Knowledge catalogue
audio.cpp 0.7 is out :) This release adds a lot of new audio models and a new way to compare them locally. Audio.cpp is now at 62 model families and 85+ model variants. And it keeps growing! The bigge
arXiv:2608.25637v1 Announce Type: new Abstract: Reference-based verifiers are important for evaluating reasoning models and providing accurate outcome rewards in reinforcement learning with verifiable
arXiv:2608.24949v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training has emerged as a powerful framework for enhancing the capabilities of large language models (LLMs), enabling
Need a low-cost, high-performance way to run long-lived, stateful workloads such as AI agents? Today, we introduced Cloud Run instances, which let you do just that. Consider AI agents such as OpenClaw
Presented by Gravitee Agent complexity is the insidious shadow lurking inside enterprises right now that needs a light shone on it.That’s because enterprises don't deploy a single agent and watch it r
arXiv:2509.02855v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to produce open-ended, interpretive annotations, yet there is no validated, scalable measure of i
Important read if you build with agent skills. Shared skill libraries are treated as a safe way for coding agents to reuse each other's work. New research shows they propagate malware. EvoMal plants a
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
Mary Ann Azevedo / Crunchbase News: Nevada-based identity verification and fraud prevention startup Socure raised 156M at a 5.2B valuation and acquires Austin-based agentic AI startup Fravity — Identi
arXiv:2608.26070v1 Announce Type: new Abstract: Test-time scaling uses extra test-time compute to improve performance, such as letting language models reason longer when solving a problem. As models k
Putting this tweet in the “scary” category of AI. Calling upon the non-technical business professionals that follow me to pay attention. I’m breaking down the key parts of the @RyanGreenblatt tweet on
Reuters: Sources: Anthropic discussed buying AI chip startup MatX for ~7B, but talks are no longer active; MatX is now seeking to raise new capital at a ~4B valuation — Anthropic discussed buying arti
New York Times: Sources: Meta internally projected that it could spend as much as 10B annually on Anthropic's AI models, even as Zuckerberg publicly criticized Anthropic — The social networking giant
arXiv:2608.25756v1 Announce Type: new Abstract: Reinforcement learning post-training drives reasoning and agentic capabilities in modern AI systems, yet a growing body of work shows that it is most ef
arXiv:2608.26013v1 Announce Type: new Abstract: Multimodal instruction-following models require training data that is accurate, diverse, verifiable, and challenging. Existing synthesis pipelines typic
Echo Software Ltd., a startup that’s using artificial intelligence agents to secure container images, today announced it’s acquiring the assets of Minimus Inc. following the company’s wind-down. The c
We have a limited window to strengthen cyber defenses, and together with organizations including @AnthropicAI, @awscloud, @Google, @Microsoft, and @Oracle, we're calling for a global effort to give de
arXiv:2608.24361v1 Announce Type: new Abstract: Multi-agent LLM systems are increasingly deployed in real-world applications, where failures can be costly and difficult to localize. Despite growing ef
arXiv:2608.23740v1 Announce Type: new Abstract: Concurrent multi-agent coding promises division of labor across modules, robustness through redundancy, and parallel exploration at the natural granular
arXiv:2608.24076v1 Announce Type: new Abstract: Evaluation of agentic information retrieval remains limited to scripted interactions with uniform users, missing both natural personality diversity and
Luz Ding / Bloomberg: Alibaba releases Qwen3.8-Flash, an open-weight, 125B-parameter model built on its next-gen Qwen 4 architecture, saying it rivals Opus 4.6 and V4-Flash — Alibaba Group Holding Ltd
Ollama’s latest release retains all existing functionalities while adding a built‑in web‑search capability. Users can now run research tasks directly through open models that automatically query the i
arXiv:2608.23842v1 Announce Type: cross Abstract: DevOps programming (e.g., using CLI/API scripts or IaC frameworks) is key to cloud infrastructure management. Unlike traditional programming tasks, De
arXiv:2608.24314v1 Announce Type: new Abstract: Evaluating conversational voice agents at scale re- quires reliable assessment methods that capture both observ- able interaction quality and the contex
Brain makes a user’s full history available to Computer without loading all of it into every prompt. Agents can explore it on demand, verify claims against the underlying evidence, and keep it current
arXiv:2507.21790v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are becoming widely used to support various workflows across different disciplines, yet their potential in discre
arXiv:2504.18346v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have been transformative across many domains. However, hallucination, i.e., confidently outputting incorrect info
arXiv:2608.24043v1 Announce Type: new Abstract: Recognizing sequential construction activities is important for collaborative human-robot work; for example, robots are able to understand workers' curr
arXiv:1812.00877v2 Announce Type: replace Abstract: Segmentation of skin lesion boundaries in dermoscopic imaging is an important prerequisite step for computer-aided diagnosis of malignant melanoma,
