Knowledge catalogue
arXiv:2603.22978v2 Announce Type: replace Abstract: In the maintenance of complex systems, fault trees are used to locate problems and provide targeted solutions. To enable fault trees stored as image
arXiv:2608.30584v1 Announce Type: new Abstract: Despite the impressive progress of recent MLLMs on spatio-temporal video grounding (STVG), existing evaluations and training data focus primarily on sim
arXiv:2510.26824v2 Announce Type: replace-cross Abstract: Wide access to advanced experimental methods in materials science has given rise to an abundance of procedural knowledge, which is scattered a
arXiv:2608.31016v1 Announce Type: cross Abstract: Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the no
arXiv:2606.17511v2 Announce Type: replace-cross Abstract: Robot learning and embodied agents now require simulation to serve as a shared execution substrate linking control, skills, and planning, not
arXiv:2608.30114v1 Announce Type: new Abstract: Brazilian Portuguese remains under-served by open language models, and the few that exist are difficult to reproduce and are often compared without meas
arXiv:2608.29617v1 Announce Type: cross Abstract: This paper introduces a hybrid fact-checking framework that integrates Knowledge Graph-based semantic memory with adversarial multi-agent reasoning fo
arXiv:2608.29477v1 Announce Type: cross Abstract: Document question-answering systems increasingly answer questions over collections of retrieved documents rather than one clean source, so robustness
arXiv:2608.30320v1 Announce Type: new Abstract: We describe the architecture and ablations of Qwen3.8-Flash-Next, a sparse mixture-of-experts model with 125B parameters, 6B activated per token, and ad
arXiv:2608.29526v1 Announce Type: new Abstract: Academic reviews, scholarly commentaries, and book reviews serve as sources of evaluative statements about theories, methods, literature, institutions,
arXiv:2608.31119v1 Announce Type: new Abstract: Research planning is the decisive capability of AI scientists. Yet a research plan admits no verifiable answer, so reinforcement learning lacks the envi
arXiv:2608.29996v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) achieve strong performance across many multimodal tasks; however, they often exploit spurious object-background c
arXiv:2608.20118v1 Announce Type: cross Abstract: The detection of rare disease-associated cell subsets from high-dimensional single-cell measurements is critical for understanding diseases such as le
arXiv:2608.30229v1 Announce Type: new Abstract: Korean introduces an additional typographical perturbation level not captured by ordinary character-level edit models: because syllable blocks are inter
I only started using some vLLM forks recently in a 4 x 48GB 4090 system. DS4F - ~5000pp/180tg (DSpark) Qwen3.8 Flash next - ~7500pp/135tg (MTP) This is amazing, like having the API in my house. But it
arXiv:2608.30896v1 Announce Type: new Abstract: Automotive mmWave radar can develop vibration, antenna misalignment, radome blockage, and receive-channel degradation that corrupt the signal before per
arXiv:2608.28963v1 Announce Type: cross Abstract: The number of knowledge graph databases has increased significantly with the proliferation of knowledge graph technologies. Knowledge graphs enable th
arXiv:2603.10807v2 Announce Type: replace-cross Abstract: Existing LLM safety evaluations rely on binary attack-success rates and domain-agnostic taxonomies, leaving regulated Banking, Financial Servi
arXiv:2608.30384v1 Announce Type: new Abstract: By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension,
arXiv:2608.29098v1 Announce Type: new Abstract: Multimodal safety moderation requires distinguishing risks arising from visual content, user intent, and assistant behavior. Existing safeguards, howeve
arXiv:2608.28600v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance on mathematical reasoning benchmarks, yet the mathematically meaningful skills underlying their
arXiv:2608.30207v1 Announce Type: cross Abstract: Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal,
arXiv:2608.29841v1 Announce Type: new Abstract: Generating formally verified programs from natural language remains challenging: existing approaches either produce code in a single pass without recour
There’s generally a massive difference in quality between specialized OCR providers, “simple” open-weight OCR models, and free/OSS solutions. 1️⃣ Specialized OCR models (including LlamaParse) solve fo
arXiv:2608.30213v1 Announce Type: cross Abstract: Text recognition, or extracting electronic text from document images, has been indispensable for knowledge retrieval tasks, such as retrieval-augmente
arXiv:2608.29235v1 Announce Type: new Abstract: Anti-UAV perception systems must remain reliable when sensor streams degrade under occlusion, fast motion, or modality-specific failure. Existing multim
arXiv:2608.28695v1 Announce Type: new Abstract: Image retrieval has traditionally been formulated as a point-wise matching problem, where each candidate image is scored in isolation. However, this ato
arXiv:2608.19269v4 Announce Type: replace-cross Abstract: Benchmarks can run without determining what their results license. We freeze a large evaluation collection and attempt to replay its historica
I used a famous Simon Willison's pelican riding a bicycle prompt on the biggest local LLMs that can run on 128GB Apple Silicon. U used quantizations by Unsloth. Qwen3.8 Flash-Next gives a lot of detai
arXiv:2601.06953v3 Announce Type: replace Abstract: Competitive programming remains challenging for code LLMs. Despite recent progress, many training pipelines still depend on scarce real-world data,
arXiv:2603.17304v2 Announce Type: replace Abstract: Deep learning has become an important tool for Alzheimer's disease (AD) classification from structural MRI. Many existing studies analyze individual
arXiv:2608.28458v1 Announce Type: new Abstract: Interactive dialogue games test a capability that static benchmarks largely leave implicit: a model must carry state across turns, interpret feedback, a
arXiv:2608.28432v1 Announce Type: new Abstract: Recent advances in in-context learning (ICL) text-to-SQL have substantially improved execution accuracy on public benchmarks by assembling increasingly
arXiv:2608.28394v1 Announce Type: cross Abstract: Cyber threat intelligence (CTI) is foundational to modern cyber defense, yet much of it resides in unstructured reports whose volume and heterogeneity
arXiv:2608.28478v1 Announce Type: new Abstract: Factual question answering (QA) typically assumes a single canonical answer, obscuring whether large language models (LLMs) retain divergent accounts of
arXiv:2608.27893v1 Announce Type: new Abstract: High-quality e-commerce creatives are essential for presenting products and conveying marketing messages. Recent diffusion models enable scalable creati
I haven't had a chance to test it yet, but it looks very promising. It seems to speed up MTP for MoE models across different draft widths (especially greater than 1). Check the benchmarks. submitted b
arXiv:2608.28302v1 Announce Type: new Abstract: Diffusion-based inpainting models modify only a localized part of an image, while many AI-image detectors rely on global artifacts and do not localize.
