Knowledge catalogue
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
Security operations startup Mate Security Ltd. today launched Gamebooks, a set of structured investigation procedures that govern what its artificial intelligence agents are allowed to do while workin
The Qwen3.8‑Flash‑Next 176 B multimodal MoE model uses a hybrid Gated DeltaNet / Qwen Sparse Attention (QSA) architecture that compresses long‑context history and aggregates tokens into micro‑blocks f
Qwen3.8‑Flash‑Next is a multimodal mixture‑of‑experts model with 125 B parameters that employs Gated DeltaNet (compressing historic context) and Qwen Sparse Attention (exact retrieval over full contex
arXiv:2608.23651v1 Announce Type: cross Abstract: Agent harnesses record a failed tool call and its error message in the transcript and ask the model to continue, on the assumption that the error is c
arXiv:2608.23593v1 Announce Type: cross Abstract: Text-to-image systems use learned aesthetic scorers to filter training data and guide generation, but whether these scores encode demographic attribut
As AI takes on more complex work, business leaders face a new challenge: enabling rapid innovation using agents while protecting their margins and budgets. To get a real return on AI, financial operat
https://x.com/romanchernin/status/2092488160680751437?s=20 - Multimodal (Vision) - 1M Tokens Context Window - DeepSWE ~63% EDIT: THE ORIGINAL POST IS GONE Roman Chernin @romanchernin The mysterious Ox
The Artist: Qwen3.8-27B-UD-Q3K_XL, q8_0 caches, xhigh, temp 1.0, image-min-tokens 1024, froggeric template) I was screwing around with different Qwen3.8-27B quants and thought of this very simplistic
arXiv:2608.24551v1 Announce Type: cross Abstract: Machine learning models are widely used in financial fraud and credit-risk detection, yet their adversarial robustness remains difficult to evaluate b
arXiv:2608.23660v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to provide prior causal knowledge for structural causal discovery, yet whether their direct-edge ju
arXiv:2506.13182v3 Announce Type: replace-cross Abstract: [...] Since then, various APR approaches, especially those leveraging the power of large language models (LLMs), have been rapidly developed t
arXiv:2608.24132v1 Announce Type: cross Abstract: Product catalogs in fast-moving service businesses are shifting from static, independently priced SKUs toward dynamically bundled, discount-coupled of
arXiv:2608.24167v1 Announce Type: new Abstract: Whittle index policies offer a scalable method for restless multi-armed bandits, but under partial observability even determining the indifference subsi
We're releasing a fully quantized NVFP4 version of Qwen3.8-27B. The checkpoint was trained using quantization-aware distillation (QAD) with QUASAR, our new QAT algorithm. We used the original BF16 mod
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
arXiv:2608.23917v1 Announce Type: new Abstract: Common shortest-path algorithms, such as Dijkstra's (SPF), that OSPF uses, provide exact routing solutions but must be recomputed for each network topol
Hi all, I'm looking for the best model for a hobby project and trying to make sense of the various data I came across. I know benchmarks do not often translate to the real world, especially to your pa
arXiv:2608.24191v1 Announce Type: cross Abstract: Urdu, the world's tenth most spoken language with 246 million speakers, remains almost entirely absent from mainstream LLM safety evaluation and nine
arXiv:2608.23927v1 Announce Type: new Abstract: Video generative models provide rich physical priors for robot learning, yet existing world-action models (WAMs) face a fundamental trade-off: synchrono
Glean Technologies Inc. today unveiled Glean Tau, a desktop workspace that connects the company’s enterprise artificial intelligence to a user’s local files, applications and code. The launch anchors
Research from August 2026 indicates that GLM‑5.3‑Flash (also called Ox Alpha) delivers a 63 % performance score at 0.24 per task, which is more cost-effective than DeepSeek‑V4 Flash 0731 (53 % at 0.46
GLM-5.3-Flash by @Zai_org, aka Ox Alpha, is now live in LM Studio Bionic! This model surpasses GLM 5.2 in performance while being 9-10x cheaper. It also supports image input. In Bionic, this model is
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
Google has launched Gemini 3.5 Transcribe, a new voice‑to‑text AI model in the Gemini 3.5 branch that powers Gboard’s “Rambler” feature on Pixel 11 and is set to roll out across Google products such a
Google has updated Gemini Audio with new transcription capabilities that automatically detect specialized jargon and more than 85 languages. Gemini 3.5 Transcribe is a new addition to the Gemini famil
Great new paper from AWS on agent handoff tax. If you build agents today, you need to understand the so-called handoff tax. (bookmark it) Escalating to a stronger model mid-run is usually the resort w
Great paper on why agent leaderboard comparisons are hard to trust. It's on the hot topic of how much of an agent benchmark score actually belongs to the harness. The harness is the layer between the
arXiv:2608.24603v1 Announce Type: new Abstract: Vision language action models (VLAs) have advanced general purpose robotic grasping and manipulation by enabling robots to interpret visual observations
So I've been going down a rabbit hole trying to run local LLMs without dropping 800+ on a Mac or GPU. RAM prices are insane right now and I realized that used phones have decent unified memory for dir
