model releases

GeoRouteNet: Geometry-Enhanced Non-Autoregressive Neural Solver for the Traveling Salesman Problem

arXiv:2606.22776v1 Announce Type: new Abstract: The traveling salesman problem (TSP) is a canonical NP-hard combinatorial optimization benchmark that tests the representational capacity and generaliza

Model Releases

GeoTransolver: Learning Physics on Irregular Domains Using Multi-scale Geometry Aware Physics Attention Transformer

DGX agent

arXiv:2512.20399v3 Announce Type: replace Abstract: We present GeoTransolver, a multiscale geometry-aware physics attention transformer for Computer Aided Engineering (CAE). GeoTransolver extends the

model-releasesarxiv-cs-lg

23 Jun 2026

GitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and Merge

arXiv:2606.14470v2 Announce Type: replace-cross Abstract: Large language model reasoning leaves no trace once it is done. The steps of a chain of thought disappear when the context window closes, a pr

Gold Points Sniper: Self-guided Visual Reasoning in VLM for Fine-grained Action Understanding

arXiv:2606.22409v1 Announce Type: new Abstract: Robots operating in everyday environments must understand fine-grained human actions, intentions, and contextual cues from broad views where people occu

Good-Enough LLM Obfuscation (GELO)

arXiv:2603.05035v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly served on shared accelerators where an adversary with read access to device memory can observe K

Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit Solutions

arXiv:2602.04548v2 Announce Type: replace Abstract: We develop a general mathematical framework to analyze scaling regimes and derive explicit analytic solutions for gradient flow (GF) in large learni

GRAG: Generic Response-Augmented Generation Framework for Personalized Conversational Systems

arXiv:2606.21097v1 Announce Type: cross Abstract: Deploying highly capable personalized conversational agents in resource-constrained or privacy-sensitive environments remains a significant challenge.

GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling

arXiv:2606.20799v1 Announce Type: new Abstract: Generating visually consistent multi-shot videos remains an open challenge. As videos span more shots, inconsistencies can accumulate across shots, caus

Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention

arXiv:2606.20945v1 Announce Type: new Abstract: Self-attention is central to Transformer performance and is often the most expensive part of the Transformer at long context lengths because its pairwis

H-RINS: Hierarchical Tightly-coupled Radar-Inertial State Estimation via Smoothing and Mapping

model-releasesarxiv-cs-ro

arXiv:2603.14109v2 Announce Type: replace Abstract: Millimeter-wave radar enables robust perception in visually degraded environments, yet radar-inertial estimation remains prone to drift: sparse body

HaineiFRDM: Structure-Preserving Diffusion for Film Restoration under Fast Motion and Diverse Defects

arXiv:2512.24946v2 Announce Type: replace Abstract: Existing film-restoration methods frequently fail under fast motion, producing limb disappearance and structural distortion due to inaccurate motion

HalluHard update: We’ve added GLM-5.2, using adaptive thinking with maximum reasoning effort, to our leaderboard. Despite its impressive per…

model-releasesgary-marcus--x

HalluHard update: We’ve added GLM-5.2, using adaptive thinking with maximum reasoning effort, to our leaderboard. Despite its impressive performance on other benchmarks, GLM-5.2 still hallucinates fre

Hedgementation = Hedgerow Segmentation: A Remote Sensing Benchmark

arXiv:2606.23615v1 Announce Type: new Abstract: We propose Hedgementation: a new benchmark to evaluate machine learning models for hedgerow mapping from remote sensing data at country scale and 10m^2

HEM: a margin-based loss for visual categorisation tasks

arXiv:2501.12191v2 Announce Type: replace-cross Abstract: Training deep neural networks (DNNs) on classification tasks can be performed with a number of different losses, but cross-entropy (CE) loss i

HERCULES: An Open-Source Simulation Framework for Heterogeneous Multi-Robot SLAM, Collaborative Perception, and Exploration

arXiv:2606.22756v1 Announce Type: cross Abstract: We present HERCULES, an open-source simulator and data-collection pipeline for heterogeneous multi-robot autonomy. Built upon the Unreal Engine 5 (UE5

Here's Sonnet 3.7 doing the same thing a year ago. https://x.com/emollick/status/1894441728175677837?s=20

model-releasesethan-mollick--x

Here's Sonnet 3.7 doing the same thing a year ago. https://x.com/emollick/status/1894441728175677837?s=20 Snake games are a bad test of AI beca- 'Claude 3.7, make a snake game, but the snake is self-a

