model releases

Unsupervised Partner Design Enables Robust Ad-hoc Teamwork

arXiv:2508.06336v2 Announce Type: replace-cross Abstract: We introduce Unsupervised Partner Design (UPD), a population-free multi-agent reinforcement learning method for robust ad-hoc teamwork. UPD ge

VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation

DGX agent

arXiv:2606.07992v1 Announce Type: new Abstract: As the Model Context Protocol (MCP) standardizes tool-calling for autonomous agents, it introduces a critical, unexamined attack surface: the error-hand

model-releasesarxiv-cs-ai

9 Jun 2026

Version of AI tool too powerful for public released to public https://bbc.in/4xfGSlq

model-releasesclem-delangue--x

A version of an AI tool deemed too powerful for public release was inadvertently made available to the public, according to a report from BBC News. The incident highlights concerns about controlling a

VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation

arXiv:2606.08091v1 Announce Type: new Abstract: Recent agent frameworks such as Claude Code, Codex, and OpenClaw are strong at tool use and orchestration, but whether they can handle long video genera

Visual Template Inference for Data Extraction from Documents

arXiv:2501.06659v2 Announce Type: replace-cross Abstract: Many templatized documents are programmatically generated from structured data following a visual template. Such documents include invoices, t

VisualFLIP: Do Predictions Depend on Task-Critical Visual Evidence in Multimodal Reasoning?

arXiv:2606.07872v1 Announce Type: new Abstract: When a multimodal large language model answers a visual reasoning question correctly, is the prediction actually supported by the task-critical visual e

VisualLeakBench: Reproducible Action-Boundary Propagation Failures in Vision-Language Agents

arXiv:2606.07595v1 Announce Type: cross Abstract: Vision-language agents increasingly consume screenshots, documents, and user interfaces before writing to memory, sending messages, or invoking extern

vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models

arXiv:2606.08094v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies are typically shipped as Python/PyTorch stacks that assume a workstation-class GPU, a mismatch for the hardware

VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation

model-releasesarxiv-cs-ro

arXiv:2606.07723v1 Announce Type: new Abstract: Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes while adaptively planning

We encourage developers to share their builds with us and give feedback to shape future iterations. Let’s shape the future of sovereign AI t…

We encourage developers to share their builds with us and give feedback to shape future iterations. Let’s shape the future of sovereign AI together. Download: https://huggingface.co/CohereLabs/North-M

model-releasescohere--x

We talk a lot about how important it is to set up self-verification loops. Especially in the age of powerful models that can run for long pe…

model-releasesboris-cherny--x

We talk a lot about how important it is to set up self-verification loops. Especially in the age of powerful models that can run for long periods of time, self-verification is a key ingredient that en

WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces

arXiv:2606.09426v1 Announce Type: new Abstract: Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and ext

We're getting Fable 5 before GTA 6

model-releasesjerry-liu--x

This post humorously suggests that Fable 5 will release before Grand Theft Auto 6, likely commenting on the extended development timelines of both highly anticipated games. The statement reflects comm

We're hosting Claude Fable 5 Build Day in San Francisco on June 13. Point Fable 5 at a problem worth solving and build a solution with Claud…

We're hosting Claude Fable 5 Build Day in San Francisco on June 13. Point Fable 5 at a problem worth solving and build a solution with Claude Code. The Anthropic team will be in the room, with a chanc

model-releasesthariq--x

We've got 13 days to burn as much tokens as humanly possible on Claude Max plans Before they revert to API based billing 💀

model-releasesjerry-liu--x

We've got 13 days to burn as much tokens as humanly possible on Claude Max plans Before they revert to API based billing 💀 Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for gen

What Codex unlocks for Notion

OpenAI's Codex model enables Notion to add AI-powered capabilities to its workspace platform, allowing users to automate tasks and generate content through natural language commands. This integration

model-releasesopenai

What it feels like to work with Mythos

model-releasesethan-mollick

This article by Ethan Mollick describes the user experience and practical workflow of working with Mythos, an AI system. It likely covers the system's capabilities, interface, strengths, limitations,

