Knowledge catalogue
A few days ago I posted asking what people considered the best local model for an 8 GB VRAM GPU. At the time, my personal sweet spot was Qwen3.6-35B-A3B, for agentic coding with Pi.dev. Well… Thanks t
arXiv:2608.27206v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) demonstrate exceptional visual reasoning capabilities, yet their inference costs escalate rapidly with the proliferation
arXiv:2608.26887v1 Announce Type: new Abstract: LLMs are thought to track 'belief states,' i.e., running probability distributions over the latent variables that govern language (Shai et al., 2024; Sa
arXiv:2608.27291v1 Announce Type: cross Abstract: Music recommendation relies primarily on two signals: user-item interactions, which fail in the cold-start regime, and intrinsic musical content, avai
We're releasing Qwen3.8-27B quantized with our newest methods, GSQ + RCO. Higher-quality models, same file size, now with the search and the quantizer both learned. What's inside: GSQ (Gumbel-Softmax
arXiv:2608.26732v1 Announce Type: cross Abstract: Graph neural networks (GNNs) are typically conceptualized as message-passing neural networks, yet it remains unclear why neighborhood aggregation reli
arXiv:2608.26649v1 Announce Type: new Abstract: Objective: Model-based closed-loop neural stimulation holds promise for therapeutic applications ranging from Parkinson's disease to sensory restoration
arXiv:2608.26218v1 Announce Type: new Abstract: A coding agent combines a model with a harness, which decides what the model sees, which tools it can use, and how the work continues. We ask whether ch
arXiv:2608.26156v1 Announce Type: new Abstract: Retail intelligence often relies on monitoring popular, high-velocity products, potentially biasing economic indicators by ignoring the 'long tail' of n
arXiv:2607.19326v2 Announce Type: replace Abstract: Low-rank adaptation introduces a static learned update applied identically to every input. The update provides task-level adaptation but does not ex
arXiv:2608.26748v1 Announce Type: new Abstract: Diffusion models can be used to generate spatiotemporal signals of physical phenomena, such as time-series images of fluid dynamics. However, a major li
Static embeddings offer unmatched throughput, but they also suffer from accuracy loss compared to traditional embedding models. Can we make them better for retrieval? We tried several things: ✅️ raw m
arXiv:2608.26511v1 Announce Type: new Abstract: Large language models often exhibit sycophancy, revising their answers to align with users when users push back. Such answer flips, however, can arise f
arXiv:2608.27076v1 Announce Type: new Abstract: Algorithmic trading now represents a market exceeding $20 billion, where even marginal gains in signal robustness can translate into economically signif
arXiv:2608.26624v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation (OVSS) aims to segment image regions corresponding to arbitrary text queries. Although the Segment Anything Model
Hey all, and hello fellow DGX Spark-ers! Today I managed some pretty crazy numbers: 181 tok/s aggregate on 2× DGX Spark on Qwen3.8-Flash-Next at 512Kcontext (2.8M kvc) I hit 181 tok/s aggregate today
arXiv:2608.26706v1 Announce Type: new Abstract: Expert-level financial question answering requires both grounded verification to catch numeric hallucinations and audit trails for regulatory compliance
arXiv:2608.26877v1 Announce Type: new Abstract: Prior analyses by Derezinski and Warmuth established all-size sampling identities, selected-OLS unbiasedness, and inverse moments for ordinary volume sa
arXiv:2608.27176v1 Announce Type: cross Abstract: Understanding spoken dialogue requires joint reasoning over lexical content and paralinguistic acoustic signals such as emotion and conversational int
arXiv:2608.25022v1 Announce Type: new Abstract: As people adopt transformer-based language models (e.g., ChatGPT and Gemini) for an increasing number of use-cases, it is important to know how such mod
arXiv:2607.09156v2 Announce Type: replace Abstract: Additive activation steering is calibrated in single-turn chat and then deployed inside agent scaffolds. The quantity usually reported for that move
arXiv:2607.08789v2 Announce Type: replace Abstract: Bayesian and multiplicative-weights updates reweight experts, models, or actions from sequential feedback. We show that the regret of any such updat
arXiv:2608.25869v1 Announce Type: new Abstract: Large language models (LLMs) increasingly assess generated content, giving rise to the LLM-as-a-Judge paradigm. These systems now score outputs, filter
// Automata from agent traces // How much of your agent's behavior comes from the model, and how much from the harness you wrapped around it? New work collapses an entire corpus of agent traces into a
arXiv:2608.25500v1 Announce Type: cross Abstract: Reusable skill libraries allow large language model (LLM) agents to reuse procedural knowledge across tasks, but they also turn memory access into a c
arXiv:2608.25061v1 Announce Type: new Abstract: GPUs increasingly accelerate database systems, but query-specific peak performance still often relies on hand-written kernels. Existing LLM kernel bench
arXiv:2608.25876v1 Announce Type: cross Abstract: Generative design interfaces increasingly expose semantic controls that let users steer output with concepts such as 'more elegant' or 'more minimalis
arXiv:2608.24936v1 Announce Type: cross Abstract: We present GreenLeaf Law Embed Tiny, a 0.6B parameter embedding model for legal domain retrieval. GreenLeaf-Tiny achieves 75.11% on the Massive Legal
Software delivery platform provider Harness Inc. today announced the launch of Agent-Ready Harness Code Repository and AI Code Review, aimed at developer teams adopting artificial intelligence coding
arXiv:2608.25729v1 Announce Type: new Abstract: Long-video MLLMs must model temporal change before a limited visual-token budget removes most frame evidence. We introduce LongVU-TTT, which inserts a c