Hierarchical Adversarial Bandits for Online Configuration Optimization

arXiv:2505.19061v2 Announce Type: replace Abstract: Motivated by Online Configuration Optimization in large, dynamic parameter spaces, this work studies the nonstochastic multi-armed bandit (MAB) prob

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition

arXiv:2601.12879v2 Announce Type: replace Abstract: Extracting sparse circuits from billion-parameter transformers is constrained by O(2^n) search cost and pervasive feature reuse across co-active pat

HiMatch-AD: DINOv3-driven Hierarchical Matching for Training-free Medical Anomaly Detection

arXiv:2606.22556v1 Announce Type: new Abstract: Anomaly detection is essential for medical image analysis, where pathological regions often appear as rare deviations from normal anatomical structures.

Holo-World: Unified Camera, Object and Weather Control for Video World Model

arXiv:2606.20083v2 Announce Type: replace Abstract: Video world models are moving toward preserving an observed world under controllable camera and object motion while allowing its environmental state

How GPT-5 helped immunologist Derya Unutmaz solve a 3-year-old mystery

Immunologist Derya Unutmaz leveraged GPT-5 to resolve a complex scientific mystery that had remained unsolved for three years, demonstrating the AI model's capacity to assist in advanced biomedical re

model-releasesopenai

How Omio is building the future of conversational travel

Omio, a travel platform, is leveraging OpenAI's technology to enhance its services through conversational AI capabilities. This implementation likely enables customers to search for and book travel op

model-releasesopenai

How Should a Robot Configure Its Laser Scanner for Inspection?

arXiv:2606.21093v1 Announce Type: cross Abstract: Robotic inspection relies on accurate sensing to acquire high-fidelity geometric measurements for defect detection and metrology. While prior work has

How Should a Simulation-to-Reality Transfer Budget Be Spent?

arXiv:2606.22062v1 Announce Type: cross Abstract: Simulation-to-reality transfer, often called sim-to-real transfer, is a central challenge in robot learning. Yet, the tradeoff between measuring a sys

How Well Do Self-Supervised Speech Models Encode Age and Gender in Children's Speech? A Layer-Wise Analysis Across Multiple Architectures

arXiv:2606.22177v1 Announce Type: cross Abstract: Self-supervised learning (SSL) models have become a central component of modern speech processing systems, as they enable the learning of rich acousti

HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks

arXiv:2603.19822v2 Announce Type: replace Abstract: Existing UAV vision-language navigation (VLN) benchmarks have enabled language-guided flight, but they largely focus on long, step-wise route descri

Hybrid Compression: Integrating Pruning and Quantization for Optimized Neural Networks

arXiv:2606.22935v1 Announce Type: new Abstract: Deep neural networks have witnessed remarkable advancements in recent years and have become integral to various applications. However, alongside these d

HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models

arXiv:2606.23406v1 Announce Type: new Abstract: We present HyperQuant (Hadamard, optimallY Packing, Entropy Rice-coding), a unified post-training quantization pipeline for the weights and the KV cache

I also have Claude monitoring Slack channels to proactively respond to people to answer their questions and draft PRs, and to react with spe…

model-releasesboris-cherny--x

I also have Claude monitoring Slack channels to proactively respond to people to answer their questions and draft PRs, and to react with specific emojis like ✅❌ when a thread is resolved. To set it up

I guarantee you are sleeping on small models. Deepseek V4 Flash can do ~80% of the tasks you ask Claude or Codex for. It is 137x cheaper per…

model-releasesclem-delangue--x

DeepSeek V4 Flash is a small language model capable of handling approximately 80% of common tasks performed by larger models like Claude or Codex, while offering significantly lower costs (137x cheape

I tag Claude many times a day to write PRs, address user feedback, investigate incidents, do data analyses, summarize information, etc. Use …

model-releasesboris-cherny--x

I tag Claude many times a day to write PRs, address user feedback, investigate incidents, do data analyses, summarize information, etc. Use it as your company's search engine. 'What's the status on X?