When Behavioral Safety Evaluation Fails: A Representation-Level Perspective

arXiv:2606.08044v1 Announce Type: cross Abstract: Large Language Model (LLM) safety has often been evaluated at the behavior level, which provides limited evidence of internal robustness, as these eva

When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents

arXiv:2602.08235v2 Announce Type: replace-cross Abstract: Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe unin

When Do Local Score Models Extrapolate Across Size? A Diagnostic Theory and Benchmark

arXiv:2606.09705v1 Announce Type: new Abstract: Scientific generative modeling often requires size transfer, where models trained on small systems are evaluated on larger ones. While translation-invar

Where Does the Answer Come From? Benchmarking View-Level Visual Evidence Identification in Multi-View MLLMs for Autonomous Driving

arXiv:2606.09644v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) achieve strong results on visual reasoning benchmarks, but answer accuracy alone does not indicate whether a

Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models

arXiv:2606.07808v1 Announce Type: new Abstract: Reasoning language models deployed in agentic workflows must follow an instruction hierarchy: when instructions from different sources conflict, the mod

Who Earns the Safety? Intervention-Aware Quantum Predictive Control with Safety Attribution

arXiv:2606.09778v1 Announce Type: cross Abstract: Hard safety filters are increasingly placed downstream of learned controllers to guarantee constraint satisfaction at run time. Yet a filtered control

Wordle 1,815 6/6 ⬛⬛🟨⬛⬛ ⬛🟨⬛⬛⬛ ⬛🟩⬛🟩⬛ 🟩🟩⬛🟩⬛ 🟩🟩🟩🟩⬛ 🟩🟩🟩🟩🟩

model-releasesanthropic--x

This post shows a completed Wordle game (#1,815) solved on the sixth and final attempt, with the emoji grid indicating which letters were correct, misplaced, or absent in each guess. Anthropic shared

XCR-Bench: Benchmarking Cross-Cultural Reasoning in LLMs via Culture-Specific Items and Hall's Triad

arXiv:2601.14063v2 Announce Type: replace-cross Abstract: Cross-cultural competence in large language models (LLMs) requires understanding and adapting Culture-Specific Items (CSIs) across varying cul

You can try Claude Fable 5 as part of Devin Cloud’s Ultra agent. Devin Ultra is our smartest and most capable agent, which excels at long-ho…

model-releasescognition-ai--x

You can try Claude Fable 5 as part of Devin Cloud’s Ultra agent. Devin Ultra is our smartest and most capable agent, which excels at long-horizon tasks and debugging. We tuned the harness so Ultra cos

Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models

arXiv:2606.09749v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these

Zero-Parameter Geometric Gating for Temporally Stable Low-Altitude UAV Video Semantic Segmentation

arXiv:2606.09162v1 Announce Type: new Abstract: Video semantic segmentation for low-altitude UAVs requires temporal consistency, yet dense optical flow introduces spatially structured noise in the pla

Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline

arXiv:2606.07965v1 Announce Type: new Abstract: Large Visual Language Models (LVLMs) have achieved remarkable success in vision tasks. However, the significant differences between industrial and natur

Zero-Shot Semantic Re-Identification for Autonomous Driving: A VLM Baseline Study

arXiv:2606.09362v1 Announce Type: new Abstract: Re-Identification (ReID) in autonomous driving is typically formulated as a visual matching problem, where observations of vehicles, pedestrians, and cy

ZIPP:Zero-shot Image Personalization from Personas

arXiv:2606.08841v1 Announce Type: new Abstract: Text-to-image diffusion models are increasingly deployed in open-ended creative contexts, yet their outputs remain impersonal, optimized for aggregate a

Zscaler launches AI Broker and Endpoint AI Security for agents

model-releasessiliconangle

Zscaler Inc. today unveiled a set of products designed to secure autonomous artificial intelligence agents, with the cybersecurity company claiming it has built the industry’s first complete zero-trus

3DMorph: Single-Image-Guided Local 3D Shape Editing and Morphing

arXiv:2606.07115v1 Announce Type: new Abstract: Despite recent progress in 3D generation, intuitive editing of existing shapes remains limited. Unlike images, which benefit from well-established inpai