Hi everyone. I am currently using gemma 4 model and used qwen 3:8b model. My goal is to use claude code to make projects, AI Tools Please help me find out what is more useful. Suppose i have to make a
arXiv:2608.24042v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models pretrained on large-scale robot datasets provide a strong foundation for robot manipulation, their performan
arXiv:2402.01767v4 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) significantly improves document-based question answering by integrating external documents during generat
arXiv:2608.24467v1 Announce Type: new Abstract: Although recent Multimodal Large Language Models (MLLMs) have advanced general product understanding, they implicitly encode product information into gl
Hosting the 2nd founder dinner in sf on August 31 with @GuangyuRobert at @Fundamental - the team behind @tryshortcutai Agents are increasingly capable of solving tasks for longer task horizons without
I think that mall models between 10B and 40B are the real gamechanger. These models will be the ones that will make the AI buble pop and big companies like Anthropic and OpenAi go to hell. We are curr
I ended up fine tuning a mistral 7b to outperform our costly foundational model and saved $300k. I previously thought that fine tuning was pointless (it's definitely not) and that all these problems c
arXiv:2608.23992v1 Announce Type: cross Abstract: Large language model (LLM) agents invoke external tools to retrieve and reason over information beyond pretrained knowledge. The Model Context Protoco
arXiv:2602.10863v2 Announce Type: replace-cross Abstract: Long-horizon reinforcement learning for information seeking agents remains difficult because terminal rewards reveal whether the final answer
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
The internet connected billions of people and mobile devices, putting computers in every hand. Now, we’re in the middle of the next big technology shift, deploying millions of autonomous AI agents to
**Intelligent Transcription with Gemini 3.5 Transcribe** In August 2026 Google unveiled Gemini 3.5 Transcribe, a next‑generation speech‑to‑text engine engineered for highly accurate, low‑latency real‑
Interesting new approach to recursive self-improvement in agents. Systems that add a meta-level hold that level fixed. Systems that edit themselves have to leave part of their own editing machinery un
Introducing GLM-5.3-Flash - Leading capabilities at a highly competitive price - Natively multimodal with a 1M-token context window - A 320B-A18B model released under the MIT License - Previously prev
Benchmarking Retrieval-Augmented Generation End to End — from Building the Vector Database to Serving an Iterative, Multi-Hop Question-Answering Inference Pipeline The post Introducing the MLPerf End-
arXiv:2608.24882v1 Announce Type: new Abstract: World action models (WAMs) improve robot control by modeling how observations evolve, but generating future observations at test time incurs substantial
arXiv:2608.23880v1 Announce Type: new Abstract: Inferring the collective emotional state of a group of people from a single image, a task known as group emotion recognition (GER), requires integrating
arXiv:2602.19001v2 Announce Type: replace Abstract: As large language models increasingly power personal assistants, users expect them to reason over multimodal life histories, from recognizing people
I was bored and handwrote a tiny 100-line bash script to let an agent search for and read articles from an offline wikipedia archive during a regular chat. It's not particularly useful, but it's defin
arXiv:2608.23622v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong capabilities in reasoning, planning, and tool use, but many scientific and engineering tasks require more
arXiv:2608.24469v1 Announce Type: new Abstract: Ternary transformers offer extreme memory and compute efficiency, but existing low-bit LoRA-based methods cannot directly fine-tune ternary weights. Cur
arXiv:2608.23943v1 Announce Type: cross Abstract: High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. To support relighting and integration in
arXiv:2608.24462v1 Announce Type: new Abstract: In this paper, we propose extbf{Mahalanobis-Based Multi-Head Attention} (MHA-CSP), a novel attention mechanism that replaces the standard dot-product wi
arXiv:2608.23918v1 Announce Type: new Abstract: Large Language Models excel at code generation, yet competitive programming exposes a persistent failure mode: existing multi-agent pipelines distribute
arXiv:2505.11239v4 Announce Type: replace Abstract: Understanding human mobility through Point-of-Interest (POI) trajectory modeling is increasingly important for applications such as urban planning,
arXiv:2608.24107v1 Announce Type: cross Abstract: Material replacement is a common interior-design operation: changing the material of a selected surface while preserving its geometry, surroundings, a
⚡Meet Qwen3.8-Flash, a multimodal MoE and an early preview of the Qwen4 architecture, now open-weight! The production version Qwen3.8-Flash will be available soon via QwenCloud API at just 0.16/1M inp
Megathread for discussing the release of GLM-5.3-Flash. Quants Fine-Tunes & Abliterations Chat Templates Inference Server Support & Configuration Experiences, Benchmarks & Model Comparisons We'll try
Megathread for discussing the (impending) release of Qwen 3.8 Flash Next. Quants Fine-Tunes & Abliterations Chat Templates Inference Server Support & Configuration Experiences, Benchmarks & Model Comp