Knowledge catalogue
Hello, I have a friend who's using various local LLM's like qwen3.6 27B, 35b-a3b, North Mini Code, and qwen2.5-vl-7b (just for vision). They have a use case where they're trying to have an LLM drive a
For 6 months now I've been trying to make agentic coding work for me, using Pi and a handful 30-120B models (Qwens, Nemotrons, Leguna...etc). I'm not greedy either, I stick to decent quants, never qua
arXiv:2607.26309v1 Announce Type: cross Abstract: Estimating causal effects of linguistic properties from observational text is difficult because the same document can contain both the treatment of in
arXiv:2510.00192v3 Announce Type: replace Abstract: Low-rank adaptation (LoRA) has become a widely used paradigm for parameter-efficient fine-tuning of large language models, yet its representational
arXiv:2607.26117v1 Announce Type: cross Abstract: Self-repair - returning a failed program to the model together with its test output and asking for a correction - is a standard component of code agen
Its a custom Swift/Metal inference engine that runs Gemma 4 26B-A4B-IT on M-series Macs with very low RAM. It uses ~2GB instead of ~14 GB. The result is reportedly 5–6 tok/s on an 8 GB M2 MacBook Air
arXiv:2607.26410v1 Announce Type: new Abstract: We present Voice Memory, a inference-only scheme for agentic speech recognition: at stream time, a frozen corrector reads a single per-domain memory.md
If you were able to get an inference machine that could do decode at 1k toks/s or even 10k tok/s, would that even be helpful? Would it unlock any new use cases? Let’s assume that this is for actually
Yesterday I cohosted a dinner with @dexhorthy with a wonderful group of founders, to talk about agent loops and loop engineering. Some interesting insights: * Most of our group was *not* actively usin
arXiv:2607.25415v1 Announce Type: new Abstract: Production LLM agents are increasingly assembled from a frozen model wrapped in a harness: a prompt template, a tool set, a memory/retrieval layer, a pl
arXiv:2503.05632v2 Announce Type: cross Abstract: In many image analysis problems, the contours of objects carry important statistical information about shape. Such contours are typically affected by
arXiv:2607.25875v1 Announce Type: cross Abstract: Traffic forecasting is important for efficient traffic management and route planning in smart cities. Existing traffic forecasting studies typically a
TIL: Adding a custom MCP server to Claude and ChatGPT Connecting a custom MCP server to Claude and ChatGPT's standard chat interfaces is possible, but can take quite a few steps. Tags: ai, generative-
arXiv:2602.09611v2 Announce Type: replace-cross Abstract: Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (
arXiv:2607.24814v1 Announce Type: new Abstract: Access to specialist clinical expertise remains severely limited across sub-Saharan Africa, where physician-to-patient ratios can fall below 1:25,000 in
arXiv:2607.25911v1 Announce Type: cross Abstract: Annotation is among the most demanding visualization tasks to automate, as it simultaneously requires correctly navigating visual, semantic, and styli
arXiv:2607.24774v1 Announce Type: new Abstract: Nuclear radiation, the energy released during atomic decay, poses persistent risks to public health and the environment, and concerns have only grown si
arXiv:2607.25993v1 Announce Type: new Abstract: Ultra-high-resolution (UHR) remote-sensing (RS) imagery provides fine-grained Earth-observation evidence over city-scale scenes, but poses a fundamental
I bought an RTX 5090 last year just to run 27B models natively. I even fine-tuned it with my own data using LoRA, building RAGs and was pretty damn happy with the results at first. But, Q8 quantizatio
arXiv:2509.16780v3 Announce Type: replace-cross Abstract: Large language models (LLMs) show promise as educational aids but often lack alignment with specific course materials. We investigate Retrieva
The Together AI platform’s dedicated inference architecture consists of three immutable entities: **configs** (engine, GPU type/count, parallelism and optimization profile), **deployments** (a specifi
arXiv:2607.25609v1 Announce Type: cross Abstract: Understanding disease trajectories from longitudinal clinical data remains challenging due to complex temporal dynamics and heterogeneous patient coho
arXiv:2607.25659v1 Announce Type: new Abstract: Rubric-based reinforcement learning enriches language model training by evaluating model outputs against explicit criteria. Yet in GRPO-style pipelines,
arXiv:2607.25400v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly entrusted with natural-language workflow instructions (e.g., retail-payment policies) that specify no
arXiv:2607.25888v1 Announce Type: cross Abstract: This study identifies new depression biomarkers based on the dynamical properties of tract variables, which represent geometric features describing th
arXiv:2607.25890v1 Announce Type: new Abstract: AI coding agents are being adopted at historic speed, yet security and risk concerns remain the primary barrier to scaling agentic AI across organizatio
arXiv:2607.25047v1 Announce Type: cross Abstract: Extended Reality (XR) is increasingly used in human-robot interaction to communicate robot intent, planned motion, reachability, and state. We argue t
arXiv:2507.11548v3 Announce Type: replace-cross Abstract: The use of publicly available generative AI systems for resume evaluation is often justified by the assumption that these tools reduce bias re
arXiv:2607.25423v1 Announce Type: cross Abstract: Eliciting explainable AI (XAI) requirements from stroke survivors presents a methodological challenge with direct implications for the design of trust
arXiv:2607.24749v1 Announce Type: cross Abstract: Although advancements in game character AI aim to enhance player engagement, evidence suggests that perceiving an opponent as artificial can diminish