The LWiAI Podcast #255 (August 26 2026) reviewed recent AI alerts, including Google’s Gemini 3.7 Flash, Jalapeño’s record‑speed benchmark results, Qwen 3.8, and a case of an entirely AI‑guided drone t
When using kvarn quants at low context depth tg speed is similar to llama.cpp on and equivalent qx_x quant. However, as context depth grows kvarn tanks your tg speed. This fork optimises kvarn to have
arXiv:2608.28272v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, yet its high bitrate requirements pose significant challenges
arXiv:2511.08444v2 Announce Type: replace Abstract: EEG-based emotion recognition is hampered by profound dataset heterogeneity (channel/subject variability), hindering generalizable models. Existing
Hello! I was looking into quantizing models and i saw how Hy4 was shrunk from 1.5 TB to 200GB with high retention in benchmarks (98% i think). I was wondering if: a) it would be worth it to attempt th
arXiv:2608.27462v1 Announce Type: new Abstract: Unlike explicit attacks with obvious profanity, implicit hate speech hides malice within seemingly compliant expressions through metaphors and contextua
A hallucinated event, Crono awakens in his modest bedroom of 2095... I am using local models since 2025 January. My daily driver is qwen 3.6 35B A3B, which works pretty well for coding tasks, but I al
Hey guys I have been working on a open source LLM development repo. Anyone can train any amount of parameter against any arch (GQA, MLA, Dense...) When I tried to implement MLA I read the technical re
Since I spent the time to figure it out and it is not like it will make me any money ever. I think I'd share with you all what I managed to cobble together. First and foremost here the relevant bits a
Running on a M1 Max 64 GB: - SSD streaming for tensors - SSD streaming for engrams - SSD streaming for MTP How is it possible? * Custom Q4 quant: benchmarked all metal tensors then picked and spliced
specs hardware: M4 Max 128GB Studio inference engine: llama.cpp (qwen4exp branch) judge: claude-opus-4-6 AtomicChat/Qwen3.8-Flash-Next-GGUF Qwen3.8-Flash-Next is a great model I benched in my previous
Hardware: rtx 5080 16 gb vram; 64 gb ram ddr5 6000hz; ssd with unlimited memory; ryzen 7 9800 x3d. OS: Windows 11 Software: I’d prefer llama.cpp, but it’s not a strict requirement; I’ll use whatever y
~20–30GB smaller than Unsloth/AesSedai Q4 at similar PPL. After several days of testing I released a set of mainline-compatible imatrix quants for Qwen3.8-Flash-Next. Goal: same quality band as the po
Announcement: https://www.tbench.ai/news/terminal-bench-4-0 Leaderboard: https://www.tbench.ai/ Imo the best aspect in their announcement is their focus on rapidly iterating on TerminalBench to keep t
This paper does a good job of showing the promise and gaps of autonomous AI scientists. Big question is how much more advanced models close those gaps. Today, we're excited to share early progress on
arXiv:2602.20159v3 Announce Type: replace-cross Abstract: Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grou
arXiv:2608.26133v1 Announce Type: new Abstract: Evaluating AI agents that use external tools requires realistic test scenarios that capture how practitioners compose tools and iterate across conversat
arXiv:2608.26130v1 Announce Type: new Abstract: Coding agents built on large language models (LLMs), such as Claude Code, Cursor, OpenAI Codex, GitHub Copilot, and Aider, receive tool responses that r
arXiv:2608.27051v1 Announce Type: new Abstract: Detecting the fetal abdominal circumference standard plane in low-cost obstetric blind sweeps is a highly imbalanced frame-classification problem: posit
arXiv:2608.26291v1 Announce Type: new Abstract: Mentalization - the ability to infer others' beliefs and intentions to guide one's own choices - is a key cognitive function underlying human social int
arXiv:2608.26172v1 Announce Type: cross Abstract: Deploying natural-language interfaces over enterprise OLTP catalogs fails at scale because semantic parsers collapse under schema-graph scaling, infla
GLM-5.3 has arrived on Together AI on Day 0 @Zai_org pushed the GLM-5.2 base further with scaled post-training, delivering stronger coding and long-horizon agent performance. Across benchmarks, it nea