Knowledge catalogue
arXiv:2606.09671v1 Announce Type: cross Abstract: Alzheimer's disease (AD) progression is highly heterogeneous and is typically observed through sparse and irregular longitudinal data, posing challeng
arXiv:2601.08097v2 Announce Type: replace Abstract: Reward modeling is essential for aligning large language models with human preferences, yet predominant architectures rely on a static pooling strat
arXiv:2511.02748v2 Announce Type: replace-cross Abstract: We argue that sixth-generation (6G) intelligence is not fluent token prediction but the capacity to imagine and choose -- to simulate future s
arXiv:2603.08683v2 Announce Type: replace-cross Abstract: Autoregressive 'language' models (LMs) trained on raw waveforms can be repurposed for lossless audio compression, but prior work is limited to
arXiv:2604.03779v2 Announce Type: replace-cross Abstract: Diffusion models have excelled at generative tasks for both continuous and token-based domains, but their application to discrete ordinal data
I really do think we'll see a lot of value accrue in AI startups building 'model routing as a service' Not just OpenRouter - this includes a much broader set of verticalized agents and infrastructure.
arXiv:2602.06245v2 Announce Type: replace-cross Abstract: Neural-network techniques are often transferred across architecture families by analogy, but such transfer is valid only when the assumptions
Interesting model here 35b a3b trained for agentic use It gets 60.7 on Terminal Bench2 qwen 3.6 27b gets 59.3 Essentially the same Going to have to try it out https://huggingface.co/nex-agi/Nex-N2-min
Model routing is growing a lot these days Good take My guess is - demand for intelligence is near infinite - but 80% of workloads will be running on 99% cheaper models within 12-18 months - 20% of wor
Seeing a number of benchmarks showing Opus is the best model for long-running work. Five tips for running Opus autonomously for hours/days: 1. Use auto mode for permissions, so Claude doesn’t ask for
Xiaomi achieved over 1,000 tokens per second output from a 1 trillion-parameter model using a single standard 8-GPU commodity node through extreme model-system codesign . The approach combines FP4 qua
arXiv:2606.05339v1 Announce Type: cross Abstract: MCP (Model Context Protocol) enables LLMs (Large Language Models) to interact with external tools and data sources via a standardized protocol. Its ra
arXiv:2606.06360v1 Announce Type: new Abstract: Modelling individual decision-making during infectious disease outbreaks is crucial for understanding behavioural dynamics and informing effective publi
arXiv:2606.05413v1 Announce Type: cross Abstract: As urban environments continue to evolve rapidly, accurately modeling the dynamic behaviour of Points of Interest is essential for supporting data-dri
arXiv:2606.05855v1 Announce Type: cross Abstract: Continuous electroencephalography (EEG) emotion prediction aims to model the temporal evolution of human emotional states from EEG signals. Unlike con
arXiv:2509.20324v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) is an emerging approach in natural language processing that combines large language models (LLMs) with ex
arXiv:2606.05167v1 Announce Type: cross Abstract: Realism is a central yet seemingly under-theorized concept in Agent-Based Modelling. This paper presents a Systematic Literature Review, aiming to ide
Coco Feng / South China Morning Post: A research team that includes Huawei says it successfully used Huawei's Ascend 910C chips for DeepSeek V4 Pro model's post-training, amid increased US sanctions —
arXiv:2606.05742v1 Announce Type: new Abstract: Speculative decoding accelerates generation by verifying multiple drafted tokens in a single target-model forward pass, reducing sequential decoding ite
arXiv:2606.04930v1 Announce Type: cross Abstract: Real-time data analysis requires the ability to accurately and adaptively address nonlinear dynamics in a nonstationary data stream while preserving c
arXiv:2606.04911v1 Announce Type: cross Abstract: Breast cancer remains a leading cause of cancer-related mortality among women. Its clinical management requires multimodal reasoning across a clinical
Introducing NVIDIA Nemotron 3 Ultra. A frontier smart open model built for long-running agents that need to plan, reason, use tools and keep working across complex coding, research and enterprise work
Nemotron 3 Ultra (550B-A55B) is here - our strongest open-weight model and full training recipe to date. Heavy emphasis on real-world inference efficiency for long-context agentic workloads. Everythin
NVIDIA Nemotron 3 Ultra is on Fireworks, day zero. Nemotron Ultra is an open model for frontier reasoning and orchestration in long-running autonomous agents. Think use cases like coding agents, deep
arXiv:2606.04104v1 Announce Type: cross Abstract: Agent systems execute through runtimes with very different control points: local coding tools, framework SDKs, managed agent platforms, API gateways,
Dina Bass / Bloomberg: Robotics startup Generalist, which released its GEN-1 model to complete short physical tasks in April, raised 400M led by Radical Ventures at a 2B valuation — The company raised
arXiv:2606.04579v1 Announce Type: new Abstract: While Process Reward Models (PRMs) have achieved remarkable success in mathematical reasoning, their application in complex scientific domains-such as b
Carl Franzen / VentureBeat: Alibaba releases Qwen3.7-Plus, a multimodal proprietary model with a 1M-token context window, costing $2 per 1M tokens, 60% less than text-only Qwen3.7-Max — However, like
arXiv:2606.03874v1 Announce Type: new Abstract: We present DyaPlex, a streaming, full-duplex speech-and-motion model designed for dyadic interaction. To capture the continuous and reciprocal nature of
