model releases

Adaptive Camera Sensor for Vision Models

arXiv:2503.02170v2 Announce Type: replace-cross Abstract: Domain shift remains a persistent challenge in deep-learning-based computer vision, often requiring extensive model modifications or large lab

Adaptive Fused Prior Transfer for Controllable Generative Image Compression

DGX agent

arXiv:2605.16817v1 Announce Type: cross Abstract: Learned image compression has achieved competitive rate-distortion performance, but very-low-bitrate reconstruction remains difficult because the tran

model-releasesarxiv-cs-cv

19 May 2026

ADR: An Agentic Detection System for Enterprise Agentic AI Security

arXiv:2605.17380v1 Announce Type: new Abstract: We present the Agentic AI Detection and Response (ADR) system, the first large-scale, production-proven enterprise framework for securing AI agents oper

Advancing content provenance for a safer, more transparent AI ecosystem

OpenAI discusses methods for establishing content provenance—tracking the origin and history of digital content—to improve transparency and safety in AI systems. The work addresses how verifiable cont

model-releasesopenai

Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory

arXiv:2605.18733v1 Announce Type: new Abstract: Autoregressive video generation has improved rapidly in visual fidelity and interactivity, but it still suffers from long-term inconsistency and memory

Adversarial Agent Collaboration for Correctness Improvements of C to Safe Rust Translation

arXiv:2510.03879v3 Announce Type: replace-cross Abstract: Translating C to memory-safe languages, like Rust, prevents critical memory safety vulnerabilities that are prevalent in legacy C software. Ev

Agentic AI Governance and Lifecycle Management in Healthcare

arXiv:2601.15630v2 Announce Type: replace Abstract: Healthcare organizations are beginning to embed agentic AI into routine workflows, including clinical documentation support and early-warning monito

Agentic Chunking and Bayesian De-chunking of AI Generated Fuzzy Cognitive Maps: A Model of the Thucydides Trap

arXiv:2605.17903v1 Announce Type: new Abstract: We automatically generate feedback causal fuzzy cognitive maps (FCMs) from text by teaching large-language-model agents to break the text into overlappi

AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents

arXiv:2605.16819v1 Announce Type: cross Abstract: GPU kernel optimization is increasingly critical for efficient deep learning systems, but writing high-performance kernels still requires substantial

AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech

arXiv:2605.17583v1 Announce Type: new Abstract: While existing text-to-speech (TTS) models exhibit high expressiveness, fine-grained control over composite instructions remains challenging due to the

AgentWall: A Runtime Safety Layer for Local AI Agents

arXiv:2605.16265v1 Announce Type: new Abstract: The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active ac

AgroCoT: A Chain-of-Thought Benchmark for Evaluating Reasoning in Vision-Language Models for Agriculture

arXiv:2511.23253v3 Announce Type: replace Abstract: Recent advancements in Vision-Language Models (VLMs) have significantly impacted various industries. In agriculture, these multimodal capabilities h

AI for Auto-Research: Roadmap & User Guide

arXiv:2605.18661v1 Announce Type: new Abstract: AI-assisted research is crossing a threshold: fully automated systems can now generate research papers for as little as $15, while long-horizon agents c

AI4BayesCode: From Natural Language Descriptions to Validated Modular Stateful Bayesian Samplers

arXiv:2605.18476v1 Announce Type: cross Abstract: Coding and computation remain major bottlenecks in Markov chain Monte Carlo (MCMC) workflows, especially as modern sampling algorithms have become inc

Algebraic Priors for Approximately Equivariant Networks

arXiv:2506.08244v2 Announce Type: replace-cross Abstract: Equivariant neural networks incorporate symmetries through group actions, embedding them as an inductive bias to improve performance. Existing

Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)

arXiv:2605.18629v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into high

Alignment Dynamics in LLM Fine-Tuning

arXiv:2605.18309v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and reinforcement learning from human feedback, the alig

Also had some early access to Gemini 3.5 Flash. Very fast for a flash model and very capable, though not as powerful as a full frontier mode…

model-releasesethan-mollick--x

Also had some early access to Gemini 3.5 Flash. Very fast for a flash model and very capable, though not as powerful as a full frontier model. I added it to the gallery or procedurally generated one-s

AMO: Adaptive Muon Orthogonalization

arXiv:2605.17806v1 Announce Type: new Abstract: Muon has recently emerged as a competitive alternative to AdamW for large-scale pre-training, with orthogonalization via Newton-Schulz (NS) iterations a

Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models

arXiv:2602.07715v2 Announce Type: replace Abstract: Recovering a signal from its degraded measurements is a long standing challenge in science and engineering. Recently, zero-shot diffusion based meth

Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models

model-releasesarxiv-cs-cl

arXiv:2605.18504v1 Announce Type: new Abstract: Machine Translation (MT) for Ancient Greek (AG) to Modern Greek (MG) is a low-resource task, constrained by the lack of large-scale, high-quality parall

Announcing Claude Managed Agents on Cloudflare

model-releasescloudflare-ai

Cloudflare has integrated with Anthropic's Claude Managed Agents to provide a fast, isolated execution environment for autonomous code delivery. This means builders can scale agent workflows globally

Anthropic Claude is now a partner node in ComfyUI Drop Claude into any workflow to: → rewrite weak prompts into great ones → describe and cr…

Anthropic Claude is now a partner node in ComfyUI Drop Claude into any workflow to: → rewrite weak prompts into great ones → describe and critique images intelligently → feed structured text into down

model-releasescomfyui--x

ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery

arXiv:2605.16902v1 Announce Type: new Abstract: Scientific artifacts such as models and datasets are foundations for research. With the rapid growth of platforms like HuggingFace, researchers now have