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
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
Uber has a lot in common with the cities it serves. Both are always changing and growing, both must carefully manage the resulting traffic to prevent congestion and sprawl. Uber has continuously evolv
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
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
We’re excited to introduce v5 Droplets, a new generation of compute built on 5th Gen AMD EPYC™ processors. v5 Droplets are purpose built to deliver higher performance for demanding workloads such as c
arXiv:2608.24087v1 Announce Type: cross Abstract: Current LLM agent systems decide delegation before reasoning begins (a router picks a model) or after a response is complete (a verifier scores it and
Hi everyone, it's been a while since I posted so here's an update on what the Lemonade community has been up to this summer. Our overall mission is to enable local AI builders with everything they nee
arXiv:2608.23803v1 Announce Type: cross Abstract: Lung cancer tissue diagnostics is complex, as therapy decisions in precision oncology rely on the integration of histomorphological, immunohistochemic
arXiv:2608.24065v1 Announce Type: cross Abstract: While recent advances in data synthesis aim to curate high-quality datasets, most generation pipelines still rely on heuristic prompt-based control. T
arXiv:2608.24748v1 Announce Type: cross Abstract: How can humans make sense of the rapid takeoff of artificial intelligence (AI)? We studied the sensemaking dynamics of AI through an open-ended, mixed
arXiv:2608.24340v1 Announce Type: cross Abstract: The prediction of student engagement from the online tutoring videos is difficult because engagement is a multidimensional construct comprising distin
Nutanix Inc. today introduced new capabilities intended to help enterprises run agentic artificial intelligence applications alongside existing virtual machines and containerized workloads without spl
arXiv:2608.24658v1 Announce Type: new Abstract: Scaling test-time reasoning has substantially improved the problem-solving ability of large language models (LLMs), but standard autoregressive decoding
Perplexity.ai published a blog post titled “A Local‑First Agent for Private and Cost‑Effective Knowledge Work” on August 26 2026. The article describes the company’s new local‑first AI agent, which pr
Data preparation determines the ceiling of any supervised fine-tuning project. This first post in a two-part series covers the foundations of SFT data prep: quality checks, conversational (JSONL) form
arXiv:2608.24104v1 Announce Type: cross Abstract: Numerous methods have been developed to quantify feature attributions in individual predictions for tree ensembles. However, many applications require
arXiv:2608.24842v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as AI analysts to process financial disclosures and support AI-assisted investment decisions. Y
arXiv:2608.23611v1 Announce Type: cross Abstract: Large Language Models (LLMs) offer new opportunities for automated code refactoring. However, generated changes must reduce targeted quality problems
arXiv:2608.24671v1 Announce Type: new Abstract: Referring surgical video segmentation requires segmenting a target instrument or tissue region across video frames according to a natural language expre
arXiv:2608.23908v1 Announce Type: new Abstract: Tax-loss harvesting demonstrates consistent benefits to long-term portfolio growth; yet implementing it efficiently often involves complex consideration
arXiv:2608.24011v1 Announce Type: cross Abstract: Chinese ancient document understanding demands complex visual, linguistic, and historical reasoning. Current Large Vision-Language Models (LVLMs) typi
Michael Nuñez / VentureBeat: Salesforce and Anthropic unveil Claudeforce, which brings Salesforce data and workflows into Claude, starting with a plugin featuring 37 prebuilt sales skills — Salesforce
The mystery model Ox Alpha is now available in @AutoClawAIer by @Zai_org It's official name is GLM-5.3-Flash, a next-generation multimodal model for vision-language understanding, code generation, and
There’s been a lot of debate and speculation about the Hugging Face attack over the last month, and many people have been understandably skeptical of simply taking OpenAI’s word for things. I hope our
arXiv:2501.14271v4 Announce Type: replace Abstract: Meta-learning enables models to rapidly adapt to new tasks by leveraging prior experience, but its adaptation mechanisms remain opaque, especially r
We benchmarked 20+ open-weight models on easy-to-hard document extraction tasks through ExtractBench. The results are all available on @huggingface 🤗 ExtractBench is a schema-guided extraction benchma
We built one of the most comprehensive benchmarks for document extraction, and evaluated it across a lot of different systems: ✅ one-shot frontier VLMs ✅ frontier VLMs + coding agent harnesses ✅ one-s
arXiv:2608.24492v1 Announce Type: cross Abstract: Uncertainty quantification (UQ) methods are widely used for hallucination detection in large language models (LLMs) in closed-book settings where grou
Your closed model refused a task it should have done. Ours didn't. DeepSeek V4 Pro on Fireworks: beats Fable 5 on SWE-Bench and LiveCodeBench, a third of the cost per solved task, and it doesn't decli
I ran 11 uncensored variants of Gemma 4 12B that I grabbed from huggingface, sorting by downloads. 10 full abliterations plus 2 LoRA adapters which were requested to be added in the comparison, agains