogue
Setup, so the question makes sense: my coding agent's memory now lives in a folder of Markdown — entities, episodes, and procedures (workflows with a per-step success/fail record). Nothing needs an ac
Quick setup on linux: STEP 0: install/download llama.cpp, Freecad, your favourite gguf model - possibly with multimedia image reading capabilities (I've used Qwen3.8-27B-UD-Q4_K_M and relative mmproj-
arXiv:2609.04539v1 Announce Type: new Abstract: A critical challenge in deploying Large Language Models (LLMs) is developing reliable mechanisms to estimate their confidence, enabling systems to deter
arXiv:2609.04641v1 Announce Type: new Abstract: Natural-language-to-SQL systems have ad- vanced rapidly on academic benchmarks, yet production enterprise schemas exhibit graph- like, semi-structured,
A couple years later, with GPT-6. https://underdark-duel.netlify.app Apparently the mindflayer has a '101-bone skeletal rig' (This is 5E 2014 rules, and I didn't see major errors, though the mind flay
arXiv:2609.05396v1 Announce Type: new Abstract: Wireless signals with position-related labels are pivotal for both performance evaluation and model training in the realm of wireless sensing. However,
arXiv:2609.04754v1 Announce Type: new Abstract: The Duckworth-Lewis-Stern (DLS) method has been the international standard for revising target scores in rain-interrupted limited-overs cricket since 19
A few days ago, Anthropic shared this brilliant prompt. I was surprised by how it significantly improved writing with Fable 5.1. Even more surprising, it also improved writing for GPT-5.6 Sol. I have
arXiv:2609.04509v1 Announce Type: cross Abstract: Scientific and clinical decision-making depends on evidence from the primary literature, but existing standards for representing that evidence (FHIR E
arXiv:2609.04409v1 Announce Type: cross Abstract: Multilingual language models often produce inconsistent answers to semantically equivalent questions across languages, motivating methods to improve c
arXiv:2609.05320v1 Announce Type: new Abstract: Deepfake detection models often rely on high-quality inputs, fixed inference paths, and computationally expensive architectures, limiting their use in l
Hi all! I just wanna say that I am tired lol. Yes, it's another harness, but I spent a lot of time and effort and have forsaken my hobbies to build the Jenny (like XJ-9) app. Jenny is a free, MIT lice
arXiv:2609.03693v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to jailbreak attacks that bypass safety alignment through carefully crafted prompts. Many existing defense
arXiv:2609.05016v1 Announce Type: cross Abstract: Scaling laws guide the design choices for training large foundation models, but deriving them involves training an exhaustive grid over hyperparameter
arXiv:2609.04791v1 Announce Type: new Abstract: Lesion-focused image classification presents a core analytical challenge, as discriminative signals are often sparse, spatially dispersed, and easily ob
arXiv:2609.04738v1 Announce Type: new Abstract: In this paper, we study the problem of personalized survey response prediction using fine-tuned large language models (LLMs). This task poses unique cha
arXiv:2609.04411v1 Announce Type: cross Abstract: Autonomous underwater robots are widely used for exploration, monitoring, and inspection, where safe navigation depends on understanding the surroundi
arXiv:2609.05258v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to formulate optimization models from natural-language problem descriptions, yet realistic operatio
arXiv:2609.04611v1 Announce Type: new Abstract: LLM agents are rapidly becoming production software, deployed to handle customer service, adjudicate disputes, and operate internal systems. Notably, th
arXiv:2609.04253v1 Announce Type: cross Abstract: Audio-video (AV) editing aims to modify audio and video content according to a target prompt. Unlike single-modality editing, AV editing requires mode
arXiv:2609.05157v1 Announce Type: cross Abstract: Formalizing mathematics in a proof assistant, where a machine checks every definition, statement and proof, has set a new standard of rigor. Large lan
vulkan: add TQ1_0 support (mm, mat-vec, mat-vec-id, dequant, get_rows) (#27765) vulkan: add TQ1_0 support (mm, mat-vec, dequant, get_rows) vulkan: pack TQ1_0 powers of 3 into a 32-bit constant Replace
vulkan: rms_norm fusion opportunities (#28024) Support RMS_NORM + MUL + ADD (+ MUL) and RMS_NORM + VIEW + SET_ROWS. Extend ROPE + VIEW + SET_ROWS to support IMROPE. Worth around 4% in gemma4 on my sys
ggml: allow backend inputs to not create another split (#28387) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45674860 macOS/iOS: macOS Apple Silicon (arm
ggml-cuda: fix divergent barrier in f16 flash attention (#27870) ggml-cuda: fix divergent barrier in f16 flash attention ggml-cuda: avoid duplicate metadata pointer setup Website: https://llama.app At
caps : recheck typed content if template checks for string (#28511) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45690927 macOS/iOS: macOS Apple Silicon
vulkan: support type-aligned GET_ROWS (#28253) vulkan: fall back to CPU for GET_ROWS with misaligned offsets The Vulkan GET_ROWS shader asserts when a tensor's backing-buffer offset plus view_offs is
CUDA: branchless Q4_K/Q5_K unpack to speed up mmvq, L2 prefetch on DGX Spark (#26705) Update Q4_K and Q5_K to use branchless computation, which stops the scale unpack being re-executed for every colum
ggml: add gfx90c HIP support (#26454) ggml: add gfx90c HIP support ggml: make gfx90c HIP support compliant with specifications Website: https://llama.app Attestations: https://github.com/ggml-org/llam
vulkan: add DeepSeek-V4 hyper-connection fused ops (DSV4_HC_COMB/PRE/POST) (#26578) vulkan: add DeepSeek-V4 hyper-connection fused ops (DSV4_HC_COMB/PRE/POST) CUDA has these ops from the DeepSeek-V4 m