IMAGIN-4D: Image-Guided Controllable Interaction Generation

arXiv:2606.23675v1 Announce Type: new Abstract: Generating human-object interactions (HOI) is central to character animation, robotics, AR/VR, and embodied AI. Recent HOI generation methods synthesize

Improving Text-to-Music Generation with Human Preference Rewards

arXiv:2606.21670v1 Announce Type: cross Abstract: We describe our entry to the efficiency track of the Academic Text-to-Music (ATTM) Grand Challenge at ICME 2026. Beyond the challenge protocol's FAD-C

In-Context Molecular Property Prediction with LLMs: A Blinding Study on Memorization and Knowledge Conflicts

arXiv:2603.25857v2 Announce Type: replace Abstract: The capabilities of large language models (LLMs) have expanded beyond natural language processing to scientific prediction tasks, including molecula

In LLM Reasoning, there is Irrationality on top of Value Misalignment

arXiv:2606.20624v1 Announce Type: cross Abstract: Significant progress has been made in aligning LLMs with target value functions. We argue that, even when an LLM has been well aligned in (post-)train

IndicGuard: A Multilingual Safety Guard Model and Dataset for Indic Languages

arXiv:2606.22841v1 Announce Type: cross Abstract: As Large Language Models (LLMs) achieve widespread integration across diverse linguistic landscapes, ensuring their safety and alignment with regional

Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving

arXiv:2606.22913v1 Announce Type: new Abstract: Recent Vision-Language-Action (VLA) models have advanced end-to-end autonomous driving by incorporating reasoning for better interpretability and planni

Introducing Claude code for 3D modeling You can now create a production-level 3D models from any agent you are using. Ready to plug into you…

model-releasesyohei-nakajima--x

Introducing Claude code for 3D modeling You can now create a production-level 3D models from any agent you are using. Ready to plug into your own apps or games Made possible by @trysuzanne and @monid_

Introducing Claude Tag, a new way for teams to work with Claude. In Slack, Claude joins as a team member with access to the channels and too…

model-releasesyohei-nakajima--x

Introducing Claude Tag, a new way for teams to work with Claude. In Slack, Claude joins as a team member with access to the channels and tools you choose. Tag Claude in and delegate tasks to it while

Introducing Mistral OCR 4. It creates structure with bounding boxes, block classification, and inline confidence scores in 170 languages. 🧵…

model-releasesarthur-mensch--x

Mistral OCR 4 is an optical character recognition model that extracts text with structural information including bounding boxes and block classification across 170 languages. The system provides inlin

Inverse Problem for Partial Differential Equations with Jump Discontinuities in Coefficients by Two-stage Physics-Informed Deep Learning and Statistical Mixture Models

arXiv:2510.14656v2 Announce Type: replace-cross Abstract: This work proposes a two-stage physics-informed deep learning framework that combines neural-network-based sampling with statistical inference

IOI: Decoupling Kinematics and Physics for Interactive World Models

model-releasesarxiv-cs-ro

arXiv:2606.23296v1 Announce Type: new Abstract: Developing generalist embodied agents requires interactive environments providing visually realistic feedback and accurate action-conditioned dynamics.

Is Our Benchmark Enough? An Analysis of Continual Learning for MLLMs

arXiv:2606.20961v1 Announce Type: new Abstract: Continual adaptation is essential for multimodal large language models (MLLMs) deployed across evolving domains, but the state-of-the-art MR-LoRA method

It's Much Easier for Neural Networks to learn Game of Life Dynamics with the Right Activation Function: Polynomial Kolmogorov-Arnold Networks

arXiv:2606.23587v1 Announce Type: new Abstract: Previous work has found a gap between the scale of neural networks that reliably learn Conway's Game of Life, and minimal networks capable of representi

Jury Duty: Calibration and Orientation Failures in MLLM-as-a-Judge Under Cultural Ambiguity

arXiv:2606.20676v1 Announce Type: new Abstract: MLLM-as-a-Judge is conventionally validated by agreement with human annotations, but this metric is undefined when the human pool is culturally heteroge

Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse

arXiv:2606.23581v1 Announce Type: cross Abstract: Multimodal agents repeatedly re-examine the same video frames, UI screenshots, and rendered artifacts as their context window slides and reasoning ite

L20-Edu-135M: An Auditable Single-GPU Study of Data-Efficient Small Language Modeling

arXiv:2606.22189v1 Announce Type: new Abstract: Small language models are cheap to serve and feasible on local hardware, but strong public 135M-class systems are commonly trained with hundreds of bill

Large Language Model-Assisted Cleaning of Report-Derived Labels in a Large-Scale Chest CT Dataset

arXiv:2606.22382v1 Announce Type: cross Abstract: Purpose: To evaluate whether large language model (LLM)-assisted label cleaning can identify label-report discordance in CT-RATE, a large-scale public