model releases

From Traditional Taggers to LLMs: A Comparative Study of POS Tagging for Medieval Romance Languages

arXiv:2605.09147v1 Announce Type: cross Abstract: Part-of-speech (POS) tagging for Medieval Romance languages remains challenging due to orthographic variation, morphological complexity, and limited a

Model Releases

Function-Space ADMM for Decentralized Federated Learning: A Control Theoretic Perspective

DGX agent

arXiv:2605.09356v1 Announce Type: new Abstract: Decentralized federated learning (FL) is a promising approach for training machine learning models on sensor networks, Internet of Things (IoT) devices,

model-releasesarxiv-cs-lg

12 May 2026

GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives

arXiv:2605.09027v1 Announce Type: new Abstract: In multi-agent systems (MAS), a single deceptive agent can nullify all gains of an agentic AI collective and evade deployed defenses. However, existing

Gemini’s biggest new features are all about controlling your phone

model-releasesthe-verge-ai

It is, once again, Gemini season. Google is announcing a host of new Gemini features during its pre-I/O Android showcase, many of which aim to help use your phone for you. You'll find Gemini in more p

General Agent Evaluation

arXiv:2602.22953v2 Announce Type: replace Abstract: General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measur

Generating Leakage-Free Benchmarks for Robust RAG Evaluation

arXiv:2605.08838v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is widely used to augment large language models (LLMs) with external knowledge. However, many benchmark datasets,

Generating Symmetric Materials using Latent Flow Matching

arXiv:2605.10115v1 Announce Type: new Abstract: Tackling the task of materials generation, we aim to enhance the previously proposed All-atom Diffusion Transformer (ADiT) by introducing SymADiT, a sym

Generative Actor-Critic with Soft Bridge Policies

arXiv:2605.08733v1 Announce Type: new Abstract: Expressive generative policies such as diffusion and flow models are appealing for MaxEnt online reinforcement learning because of their ability to mode

Generative AI Fuels Solo Entrepreneurship, but Teams Still Lead at the Top

arXiv:2605.10291v1 Announce Type: cross Abstract: Recent advances in generative artificial intelligence (AI) are reshaping who enters entrepreneurship, but not who reaches the top of the quality distr

GenMed: A Pairwise Generative Reformulation of Medical Diagnostic Tasks

arXiv:2605.10645v1 Announce Type: new Abstract: Data-driven medical AI is traditionally formulated as a discriminative mapping from input X to output Y via a learned function f, which does not general

Geometrically Constrained Stenosis Editing in Coronary Angiography via Entropic Optimal Transport

arXiv:2605.08851v1 Announce Type: cross Abstract: The scarcity of high-quality imaging data for coronary angiography (CAG) stenosis limits the clinical translation of automated stenosis detection. Syn

Geometry-Aware Discretization Error of Diffusion Models

arXiv:2605.08392v1 Announce Type: new Abstract: Practical diffusion sampling is a numerical approximation problem: under a fixed inference budget, one must simulate a reverse-time ODE or SDE using onl

Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training

arXiv:2605.09608v1 Announce Type: new Abstract: Continual post-training aims to extend large language models (LLMs) with new knowledge, skills, and behaviors, yet it remains unclear when sequential up

Geometry-free prediction of inertial lift forces in microfluidic devices using deep learning

arXiv:2605.08109v1 Announce Type: new Abstract: Inertial microfluidic devices (IMDs) offer low-cost, high-throughput alternative techniques for many traditional particle- (or cell-) manipulation tasks

Geospatial-Temporal Sensemaking of Remote Sensing Activity Detections with Multimodal Large Language Model

arXiv:2605.10739v1 Announce Type: cross Abstract: We introduce SMART-HC-VQA, a Sentinel-2-based visual question answering dataset derived from the IARPA SMART Heavy Construction dataset, designed for

GIFT: Guided Importance-Aware Fine-Tuning for Diffusion Language Models

arXiv:2509.20863v3 Announce Type: replace Abstract: Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approa

GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction

arXiv:2605.10108v1 Announce Type: new Abstract: Joint named entity recognition (NER) and relation extraction (RE) is a fundamental task in natural language processing for constructing knowledge graphs

GLiNER2-PII: A Multilingual Model for Personally Identifiable Information Extraction

arXiv:2605.09973v1 Announce Type: cross Abstract: Reliable detection of personally identifiable information (PII) is increasingly important across modern data-processing systems, yet the task remains

Global Optimization via Softmin Energy Minimization

arXiv:2509.17815v2 Announce Type: replace Abstract: Global optimization, particularly for non-convex functions with multiple local minima, poses significant challenges for traditional gradient-based m

GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping

arXiv:2603.12275v1 Announce Type: cross Abstract: Unlearning knowledge is a pressing and challenging task in Large Language Models (LLMs) because of their unprecedented capability to memorize and dige

Google announces Gemini Intelligence, bundling existing and new Gemini features, including task automation across apps and vibe-coding own Android widgets (Allison Johnson/The Verge)

Allison Johnson / The Verge: Google announces Gemini Intelligence, bundling existing and new Gemini features, including task automation across apps and vibe-coding own Android widgets — We're one ste

model-releasestechmeme

Google debuts Gemini Intelligence automation features, Googlebook laptop series

model-releasessiliconangle

Google LLC is upgrading its consumer device portfolio with a set of Android features called Gemini Intelligence and a new laptop series. The company debuted the products today during a virtual event c

Google DeepMind details a Gemini-powered mouse pointer that understands what it is pointing at, allowing users to perform tasks without using text-heavy prompts (Google DeepMind)

Google DeepMind: Google DeepMind details a Gemini-powered mouse pointer that understands what it is pointing at, allowing users to perform tasks without using text-heavy prompts — We are developing mo

model-releasestechmeme

Google launches Intrusion Logging, an Android feature developed in partnership with Amnesty International and others, on Android 16 Pixel devices for now (Tim Starks/CyberScoop)

Tim Starks / CyberScoop: Google launches Intrusion Logging, an Android feature developed in partnership with Amnesty International and others, on Android 16 Pixel devices for now — Intrusion Logging m

model-releasestechmeme

GraphBench: Next-generation graph learning benchmarking

arXiv:2512.04475v5 Announce Type: replace-cross Abstract: Machine learning on graphs has made substantial progress across domains such as molecular property prediction and chip design. Yet benchmarkin

GravityGraphSAGE: Link Prediction in Directed Attributed Graphs

arXiv:2605.09408v1 Announce Type: new Abstract: Link prediction (inferring missing or future connections between nodes in a graph) is a fundamental problem in network science with widespread applicati

Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking

arXiv:2605.10893v1 Announce Type: new Abstract: Large vision-language models suffer from visual ungroundedness: they can produce a fluent, confident, and even correct response driven entirely by langu

Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward Models

arXiv:2603.16253v2 Announce Type: replace-cross Abstract: Vision-language process reward models (VL-PRMs) are increasingly used to score intermediate reasoning steps and rerank candidates under test-t

GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs

arXiv:2508.20325v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) become increasingly integral to various domains, their potential to generate harmful responses has prompted si

H-POPE: Hierarchical Polling-based Probing Evaluation of Hallucinations in Large Vision-Language Models

arXiv:2411.04077v2 Announce Type: replace Abstract: By leveraging both texts and images, large vision language models (LVLMs) have shown significant progress in various multi-modal tasks. Nevertheless

Hidden Error Awareness in Chain-of-Thought Reasoning: The Signal Is Diagnostic, Not Causal

arXiv:2605.09502v1 Announce Type: cross Abstract: Chain-of-thought (CoT) prompting assumes that generated reasoning reflects a model's internal computation. We show this assumption is wrong in a speci

HiDrive: A Closed-Loop Benchmark for High-Level Autonomous Driving

arXiv:2605.09972v1 Announce Type: cross Abstract: End-to-end autonomous driving has witnessed rapid progress, yet existing benchmarks are increasingly saturated, with state-of-the-art models achieving

Hierarchical Reinforced Trader (HRT): A Bi-Level Approach for Optimizing Stock Selection and Execution

arXiv:2410.14927v2 Announce Type: replace-cross Abstract: Automated equity trading requires converting noisy market and news signals into executable portfolio decisions under risk, turnover, and trans

High Precision Hydraulic Excavator Control for Heavy-Duty Grading

model-releasesarxiv-cs-ro

arXiv:2605.09465v1 Announce Type: new Abstract: High-precision heavy-duty grading is a common step in earthworks, traditionally carried out manually by skilled operators. Removing a significant amount

Higher-Order Equilibrium Tracking for EM-Compressible Online Estimation

arXiv:2605.08864v1 Announce Type: new Abstract: We study online estimation in latent-variable models by recasting the problem as tracking a moving empirical equilibrium. Standard online EM and stochas

Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning

arXiv:2605.10546v1 Announce Type: new Abstract: Pixel-based deep reinforcement learning agents are typically trained on heavily downsampled visual observations, a convention inherited from early bench

Hint Tuning: Less Data Makes Better Reasoners

arXiv:2605.08665v1 Announce Type: new Abstract: Large reasoning models achieve high accuracy through extended chain-of-thought but generate 5--8 more tokens than necessary, applying verbose reasoning

Holmes: A Benchmark to Assess the Linguistic Competence of Language Models

arXiv:2404.18923v5 Announce Type: replace Abstract: We introduce Holmes, a new benchmark designed to assess language models (LMs) linguistic competence - their unconscious understanding of linguistic

HOME-KGQA: A Benchmark Dataset for Multimodal Knowledge Graph Question Answering on Household Daily Activities

arXiv:2605.09348v1 Announce Type: cross Abstract: Large Language Models (LLMs) provide flexible natural language processing capabilities, while knowledge graphs (KGs) offer explicit and structured kno

HoReN: Normalized Hopfield Retrieval for Large-Scale Sequential Model Editing

arXiv:2605.08143v1 Announce Type: cross Abstract: Large language models encode vast factual knowledge that inevitably becomes outdated or incorrect after deployment, yet retraining is costly prohibiti

How NVIDIA engineers and researchers build with Codex

NVIDIA engineers and researchers utilize OpenAI's Codex, a large language model trained on code, to accelerate software development and improve productivity across their engineering workflows. The art

model-releasesopenai

HS-FNO: History-Space Fourier Neural Operator for Non-Markovian Partial Differential Equations

arXiv:2605.09523v1 Announce Type: new Abstract: Neural operators provide fast surrogate models for time-dependent partial differential equations, but their standard autoregressive use usually assumes

Human-Inspired Memory Architecture for LLM Agents

arXiv:2605.08538v1 Announce Type: new Abstract: Current LLM agents lack principled mechanisms for managing persistent memory across long interaction horizons. We present a biologically-grounded memory

Human-LLM Dialogue Improves Diagnostic Accuracy in Emergency Care

arXiv:2605.08533v1 Announce Type: new Abstract: Clinical decision-making in emergency medicine demands rapid, accurate diagnoses under uncertainty. Despite benchmark progress, evidence for LLMs as int

Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation

arXiv:2501.12202v4 Announce Type: replace Abstract: We present Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets. This system includes two fo

HyperSpace: A Generalized Framework for Spatial Encoding in Hyperdimensional Representations

arXiv:2604.15113v2 Announce Type: replace Abstract: Vector Symbolic Architectures (VSAs) provide a well-defined algebraic framework for compositional representations in hyperdimensional spaces. We int

Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD Modulation

arXiv:2605.10009v1 Announce Type: new Abstract: Query-based image retrieval (QBIR) requires retrieving relevant images given diverse and often stylistically heterogeneous queries, such as sketches, ar

I love seeing a new eval with such low scores. When we announced GPT-5.5, almost every benchmark had a score above 50%. It's time to retire …

model-releasesgary-marcus--x

I love seeing a new eval with such low scores. When we announced GPT-5.5, almost every benchmark had a score above 50%. It's time to retire evals like GQPA and bring in a new set. The first ProgramBen