model releases

arXiv:2510.26615v3 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) extends large language models (LLMs) with external knowledge, but it must balance limited effective context, re

arXiv:2601.10003v2 Announce Type: replace Abstract: Constructing Knowledge Graphs (KGs) from unstructured text provides a structured framework for knowledge representation and reasoning, yet current L

arXiv:2604.21356v1 Announce Type: new Abstract: High-quality digital terrain models derived from airborne laser scanning (ALS) data are essential for a wide range of geospatial analyses, and their gen

arXiv:2604.21284v1 Announce Type: new Abstract: MemPalace is an open-source AI memory system that applies the ancient method of loci (memory palace) spatial metaphor to organize long-term memory for l

arXiv:2604.21094v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) excel on relational data, but standard benchmarks unrealistically assume the graph is centrally available. In practice, set

Fireworks AI announced the release or deployment of DeepSeek V4, a large language model, alongside another project or update called 'Spud' on the same day, with the team planning to work through the n

arXiv:2604.21214v1 Announce Type: cross Abstract: Text-to-SQL models have significantly improved with the adoption of Large Language Models (LLMs), leading to their increasing use in real-world applic

arXiv:2604.21700v1 Announce Type: cross Abstract: The growing application of large language models (LLMs) in safety-critical domains has raised urgent concerns about their security. Many recent studie

arXiv:2604.21282v1 Announce Type: cross Abstract: Automated code vulnerability detection is critical for software security, yet existing approaches face a fundamental trade-off between detection accur

arXiv:2603.21697v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visual

arXiv:2604.21689v1 Announce Type: cross Abstract: Creative face stylization aims to render portraits in diverse visual idioms such as cartoons, sketches, and paintings while retaining recognizable ide

arXiv:2604.21211v1 Announce Type: new Abstract: Current text anonymization evaluation relies on span-based metrics that fail to capture what an adversary could actually infer, and assumes a single dat

arXiv:2511.03325v3 Announce Type: replace Abstract: Video Question Answering (VideoQA) in the surgical domain aims to enhance intraoperative understanding by enabling AI models to reason over temporal

arXiv:2604.21346v1 Announce Type: new Abstract: Vision--language models (VLMs) often fail on abstract visual reasoning benchmarks such as Bongard problems, raising the question of whether the main bot

arXiv:2604.21801v1 Announce Type: cross Abstract: Recent advances in deep learning for remote sensing rely heavily on large annotated datasets, yet acquiring high-quality ground truth for geometric, r

arXiv:2604.21031v1 Announce Type: cross Abstract: Synthetic data generation offers promise for addressing data scarcity and privacy concerns in educational technology, yet practitioners lack empirical

arXiv:2604.21806v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) is an important image retrieval paradigm that enables users to retrieve a target image using a multimodal query that cons

arXiv:2604.21930v1 Announce Type: new Abstract: Streaming Continual Learning (CL) typically converts a continuous stream into a sequence of discrete tasks through temporal partitioning. We argue that

Tesla FSD is the first AI saving lives at scale....on real roads every single day Road accidents kill 1.19 million people every year - the #1 cause of death for ages 5–29 94%+ of crashes are caused by

This analysis examines the token consumption and economics of coding assistants, likely comparing different AI models' efficiency and cost-effectiveness for code generation tasks. The piece probably d

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. We’re in a new era of AI-driven scams When ChatGPT was release

arXiv:2604.21210v1 Announce Type: cross Abstract: In continuously monitored quantum systems, the feedback protocol of Garcia-Pintos, Liu, and Gorshkov reshapes the arrow of time: a Hamiltonian H_{meas

arXiv:2604.21312v1 Announce Type: cross Abstract: This paper presents the NTIRE 2026 Remote Sensing Infrared Image Super-Resolution (x4) Challenge, one of the associated challenges of NTIRE 2026. The

