Knowledge catalogue
arXiv:2610.19138v1 Announce Type: cross Abstract: How well can a language model turn a large, incomplete and partly contradictory body of documents into a plan when no single correct answer exists? We
Meet NVIDIA Nemotron 3.5 Super VL Our new open model combines reasoning and tool use with text, image, document, and video understanding for long-running AI agents. 120B total parameters with 12B acti
Meta Platforms Inc. today released open weights for its Muse Spark artificial intelligence model, which had been proprietary since its April debut. The release, called Muse Spark Open, is built for co
Microsoft AI: Microsoft unveils MAI-Base-2, a MoE model with 2.8T total and 80B active parameters, claiming 4x-12x more pretraining FLOPs-efficiency than DeepSeek-V4-Pro-Base — In June, we announced M
arXiv:2606.16710v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) are credited with solving complex problems, yet their agents routinely act on context that may be false. Prior work
NVIDIA Nemotron 3.5 Super VL is now available on Ollama This model combines reasoning and visual understanding across a range of agent workflows. On a single GPU, this model delivers up to 5x higher t
NVIDIA’s open‑source Nemotron 3.5 Super VL is a 120 B parameter mixture‑of‑experts multimodal model that activates only 12 B parameters per token, enabling combined reasoning, instruction following, t
NVIDIA’s Nemotron 3.5 Super VL is now available to run on the Together AI compute platform through an API. The model page—providing pricing, benchmarks, and documentation—is hosted at together.ai/mode
Jeffrey Kampman / Tom's Hardware: Nvidia's RTX Spark Superchip in the Surface Laptop Ultra outperforms Apple's M5 Max MacBook Pro by ~25% in agentic AI completion benchmarks using Qwen models — Laying
NVIDIA today released Nemotron 3.5 Super VL, an open 120-billion-parameter model that delivers the fastest task completion and highest accuracy for specialized always-on agents. Joining it are two new
arXiv:2610.19048v1 Announce Type: new Abstract: Record linkage and demographic inference from names are routine demands in social science. Most approaches to these problems require labeled training da
arXiv:2610.19872v1 Announce Type: new Abstract: A reasoning prompt can improve one deployment and degrade another. RCCM (Reasoning-Control Capability Mismatch) examines these reversals by pairing answ
arXiv:2610.15513v1 Announce Type: cross Abstract: Safety-aligned large language models (LLMs) remain vulnerable to adversarial prompts that bypass their safety training. Existing automated red-teaming
arXiv:2610.15897v2 Announce Type: cross Abstract: Qwen3-8B reviewing Llama-3.1-8B in math adds 33.2 points, yet Qwen3-8B alone is 6.4 points more accurate than the result. Reviewing another model's an
arXiv:2610.15218v1 Announce Type: new Abstract: A recurrent-depth language model reuses one block of weights several times in a row. The number of repetitions, which we call loops, is chosen when the
arXiv:2610.19869v1 Announce Type: cross Abstract: We introduce SEA-HELM Audio, a Southeast Asian (SEA) multilingual evaluation framework that extends the text-based SEA-HELM benchmark to assess perfor
arXiv:2610.16412v1 Announce Type: new Abstract: As IT systems grow in complexity, automated agent-driven incident response becomes increasingly critical. A key capability for these agents is summarizi
arXiv:2610.18745v1 Announce Type: cross Abstract: Large language models increasingly generate Solidity smart contracts that, once deployed, can never be patched, making a single latent fault permanent
arXiv:2610.17907v1 Announce Type: cross Abstract: The code generation capabilities of large language models (LLMs) can equally be misused to implement harmful functionality, underscoring the need to u
arXiv:2610.17309v1 Announce Type: cross Abstract: We introduce StartLux-Decision, decision models from 0.8B to 27B parameters that combine efficient single-pass prediction with adaptive, confidence-gu
arXiv:2610.19359v1 Announce Type: cross Abstract: Activation steering adds a vector to a model's hidden states to control a named behaviour. A gain on that behaviour, however, does not show that the v
arXiv:2610.19557v1 Announce Type: new Abstract: Contrastive learning for time series depends on deciding which pairs of inputs should be treated as similar and dissimilar. Because few augmentations re
arXiv:2610.17301v1 Announce Type: new Abstract: Language-model agents sometimes act beyond their authorization and then misreport what they did. On CAPE-Bench, matched agent tasks in which one fact de
arXiv:2610.14360v1 Announce Type: new Abstract: Large language model (LLM) alignment often assumes that the user interacting with a model is also the primary beneficiary of its behavior. Yet in many c
arXiv:2610.18420v1 Announce Type: cross Abstract: We trained Agaram 2.5B, a 2.5-billion-parameter Tamil-English language model, from scratch on about 50 billion tokens (58% Tamil, the rest English, ma
arXiv:2610.17190v1 Announce Type: new Abstract: Geographic coordinates are common inputs in applied machine learning, but latitude and longitude describe position rather than the surrounding environme
arXiv:2610.14214v1 Announce Type: new Abstract: Hallucination detection is critical for ensuring the reliability of Large Language Models (LLMs) in real-world deployments. While recent works, such as
arXiv:2610.17370v1 Announce Type: new Abstract: Scientific discovery with language models requires finding the best valid solution within a finite computational budget. We study how feedback from this
Interesting new research from Meta Superintelligence Labs It discusses how reward hacking affects coordination in multi-agent coding systems. Coding agents on a team share code, memory, and plans, so
Tessera-27B-B-CJK is a Qwen3.8-27B coding agent that thinks in compressed CJK, and it spends fewer tokens doing it. Open weights, Apache-2.0. This is our first full 'Tessera' lineup model drop! - Hugg