arXiv:2607.25988v1 Announce Type: new Abstract: Exact-equivariant architectures typically encode prescribed group actions in specialized operators, which can complicate their reuse with generic backbo
arXiv:2607.25140v1 Announce Type: new Abstract: This paper studies the behavior of language models in a multi-agent crowd simulation, focusing on how affect propagates among agents that perceive and a
arXiv:2607.25297v1 Announce Type: cross Abstract: The rapid development of large language model (LLM) agents has enabled their broad adoption across diverse real-world tasks. To standardize interactio
The Test Bench Setup I tested running a massive 1.56TB Mixture-of-Experts (MoE) checkpoint (96 shards, 93 layers, 896 experts/layer, ~4.46 bits/param MXFP4) on a budget gaming laptop. Laptop: HP Victu
arXiv:2607.25106v1 Announce Type: new Abstract: Embodied AI increasingly relies on queryable semantic maps built from pre-trained vision-language models to enable zero-shot Object Goal Navigation (Obj
arXiv:2607.24829v1 Announce Type: cross Abstract: AI-based medication recommendation systems have attracted substantial attention due to their potential to enhance patient safety and therapeutic outco
arXiv:2607.25147v1 Announce Type: new Abstract: Trajectory data collected in real-world settings is frequently incomplete due to sensor failure, communication loss, or occlusion. We address the task o
arXiv:2607.24801v1 Announce Type: cross Abstract: We study the problem of guarded query routing, where we assume that a user query first meets a router that either determines the ideal endpoint for in
arXiv:2607.26015v1 Announce Type: new Abstract: Syntactic convergence (the tendency of speakers to adapt in language towards the grammatical profiles of their interlocutors) is a well-documented featu
arXiv:2607.25579v1 Announce Type: cross Abstract: Entity alignment (EA) identifies entities across knowledge graphs (KGs) that refer to the same real-world object. Conventional EA methods mainly explo
arXiv:2607.25197v1 Announce Type: new Abstract: Sleep staging remains challenging due to long-range temporal dependencies, ambiguous stage transitions-particularly in N1-and substantial distribution s
arXiv:2607.24769v1 Announce Type: new Abstract: With the growing capabilities of frontier models, AI alignment becomes increasingly critical in high-risk deployment settings. While recent work has emp
arXiv:2607.24904v1 Announce Type: cross Abstract: Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streamin
arXiv:2607.25420v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in recommender systems, but it is often unclear how much performance can be obtained from strong pr
arXiv:2607.24765v1 Announce Type: cross Abstract: Large language models (LLMs) can give different answers to the same decision problem across runs, and reverse a decision when their own prior answer r
arXiv:2507.23541v5 Announce Type: replace Abstract: In medical scenarios, effectively retrieving external knowledge and leveraging it for rigorous logical reasoning is of significant importance. Despi
arXiv:2607.25300v1 Announce Type: new Abstract: Video editing is fundamentally message-driven: even from the same source footage, the selected shots change depending on the narrative the editor wishes
arXiv:2607.25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time. We study its input-side dual: optimizing a fluent promp
Model + harness. We have barely begun to understand the best ways to do harness engineering. A huge amount of untapped potential even without models getting better (but models are getting better) Turn
arXiv:2607.24799v1 Announce Type: cross Abstract: Large Language Models tend to hallucinate when answering domain-specific ques tions from scientific documents without prior fine-tuning. Currently, me
While building this workflow a thing that surprised me was that, initially I thought the pipeline was complete: From Goal to → Decompose → Research → Specification → Implementation It successfully bro
arXiv:2510.12201v2 Announce Type: replace Abstract: As AI becomes more common in everyday living, there is an increasing demand for intelligent systems that are both performant and understandable. Exp
arXiv:2607.24784v1 Announce Type: new Abstract: Specialised translation relies on the use of documentary and terminological resources, including corpora. These resources are particularly useful for te
arXiv:2603.25469v2 Announce Type: replace Abstract: A growing body of literature has focused on predicting wildfire occurrence using machine learning methods, capitalizing on high-resolution data and
arXiv:2607.25656v1 Announce Type: new Abstract: Complex tasks often decompose into parallelizable yet interdependent subtasks, making orchestration critical to the performance of multi-agent systems (
arXiv:2607.25164v1 Announce Type: cross Abstract: A CT examination captures multiple organs, but many biomedical questions concern abnormalities, prognosis, or longitudinal change in a specific organ.
arXiv:2607.25545v1 Announce Type: cross Abstract: Deploying diabetic retinopathy (DR) screening models in primary care requires edge-efficient systems that remain accurate, safe, and reliable under do
arXiv:2607.24768v1 Announce Type: new Abstract: Prenatal care is an important preventive service designed to improve outcomes for pregnant individuals. The American College of Obstetricians and Gyneco
arXiv:2508.00344v5 Announce Type: replace Abstract: Large Language Models (LLMs) have shown remarkable advancements in tackling agent-oriented tasks. Despite their potential, existing work faces chall
arXiv:2607.25057v1 Announce Type: new Abstract: As conversational AI systems become increasingly integrated into daily life, their potential effects on user well-being require ongoing attention. While