Artificial Adaptive Intelligence: The Missing Stage Between Narrow and General Intelligence

arXiv:2605.16844v1 Announce Type: new Abstract: Between the narrow systems we deploy and the general intelligence we speculate about lies an entire regime of machine behavior that has never received i

ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics

arXiv:2605.16582v1 Announce Type: new Abstract: We present ArtMesh, a mesh-native method for reconstructing articulated objects explicitly as connected triangle meshes with per-part rigid motion from

AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization

arXiv:2603.23566v2 Announce Type: replace-cross Abstract: Optimizing AscendC (Ascend C) operators for Ascend NPUs is difficult for two reasons. First, unlike CUDA, the ecosystem offers few public kern

Asking Back: Interaction-Layer Antidistillation Watermarks

arXiv:2605.16462v1 Announce Type: cross Abstract: Detecting unauthorized knowledge distillation from a deployed LLM API is hard because the defender controls neither the attacker's training pipeline n

ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents

arXiv:2605.17324v1 Announce Type: cross Abstract: Clarification-seeking behavior is widely regarded as a desirable property of LLM agents, enabling them to resolve ambiguity before acting on underspec

Attention-Guided Fusion of 1D and 2D CNNs for Robust ECG-Based Biometric Recognition

arXiv:2605.17685v1 Announce Type: cross Abstract: Electrocardiogram (ECG)-based biometric recognition has emerged as a promising solution for secure authentication and liveness detection. However, mos

Auditing Multimodal LLM Raters: Central Tendency Bias in Clinical Ordinal Scoring

arXiv:2605.16386v1 Announce Type: new Abstract: Multimodal large language models (LLMs) are increasingly explored as automated evaluators in clinical settings, yet their scoring behavior on ordinal cl

AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing

arXiv:2603.23069v2 Announce Type: replace-cross Abstract: The task of authorship style transfer involves rewriting text in the style of a target author while preserving the meaning of the original tex

Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reports

arXiv:2605.17561v1 Announce Type: cross Abstract: Issues faced when using software are reported in the form of bug reports. However, many bug reports are invalid, meaning they do not require code chan

Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling

arXiv:2605.17971v1 Announce Type: cross Abstract: Despite rigorous safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuri

BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting

arXiv:2605.17937v1 Announce Type: cross Abstract: Quantitative backtesting is essential for evaluating trading strategies but remains hampered by high technical barriers and limited scalability. While

Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity

arXiv:2510.00304v3 Announce Type: replace-cross Abstract: Deep learning models excel in stationary data but struggle in non-stationary environments due to a phenomenon known as loss of plasticity (LoP

Bayesian-Monte Carlo Schedule Updating for Construction Digital Twins: A Probabilistic Framework for Dynamic Project Forecasting

arXiv:2605.17608v1 Announce Type: cross Abstract: Construction projects frequently experience schedule delays and forecasting uncertainty due to variability in labor productivity, material availabilit

Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models

arXiv:2510.16727v2 Announce Type: replace-cross Abstract: Large language models internalize a structural trade-off between truthfulness and obsequious flattery, emerging from reward optimization that

Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbations

model-releasesarxiv-cs-ro

arXiv:2605.18059v1 Announce Type: new Abstract: Robustness is a critical requirement for deploying autonomous driving systems in the real world. Existing robustness benchmarks for autonomous driving h

Benchmarking inference at scale: coding agents

model-releasestogether-ai-blog

This article presents benchmarking results for AI coding agents evaluated at scale, likely comparing performance metrics such as code generation accuracy, execution success rates, and inference effici

Benchmarking Mythos-Linked Bug Rediscovery

arXiv:2605.17416v1 Announce Type: cross Abstract: Anthropic's April 2026 Mythos materials combine benchmark claims with concrete bug-finding stories across OpenBSD, FreeBSD, Linux, FFmpeg, and browser

Benchmarking Recurrent Event-Based Object Detection for Industrial Multi-Class Recognition on MTevent

arXiv:2603.21787v2 Announce Type: replace Abstract: Event cameras are attractive for industrial robotics because they provide high temporal resolution, high dynamic range, and reduced motion blur. How

BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation

arXiv:2605.17508v1 Announce Type: cross Abstract: Split Federated Learning (SFL) enables privacy-preserving collaborative training by partitioning models between clients and a server. However, under n

Beyond Accuracy: Decomposing the Reasoning Efficiency of LLMs

arXiv:2602.09805v2 Announce Type: replace-cross Abstract: As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no lon

Beyond Detection: A Structure-Aware Framework for Scene Text Tracking

arXiv:2605.17270v1 Announce Type: new Abstract: Modern visual object trackers show impressive results on general targets, yet their performance drops substantially when dealing with scene text. Althou

Beyond Geometry: Efficient Topologically-Grounded Navigation in Complex 3D Environments

model-releasesarxiv-cs-ro

arXiv:2605.17302v1 Announce Type: new Abstract: Ground robot navigation in complex 3D environments is often hindered by geometric ambiguity, where non-traversable structures such as furniture share lo

Beyond Neural Incompatibility: Cross-Scale Knowledge Transfer in Language Models through Latent Semantic Alignment

model-releasesarxiv-cs-cl

arXiv:2510.24208v2 Announce Type: replace Abstract: Language Models (LMs) encode substantial knowledge in their parameters, yet it remains unclear how to transfer such knowledge in a fine-grained mann

Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers

arXiv:2605.16949v1 Announce Type: new Abstract: Recent advances in Diffusion Transformers (DiTs) demonstrate that aligning noisy latent states with well-trained semantic features-as pioneered by Repre