Gemma 4 model load issues fixed in engine version 2.20.1. lms runtime update --all Gemma 4 12B is here! Dense, mid-sized Gemma that fits right on your laptop - released by @google under Apache 2.0 Ava
arXiv:2510.16282v2 Announce Type: replace Abstract: Personalized large language models (LLMs) tailor content to individual preferences using user profiles or histories. However, existing parameter-eff
Gemma4 is a model available through the Ollama library that can be downloaded and run locally on personal hardware. The model represents Google's Gemma series advancement and is accessible via Ollama'
arXiv:2606.03159v1 Announce Type: cross Abstract: As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-lo
Startup discovery platform @harmonic_ai rebuilt Scout, their AI platform using Deep Agents and LangSmith. Deep Agents: One frontier model + two tool sets (global company data and firm-specific context
We’re bringing new capabilities to GPT-Rosalind, a model series purpose-built for life sciences research at enterprise scale. It brings GPT-5.5’s agentic coding and tool use together with stronger int
arXiv:2606.03391v1 Announce Type: cross Abstract: Model merging has emerged as a cost-effective approach for consolidating the capabilities of multiple LLMs without retraining. However, existing mergi
arXiv:2606.00489v1 Announce Type: new Abstract: Placenta Accreta Spectrum (PAS) is a rare but highly dangerous obstetric disease. Early and accurate PAS diagnosis is critical for maternal health. Trad
arXiv:2606.01027v1 Announce Type: new Abstract: Robotic manipulation requires models that generate executable actions while anticipating and evaluating their future consequences before physical execut
arXiv:2403.07008v3 Announce Type: replace-cross Abstract: The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming. AI-labeled synthetic data c
arXiv:2606.00065v1 Announce Type: cross Abstract: Automated extraction of materials composition-property data from scientific literature has advanced considerably with the development of large languag
arXiv:2606.00094v1 Announce Type: cross Abstract: Image generative models aim to sample data points from the underlying data manifold, a task that requires learning and decoding a dense, low-dimension
arXiv:2601.09696v2 Announce Type: replace Abstract: LLMs are increasingly being integrated into clinical workflows, yet they often lack clinical empathy, an essential aspect of effective doctor-patien
arXiv:2606.00544v1 Announce Type: cross Abstract: Modern language-model fine-tuning typically pairs each prompt with a single response, even though many prompts admit multiple valid completions. This
arXiv:2606.00539v1 Announce Type: new Abstract: Training stability is a key bottleneck in low-precision language model training: efficient low-cost paths can still produce short-lived numerical risks
Adds knowledge to Ollama models using Retrieval-Augmented Generation (RAG) , where users create a knowledge base directory with reference files like PDFs, text files, or CSVs . A custom model can be c
arXiv:2511.05650v2 Announce Type: replace-cross Abstract: Alignment has greatly improved large language models (LLMs)' output quality at the cost of diversity, yielding highly similar outputs across g
arXiv:2606.01485v1 Announce Type: new Abstract: We describe our submission to the VRR Challenge @ CVPR 2026, built on the ImplicitQA / VRR-QA benchmark~ite{implicitqa}: multiple-choice video question
arXiv:2601.22947v2 Announce Type: replace Abstract: Masked diffusion language models (MDLMs) generate text by unmasking tokens in parallel and have recently emerged as alternatives to autoregressive l
arXiv:2603.08000v2 Announce Type: replace Abstract: Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasonin
Step-3.7-Flash is a compact language model from StepFun AI that reportedly achieves top-tier performance among models under 500 billion parameters on Hugging Face leaderboards, despite receiving limit
arXiv:2506.14003v5 Announce Type: replace Abstract: Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowl
If you’re iterating on deploying large language models (LLMs) on AWS GPU instances, you’ve probably noticed the larger the model to be loaded into GPU High Bandwidth Memory (HBM), the longer the painf
Bernini is a unified framework for video editing and video generation , built using Wan2.2-A14B as its renderer . The model covers complementary task families that demonstrate its capabilities as a un
arXiv:2512.19673v3 Announce Type: replace-cross Abstract: Existing reinforcement learning (RL) approaches treat large language models (LLMs) as a unified policy, overlooking their internal mechanisms.
arXiv:2605.30808v1 Announce Type: cross Abstract: Preference alignment is a crucial post-training step for large language models (LLMs) to ensure their outputs align with human values. However, post-t
arXiv:2605.31487v1 Announce Type: new Abstract: Deploying computer vision models in Warehouse Facilities traditionally requires extensive resources for camera mounting, image collection, annotation, t
arXiv:2603.23398v2 Announce Type: replace-cross Abstract: Generative modeling of discrete data, such as graphs, underpins many scientific and industrial applications, including molecular discovery and
Many research labs only consider inference efficiency after the fact. Step 3.7 Flash is a 196B MoE model, and built for inference from the start by @StepFun_ai. Multi-Matrix Factorization Attention (M
arXiv:2605.31036v1 Announce Type: cross Abstract: Online advertising platforms rely on machine learning models to predict click-through rates (pCTR) and conversion rates (pCVR) for auction mechanisms.
arXiv:2605.30383v1 Announce Type: cross Abstract: Scaling individual robot capabilities is common but costly. Here we investigate a system-level design question in real-world multi-robot coordination: