Knowledge catalogue
I have been using local models on/off for like 2 years or so but never really used them extensively because the closed ones were always much better. Once Qwen 3.8 27B was released I decided to give it
arXiv:2608.16894v1 Announce Type: cross Abstract: ML venues shape what kinds of research claims become legible to reviewers and what forms of evidence count as rigorous. The NeurIPS and ICML Position
arXiv:2608.17956v1 Announce Type: cross Abstract: In the Code World Model paradigm an LLM synthesizes an executable world model that a classical planner searches, and the model is accepted when it rep
arXiv:2608.17271v1 Announce Type: new Abstract: Artificial superintelligence (ASI) requires AI to move beyond mastering existing knowledge toward exploring the unknown, creating new knowledge, and tur
arXiv:2509.06777v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) suffer from oversquashing, where structural bottlenecks limit message propagation between distant nodes, hindering task
arXiv:2608.17684v1 Announce Type: new Abstract: Self-evolving agents turn experience into reusable skills, workflows, or memories, but post-evolution accuracy alone does not show whether learned behav
arXiv:2608.17906v1 Announce Type: new Abstract: Autonomous research systems are increasingly capable of executing long research workflows, yet automation alone does not ensure that the resulting proce
arXiv:2608.17718v1 Announce Type: new Abstract: Long-horizon agents increasingly operate across many steps, tools, and observa- tions. In this setting, the relevant oversight question is not only whet
arXiv:2509.15236v2 Announce Type: replace-cross Abstract: Data-driven surrogate models are increasingly used in computational fluid dynamics, and their reliability depends on the quality of the traini
arXiv:2608.17253v1 Announce Type: cross Abstract: Reinforcement learning (RL) has emerged as a powerful approach for improving reasoning in language and vision-language models, yet its strongest succe
arXiv:2608.17536v1 Announce Type: cross Abstract: Legal consultation questions exhibit multi-level complexity. A single retrieval strategy often leads to over-reasoning for simple questions and poor i
arXiv:2608.17632v1 Announce Type: cross Abstract: Large language models (LLMs) can both expand underspecified queries and encode text as dense representations, suggesting a unified model for query exp
I’ve been using deepseek-v4-flash:0731 on Ollama Cloud, and recently it feels like my usage is getting consumed much faster than before. My prompts and general workflow haven’t changed much, but the a
Hermes now leverages NVIDIA's SkillEvaluator on skill installs, checking for PII, leaked secrets, Unicode smuggling, licensing and security issues before you confirm. We pointed it at our own bundled
arXiv:2312.06576v2 Announce Type: replace Abstract: Graph Transformers (GTs) facilitate the comprehension of complex relationships on graph-structured data by leveraging self-attention of the possible
Hello everyone, tried so hard to optimize my config and finally I simply get up to 70 t/s with q6 variant. And wanted to share with you guys so that other people with the same setup can enjoy. Please
Hey everyone! We’re releasing new Qwen3.8-27B GGUFs with 10% higher accuracy for the same size. This uses a new version of Dynamic v3.0 Unsloth Dynamic V3 outperforms others by >10% on Div-300, KLD &
arXiv:2608.17393v1 Announce Type: new Abstract: Reinforcement learning for coding agents increasingly relies on long-running agent harnesses to manage tool integration, repository contexts, and execut
arXiv:2608.17753v1 Announce Type: new Abstract: Short-duration heavy-rainfall warning determines whether 1 h rainfall will exceed a threshold within a target-station neighborhood over the next few hou
New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the mo
Four Tesla V100s from 2017 matched my RTX 5090 on single-request Qwen 3.8 decode. Repo: https://github.com/dnv2003/v100-skinny https://i.redd.it/5ws2ak3uqckh1.gif The 5090 was not being held back. It
arXiv:2510.02625v5 Announce Type: replace Abstract: Missing data in tabular datasets forces practitioners into a hard choice: deploy a general-purpose imputer that may perform poorly for the problem a
arXiv:2608.17220v1 Announce Type: cross Abstract: Autonomous AI agents are emerging as interfaces for decentralized finance (DeFi) actions such as swaps, lending operations, and yield management. Beca
arXiv:2608.17171v1 Announce Type: new Abstract: Many table-centric NLP tasks such as NL2SQL first retrieve relevant tables from large collections using keyword search. Recent work uses LLMs to generat
arXiv:2608.16970v1 Announce Type: cross Abstract: LLM-based code generation is now embedded in mission-critical pipelines, but defenses against vulnerable output remain post-hoc -- static analyzers, f
arXiv:2607.18046v2 Announce Type: replace Abstract: Graphical User Interface (GUI) agents powered by vision-language models hold promise for automating real-world mobile tasks. However, progress is li
arXiv:2608.17966v1 Announce Type: new Abstract: Sparse attention mechanisms, which score all token pairs but propagate only the strongest, now underpin the most efficient Transformers for lightweight
arXiv:2608.17301v1 Announce Type: new Abstract: Post-training with supervised chain-of-thought fine-tuning and reinforcement learning from verifiable rewards has substantially improved the mathematica
arXiv:2608.18011v1 Announce Type: new Abstract: Reasoning in LLMs is overwhelmingly studied in domains that provide a model with rules: mathematics and code. Linguistic puzzles invert this: the solver
Sovereign AI models lagging behind cutting‑edge systems risk significant disadvantages when applied to frontier tasks such as cyber defence. Ethan Mollick highlights that this penalty is most pronounc