arXiv:2608.25176v1 Announce Type: new Abstract: Structural health monitoring (SHM) is essential in modern engineering, providing data for condition-based maintenance, lifecycle assessment, and predict
arXiv:2608.25698v1 Announce Type: new Abstract: Forecasting future measurements from geographically distributed sensors is essential across many domains. However, the spatial distribution of these sen
arXiv:2608.25768v1 Announce Type: new Abstract: Turkish encoder models have adopted modern architectures while leaving the pretraining objective fixed at masked language modelling. This paper introduc
Ever since Qwen 3.8 Flash Next dropped, there's a misconception going around that N-gram tables will let people run 1T+ parameter models on a single server with 980B parameters offloaded to SSD. I'm h
arXiv:2608.25275v1 Announce Type: cross Abstract: Learned traffic-behavior models are commonly trained separately for each intersection, creating model portfolios that cannot share evidence across sit
Got the new Qwen3.8-Flash-Next (176B total, 6B active MoE) running locally and figured I'd share for anyone else wondering if their setup can handle it. **My hardware:** 192GB DDR5 RAM, RTX 5070 Ti (1
arXiv:1807.04783v3 Announce Type: replace Abstract: Can advances in NLP help advance cognitive modeling? We examine the role of artificial neural networks, the current state of the art in many common
arXiv:2608.25095v1 Announce Type: cross Abstract: The proliferation of distributed energy resources (DERs) in distribution grids enables the active coordination of these assets to reduce costs and ena
arXiv:2505.23022v2 Announce Type: replace Abstract: Large Language Model (LLM) serving increasingly underpins online Web services such as conversational agents, Web search, and programming assistants,
arXiv:2608.24920v1 Announce Type: new Abstract: This study examines whether LLM-generated replies remain semantically consistent when the underlying LLM changes. Using messages from real collaborative
arXiv:2608.25701v1 Announce Type: new Abstract: We propose a novel pretraining strategy for skeleton-based zero-shot spatio-temporal action localization to estimate unseen actions for person instances
arXiv:2608.25166v1 Announce Type: new Abstract: Transformer representations describe trajectories through high-dimensional vector spaces, which are shaped dynamically as tokens incorporate relational
arXiv:2608.25523v1 Announce Type: new Abstract: Prefix caching introduces a fundamental tradeoff in multi-agent large language model (LLM) serving: retaining a long system-prompt key-value (KV) cache
arXiv:2608.25700v1 Announce Type: new Abstract: The Meteosat Third Generation (MTG) Flexible Combined Imager (FCI) offers new opportunities for tropospheric temperature and humidity profiling, at high
arXiv:2608.25302v1 Announce Type: new Abstract: Guided depth super-resolution (GDSR) typically extracts RGB guidance features through convolutional hierarchies, inheriting their fine-to-coarse bias. T
arXiv:2608.25251v1 Announce Type: new Abstract: Medical vision-language models (VLMs) can appear reliable in-domain while failing when acquisition domain, paired supervision, or evaluation protocol ch
arXiv:2603.23134v2 Announce Type: replace Abstract: Drones are becoming popular as a complementary system for Emergency Medical Services (EMS). Although several pilot studies and flight trials have sh
arXiv:2608.24644v1 Announce Type: cross Abstract: This paper introduces an environment for constructing literate programs in concert with language-aware machine agents. This environment includes a gra
arXiv:2608.23796v1 Announce Type: cross Abstract: Problem definition: Solar electricity generation is a strategic component of energy portfolios designed to meet growing demand and reduce carbon emiss
Upgraded to a 5070 Ti so I could run Qwen 3.8 27B, which works perfectly, but didn't want to let the old 4070 Ti go to waste. The cards would touch if I put them both in the PC and I knew the heat wou
arXiv:2608.24024v1 Announce Type: new Abstract: Confidence-based voting aggregates parallel LLM rollouts by weighting each with internal signals such as token log probabilities, and has been actively
arXiv:2608.24632v1 Announce Type: new Abstract: Accurate assessment of student competencies is essential for enabling educators to identify individual needs, design targeted interventions, and evaluat
arXiv:2608.23932v1 Announce Type: new Abstract: This study introduces the evolutionarily recurrent decision model (ERDM), a computational reinforcement learning framework designed to examine how evolu
arXiv:2608.23758v1 Announce Type: cross Abstract: Recent large audio language models (LALMs) have achieved impressive progress in audio understanding. However, existing evaluations remain largely cons
arXiv:2608.23666v1 Announce Type: new Abstract: Sycophancy and hallucination are persistent failure modes of Large Language Models (LLMs) across domains. However, it becomes particularly consequential
GLM-5.3-Flash is live in Hermes Agent via Nous Portal https://portal.nousresearch.com Introducing GLM-5.3-Flash - Leading capabilities at a highly competitive price - Natively multimodal with a 1M-tok
GLM-5.3-Flash scores 57 on the Artificial Analysis Intelligence Index. At 0.09 Cost per Task, it sits comfortably on the Intelligence vs. Cost per Task Pareto frontier @Zai_org has released GLM-5.3-Fl
In this post, you will learn how GoDaddy migrated from their legacy business intelligence (BI) tool to Amazon Quick. This was a two-year transformation that delivered results across every dimension of
arXiv:2608.24580v1 Announce Type: new Abstract: Understanding social interactions from non-verbal visual data is important for behavior analysis and activity monitoring. We propose an interpretable co
arXiv:2608.23619v1 Announce Type: cross Abstract: Legacy software repositories embed decades of domain knowledge in undocumented code, making understanding and modernization difficult. We treat a prog