tests : initialize the L2_NORM batch array (#28553) tests: bind the L2_NORM batch count to a local GCC cannot prove the loop fills norms up to the index read after it while the bound is a class member
I wanted a quick calories counter for myself, using LLMs to evaluate the calories from pictures of meals + descriptions. I needed to pick a model so I made a quick benchmark. The setup was: - Nutritio
arXiv:2609.05289v1 Announce Type: new Abstract: Automated reference-based evaluation methods play a critical role in assessing natural language generation systems. Existing meta-evaluation primarily m
arXiv:2609.04681v1 Announce Type: cross Abstract: AI coding systems are moving from autocomplete and chat toward agents that can inspect repositories, edit multiple files, run tools, write tests, open
arXiv:2609.04504v1 Announce Type: new Abstract: Cardiac, neural, behavioral, and speech measurements from wearable and mobile devices provide partial, noise-sensitive views of physiological state. Bio
arXiv:2602.11558v2 Announce Type: replace Abstract: Brain foundation models (BFMs) are advancing neurotechnology by learning transferable representations from neural signals, with broad potential in c
arXiv:2609.04726v1 Announce Type: new Abstract: Synthetic Aperture Radar (SAR) images have all-weather, day-and-night observation capabilities. However, compared with optical images, their speckle noi
arXiv:2609.05189v1 Announce Type: new Abstract: Assessing the impacts of social policy changes is a widely acknowledged challenge for policymakers. Econometric methods can be unreliable when extrapola
Please, Oh gentle soul, please beautiful soul, please kindhearted soul, with serious hardware and time to kill, please benchmark Unsloth Qwen3.8-27B-Q8_K_XL against Qwen3.8-Next-Flash-Q4_K_XL and prov
arXiv:2609.04388v1 Announce Type: cross Abstract: Adaptive network intrusion detection systems retrain classifiers after drift alarms, but an alarm detects change; it does not establish that a challen
arXiv:2609.04855v1 Announce Type: cross Abstract: Cross-cultural mediation by large language models (LLMs) requires deciding both when to intervene and how to respond in culturally grounded conflicts.
arXiv:2609.04653v1 Announce Type: new Abstract: Multilingual large language models often struggle to reason in low- to mid-resource languages. Prior work has shown that translation can improve multili
arXiv:2506.04061v1 Announce Type: cross Abstract: Modern nanofabrication techniques have enabled us to manipulate the wavefront of light with sub-wavelength-scale structures, offering the potential to
arXiv:2609.04830v1 Announce Type: new Abstract: Personalized federated learning (PFL) is a promising paradigm for collaborative learning over distributed devices, where edge nodes collaboratively trai
arXiv:2609.04915v1 Announce Type: new Abstract: Many long-horizon LLM deployments face tight prompt budgets: latency, cost, and context limits make full-context prompting impractical as interaction le
arXiv:2609.04648v1 Announce Type: new Abstract: Reinforcement learning (RL) has become one of the primary paradigms for reasoning enhancement of large language models (LLMs). In particular, Group Rela
arXiv:2609.04651v1 Announce Type: new Abstract: This paper studies adaptive recommendation under intent drift, where feedback from each recommendation outcome can reveal whether the relational evidenc
arXiv:2609.04269v1 Announce Type: cross Abstract: Deciding whether two supplier records belong to the same corporate family is a prerequisite for spend consolidation, credit exposure aggregation and s
arXiv:2609.04716v1 Announce Type: new Abstract: Visual counting is commonly formulated at the instance level, aiming to estimate how many objects of a queried category appear in an image. However, rea
arXiv:2609.05239v1 Announce Type: new Abstract: We present a system that uses a Vision-Language Model (VLM) as a diagnostic agent for adapting a detect-to-track pipeline to a new target domain without
arXiv:2609.04357v1 Announce Type: cross Abstract: Purpose: Increased number of chest radiograph (CXR) scans create a triage bottleneck, queueing urgent examinations behind routine ones. Existing AI to
arXiv:2603.25183v2 Announce Type: replace Abstract: Context-aware machine translation (MT) leverages document-level information, yet it does not consistently outperform sentence-level MT, as contextua
This weekend I posted about the gap closing between frontier models and open source models. Well, now I'm coming with receipts. I've been running local + cloud models against real public github codeba
arXiv:2609.04749v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems have experienced rapid growth in recent years. Despite their promise, such systems remain fragile,
Model: DeepSeek-V4-Flash-Vision-Exp (local and API when impatient) Time: about one weekend (2 days) of QA and small improvements Full game is here After Qwen3.8-Flash-Next one-shotted a really cool Ca
arXiv:2609.05364v1 Announce Type: cross Abstract: Machine-learning performance modeling is a uniquely hostile terrain for long-lived software: the assumptions baked into today's abstractions are inval
// Design Docs Are All You Need // Banger paper from Google DeepMind, MIT, and colleagues. What a genuinely strange and interesting paper this one is. Here is the setup: They maintain a performance-mo
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
arXiv:2609.04407v1 Announce Type: new Abstract: Deep neural operators learn mappings between input functions and complete PDE solution fields, enabling forward evaluations of new problem instances ord
arXiv:2609.05363v1 Announce Type: new Abstract: Trade-up recommendation identifies higher-quality alternatives that preserve a customer's purchase intent while offering upgraded benefits. Large langua