arXiv:2608.17744v1 Announce Type: new Abstract: Take three frontier mixture-of-experts models (Alibaba, OpenAI, NVIDIA; 3.6-4.0B active parameters each) and fine-tune them to reason in a low-resource
arXiv:2608.17188v1 Announce Type: cross Abstract: Multi-agent AI workflows are limited not only by model quality but by token cost, latency, and context-window quality. This paper presents a practitio
Any LLM will hallucinate the world knowledge, even a 3T model. Use a 4B with a kiwix skill and local Wikipedia, 50gb and no more hallucinated world knowledge. Ask your coding agent to build your own,
arXiv:2608.16909v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly integrated into financial advisory systems, yet their role in reproducing religious bias remains underex
arXiv:2608.17564v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) are motivated by the hope that understanding and generation reinforce each other but controlled ablations repeatedly
arXiv:2608.15565v1 Announce Type: new Abstract: Experience-learning agents for optimization modeling improve by storing verified skills, but existing learners admit knowledge by checking against known
arXiv:2608.16554v1 Announce Type: new Abstract: Answer-only reinforcement learning (RL) trains reasoning models to solve fully specified problems, but many realistic queries omit a premise needed for
arXiv:2608.16098v1 Announce Type: cross Abstract: Multivariate time-series forecasting faces a structural dilemma: sharing one temporal predictor across variables is parameter-efficient but forces het
arXiv:2608.15683v1 Announce Type: new Abstract: Semantic segmentation is a core computer vision task in the remote sensing field, accelerating advancements in ur- ban development, agriculture, ecology
arXiv:2608.16211v1 Announce Type: new Abstract: Long-horizon agents are beginning to automate complete workflows that produce code, reports, and research artifacts. Medical imaging workflows are multi
arXiv:2608.16196v1 Announce Type: new Abstract: Personalized game generation requires inferring a player's abilities and behavioral style from how they play. Large language models have made this infer
arXiv:2608.16663v1 Announce Type: cross Abstract: Direct text-to-SQL asks a language model to do two jobs: interpret the business question and construct the complete relational query. In enterprise sc
arXiv:2505.02763v2 Announce Type: replace-cross Abstract: One of the central promises of legal AI is to automate drudgery -- the formal, repetitive tasks of lawyers' work that consume time without cal
arXiv:2608.14791v1 Announce Type: new Abstract: Abductive reasoning, often characterized as inference to the best explanation, is central to explanation under uncertainty, from everyday sense-making a
arXiv:2608.15788v1 Announce Type: new Abstract: Spatial intelligence requires foundation models to maintain coherent spatial state across interactions with the physical world. However, existing data-c
arXiv:2511.11427v2 Announce Type: replace Abstract: Referring Expression Comprehension (REC) requires models to localize objects in images based on different types of natural language descriptions. Ev
arXiv:2608.16259v1 Announce Type: cross Abstract: The rapid progress of image generation models calls for AI-generated image (AIGI) detectors that are not only accurate but also explainable and reliab
arXiv:2603.23924v2 Announce Type: replace Abstract: Text-to-image models often struggle to synthesize correct occlusion relationships among multiple objects, especially in densely overlapping regions.
Apparently a second version of DFlash from the original authors of DFlash GGUF quants are already made available with an accompanying llama.cpp PR: https://github.com/ggml-org/llama.cpp/pull/27342 sub
arXiv:2608.14655v1 Announce Type: cross Abstract: Omni-Large Language Models (Omni-LLMs) power complex multi-modal reasoning in applications like World Action Models and autonomous agents. However, th
arXiv:2608.16805v1 Announce Type: cross Abstract: Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to the wrong same-class instance. Gen
arXiv:2504.20823v3 Announce Type: replace Abstract: Accurate remaining useful life (RUL) estimation underpins safe operation and cost-effective maintenance of aerospace propulsion systems. We propose
arXiv:2608.14896v1 Announce Type: new Abstract: Large language models work well on English and behave in poorly understood ways on languages typologically far from it. Japanese is a clean example, whe
arXiv:2608.14927v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems can improve reasoning by spending more computation, but deployment requires deciding when extra collabora
arXiv:2608.15242v1 Announce Type: new Abstract: When a long-horizon agent execution fails, outcome-level evaluation reveals the unsuccessful result but not where the decisive error entered the traject
arXiv:2602.17510v2 Announce Type: replace-cross Abstract: We introduce LoRA-CRAFT (extbf{C}ross-layer extbf{R}ank extbf{A}daptation via extbf{F}rozen extbf{T}ucker), abbreviated CRAFT throughout, an e
arXiv:2608.14634v1 Announce Type: new Abstract: Biological intelligence naturally prevents catastrophic forgetting through Complementary Learning Systems (CLS) theory, a macroscopic consolidation proc
arXiv:2608.15830v1 Announce Type: new Abstract: Real-time tiny target perception in high-resolution imagery is critical for embodied Search-and-Rescue (SAR) missions. However, strict Size, Weight, and
arXiv:2603.17216v2 Announce Type: replace Abstract: With the advent of AI agents, automated scientific discovery is becoming an increasingly plausible goal. However, training agents to autonomously ex
arXiv:2505.21333v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have achieved considerable accuracy in Optical Character Recognition (OCR) from static images. However, the