The Newton–Schulz iteration coefficients optimized by DeepSeek-V4 are surprisingly strong: they effectively normalize all singular values to 1. This matches our previous intuition: a well-balanced spe

arXiv:2604.20917v1 Announce Type: cross Abstract: Large language models (LLMs) have shown remarkable capabilities across diverse coding tasks. However, their adoption requires a true understanding of

arXiv:2604.21215v1 Announce Type: new Abstract: Transformers process tokens in parallel but are temporally shallow: at position t, each layer attends to key-value pairs computed based on the previous

arXiv:2604.20874v1 Announce Type: cross Abstract: Every system that maintains a large language model conversation beyond a single session faces two inescapable constraints: the context window is finit

Jonathan Stempel / Reuters: The US CFTC sues New York, accusing the state of invading its authority to regulate prediction markets by filing lawsuits against Coinbase and Gemini — The U.S. Commodity F

DeepSeek V4 Pro is a new AI model release from Chinese AI company DeepSeek, announced via Hugging Face. The post expresses enthusiasm about the model's capabilities and performance, suggesting it repr

These pelicans are kind of angry looking! Left is deepseek-v4-flash, right is deepseek-v4-pro - both generated using OpenRouter via my LLM tool 🚀 DeepSeek-V4 Preview is officially live & open-sourced!

arXiv:2604.20983v1 Announce Type: cross Abstract: Vision evaluations are typically done through multi-step processes. In most contemporary fields, experts analyze images using structured, evidence-bas

This has been the most anticipated event in OSS and it doesn't disappoint. Congratulations to @deepseek_ai team. DSV4 Pro is now available on @togethercompute and we'll be adding a lot of capacity beh

this is probably the most important piece of software of the decade next to vllm and sglang. i'm not joking. llama.cpp at 100k stars now that 90% of the code worldwide is being written by AI agents, I

This is where we are right now. And i’m not gonna lie it feels pretty magical 🧚‍♀️ Qwen3.6 27B running inside of Pi coding agent via Llama.cpp on the MacBook Pro For non-trivial tasks on the @huggingf

On Friday, Chinese AI firm DeepSeek released a preview of V4, its long-awaited new flagship model. Notably, the model can process much longer prompts than its last generation, thanks to a new design t

arXiv:2511.18539v2 Announce Type: replace-cross Abstract: We propose TimePre, a simple framework that unifies the efficiency of Multilayer Perceptron (MLP)-based models with the distributional flexibi

arXiv:2604.21632v1 Announce Type: new Abstract: We investigate the ability of decoder-only transformer models to perform abstract symbolic reasoning; specifically solving propositional logic reasoning

arXiv:2604.21816v1 Announce Type: new Abstract: The Model Context Protocol (MCP) has become a common interface for connecting large language model (LLM) agents to external tools, but its reliance on s

arXiv:2604.21197v1 Announce Type: new Abstract: Federated Large Language Models (FedLLMs) enable multiple parties to collaboratively fine-tune LLMs without sharing raw data, addressing challenges of l

arXiv:2510.03247v2 Announce Type: replace-cross Abstract: Active learning (AL) is a principled strategy to reduce annotation cost in data-hungry deep learning. However, existing AL algorithms focus al

arXiv:2604.21696v1 Announce Type: new Abstract: Tabular foundation models aim to learn universal representations of tabular data that transfer across tasks and domains, enabling applications such as t

arXiv:2604.21860v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This pape

arXiv:2604.21093v1 Announce Type: cross Abstract: We introduce TravelFraudBench (TFG), a configurable benchmark for evaluating graph neural networks (GNNs) on fraud ring detection in travel platform g

arXiv:2604.21263v1 Announce Type: new Abstract: extbf{Background:} Regulatory frameworks for AI in healthcare, including the EU AI Act and FDA guidance on AI/ML-based medical devices, require clinical

Cognition AI announced an early preview opportunity for Devin integrated with GPT-5.5 Agent capabilities, inviting users to test the combination at devin.ai. This likely represents an update to Devin'

arXiv:2604.21327v1 Announce Type: cross Abstract: Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization sig