A Comprehensive Anatomy of Human and DeepSeek-R1 LLM Mathematical Reasoning

arXiv:2606.07410v1 Announce Type: cross Abstract: The emergence of 'Aha moments' in large language models, particularly DeepSeek-R1-0120, has raised the question of whether these systems genuinely rea

A Cross-view Fusion Framework for Robust 6-DoF Grasp Pose Estimation

arXiv:2606.06878v1 Announce Type: cross Abstract: In this paper, we propose a cross-view fusion framework that enhances the robustness of 6-DoF grasp pose estimation in corner views. Our framework all

A Four-Condition Diagnostic Protocol for Evidence Utilization in Long-Context and Retrieval-Augmented Language Models

model-releasesarxiv-cs-cl

arXiv:2606.06758v1 Announce Type: new Abstract: Final-answer accuracy, retrieval recall, and citation overlap do not by themselves identify whether a long-context or retrieval-augmented language model

A French engineer who lives quietly in Paris has spent 30 years writing software that the entire internet now runs on without knowing his na…

model-releasesfrancois-chollet--x

A French engineer who lives quietly in Paris has spent 30 years writing software that the entire internet now runs on without knowing his name. He wrote the code that streams every YouTube video, ever

A Geometric Gaussian Mixture Representation of Plane Curves

arXiv:2606.06505v1 Announce Type: cross Abstract: We introduce a user defined probabilistic polygonal representation for plane curves. Given a curve, we select vertices on the curve and connect consec

A Held-Out Transition-Pair Falsifier for Long-Horizon Non-Abelian State Tracking

arXiv:2606.07254v1 Announce Type: new Abstract: State tracking exposes a sharp limitation of sequence models: the relevant signal is often not a summary of observed tokens, but an ordered latent state

Accelerating Multi-Objective Bayesian Optimisation via Predictive-Gradient Catalysts

arXiv:2606.06984v1 Announce Type: new Abstract: This paper presents a general acceleration mechanism for multi-objective Bayesian optimisation (MOBO) that leverages Gaussian process predictive gradien

Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle

arXiv:2606.07462v1 Announce Type: new Abstract: As foundation models advance and agent scaffolding becomes increasingly sophisticated, agents have demonstrated remarkable proficiency in complex, long-

ActiveGrasp: Information-Guided Active Grasping with Calibrated Energy-based Model

model-releasesarxiv-cs-ro

arXiv:2511.12795v2 Announce Type: replace Abstract: Grasping in a densely cluttered environment is a challenging task for robots. Previous methods tried to solve this problem by actively gathering mul

ADAGE: Active Defenses Against GNN Extraction

arXiv:2503.00065v4 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) achieve high performance in various real-world applications, such as drug discovery, traffic states prediction, a

Adaptive Conditional Forest Sampling for Spectral Risk Optimisation under Decision-Dependent Uncertainty

arXiv:2603.12507v2 Announce Type: replace Abstract: Minimising a spectral risk objective, defined as a weighted combination of expected cost and Conditional Value-at-Risk (CVaR), is challenging when t

Added a new built in skill inspired by Claude Codes' simplify command, will automatically simplify your code with /simplify-code! A hermes u…

model-releasesnous-research--x

Nous Research has added a new built-in skill that automatically simplifies code using the `/simplify-code` command, inspired by Claude's code simplification capabilities. This feature is integrated in

An Analysis Focused on Womens Safety: Can VAD Models Be Enhanced by a Multi-modal Dataset?

arXiv:2605.25806v2 Announce Type: replace Abstract: Women's safety and security are paramount for a modern society. Crimes against women occur in daylight as well as in low-light conditions. Often, su

An Integrated Roadside Sensing and Communication Framework for Vulnerable Road User Safety at Signalized Intersections

arXiv:2606.07016v1 Announce Type: cross Abstract: Vulnerable road users (VRUs) account for approximately half of urban traffic deaths globally, with intersections concentrating a disproportionate shar

Apple announces major performance improvements across its platforms, including up to 30% faster app launches and up to 80% faster AirDrop transfers (Ryan Christoffel/9to5Mac)

Ryan Christoffel / 9to5Mac: Apple announces major performance improvements across its platforms, including up to 30% faster app launches and up to 80% faster AirDrop transfers — Today during its WWDC

model-releasestechmeme