arXiv:2610.15589v1 Announce Type: new Abstract: Many deployed distillation pipelines show the student a truncated view of the teacher: keep the top-k probabilities, renormalize, and minimize a diverge
arXiv:2610.15570v1 Announce Type: cross Abstract: Settling one comparison between two truncation samplers has cost six thousand A100-hours, and nothing says in advance how far apart two samplers can b
arXiv:2610.15961v1 Announce Type: cross Abstract: Emergent misalignment (EM) occurs when fine-tuning a language model to a narrow task makes it misaligned on unrelated ones. Because organizations now
Welcome to Mistral, New Material. Let’s bring design to mission-critical AI. New Material joins @MistralAI to design the frontier. Over the last 6 years we've teamed up with ambitious organisations tr
What AI Safety needs is better tooling and engineering. For instance, building stronger red-teaming tools. Great to see this open-source effort to red-team image models. It seems to learn better ways
1) Trying again. TLDR: Everyone can win. Open-source, frontier labs, infrastructure, applications and most importantly the American people. I understand all of the jitters about Anthropic losing share
Americans have big concerns about artificial intelligence, but that hasn’t stopped OpenAI Inc., Nvidia Corp., IBM Corp. and others from charging ahead. Last week saw shares of Nvidia, CoreWeave Inc.,
OpenDocRouter makes it dead-simple to start parsing your documents across on ton of frontier Models (gemini, luna) and latest OSS models (LightOnOCR-3, MinerU2.5-pro). Parse your first document in 60
Quartermaster (my local inference manager: one server that swaps llama.cpp, image, audio and video models in and out of VRAM) can now help you server and manage decision models: Auto-discovered. Drop
This is my new favorite way to keep up with AI papers. I turn my curated papers into a 2-minute spoken technical briefing with @FishAudio Drama 3, straight from Codex. In the demo, I took one of my fa
arXiv:2610.13627v1 Announce Type: new Abstract: Evaluating large language models (LLMs) on AMLworld's smallest test splits is costly because each of over a million targets requires a separate graph pr
Enterprise AI scalability is running into a hard budget wall for some customers. As agentic workloads multiply, cloud token bills are consuming allocations faster than planned, prompting companies to
arXiv:2610.12998v1 Announce Type: new Abstract: Creativity benchmarks for large language models (LLMs) vary widely in task and metric design. This raises the question of whether they capture a common
arXiv:2610.12617v1 Announce Type: new Abstract: Geopolitical and strategic intelligence reports constitute a rich source of expert knowledge and have increasing value in the current political climate,
Mistral AI announced its Le Chonk model, which performs visual grounding by accurately locating objects within images. On the Dense 200 benchmark it achieved a 42 % score, outperforming even frontier‑
arXiv:2610.13534v1 Announce Type: new Abstract: Long-horizon embodied agents must maintain task-relevant information, coordinate heterogeneous robots, and adapt their decisions as execution unfolds. E
Meta is making up for lost time in the AI race. After launching Muse Spark, the first model from its revamped Superintelligence Labs division, and buzzy AI agent Muse, it's now launching two new model
arXiv:2610.13386v1 Announce Type: new Abstract: Stance detection remains challenging for large language models (LLMs) due to implicit opinions, sarcasm, and context-dependent expressions of stance. Al
arXiv:2610.13895v1 Announce Type: cross Abstract: Large language models reuse the same attention heads across tasks, but identifying these shared heads does not explain what they do differently in eac
arXiv:2610.12863v1 Announce Type: new Abstract: Satirical news is a unique form of misinformation: it is intended to be humorous by the original publication source but can be misinterpreted. Explanati
Introducing Multi-Agent Self-Supervision (MASS): Recursive self-improvement through collective intelligence Blog: https://pub.sakana.ai/mass/ As AI systems tackle increasingly open-ended research prob
New paper from the team at Sakana AI: Recursive Self-Improvement through Multi-Agent Self-Supervision (MASS) How do we keep improving AI when the tasks become too complex for humans to reliably evalua
One of the biggest historical bottlenecks for training specialized models has been curating ground-truth. This is typically a very labor intensive process done with human supervision. Now frontier mod
I have an app that processes ~500 different documents every day. An agent analyzes them, sorts them, tags them, extracts various legal nuances, creates descriptions, etc. So far I've been using Qwen 3
I love Dash2Dock Lite, but Icedman is always a week or two before updates. I randomly ran pacman for the first time in weeks, not realizing GNOME had a major update. I told it to fix it in DeepSeek Ha
For what it's worth. I'm a mechanical engineer by education and software engineer in practice over the past ~20 years. Playing around with local models has been a recent hobby. Today I decided to do a
I was curious about how omni decision models could be used in rescue workers bodycams or smart glasses, so I decided to build a quick demo. I went with @liquidai d1-omni-600M since it supports both vi
arXiv:2610.11050v1 Announce Type: new Abstract: Computer-use agents are capable of completing complex tasks, increasing the use of automatic judges to determine success, either for training or for eva
arXiv:2610.10946v1 Announce Type: new Abstract: Large language models (LLMs) are entering wildfire management, where overstated evaluations can cost property and lives. How do they perform on wildfire
arXiv:2610.12445v1 Announce Type: cross Abstract: Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We show that white-box deception d