model releases

OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification

arXiv:2606.01476v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher, mitig

Model Releases

On the Evaluation of Spiking Neural Network Configurations for Network Intrusion Detection

DGX agent

arXiv:2606.01442v1 Announce Type: cross Abstract: Network intrusion detection is a core component of modern cybersecurity infrastructure, yet the deep learning models that dominate the field are compu

model-releasesarxiv-cs-ai

2 Jun 2026

On the Generalization Gap in Self-Evolving Language Model Reasoning

arXiv:2606.01075v1 Announce Type: new Abstract: Recent work suggests that large language models (LLMs) can improve through self-evolution (SE), using supervision signals generated by the model itself.

On the Generalization in Topology Optimization via Sensitivity-Conditioned Bernoulli Flow Matching

arXiv:2606.02179v1 Announce Type: cross Abstract: Surrogate models for topology optimization (TO) exhibit highly variable out-of-distribution (OOD) generalization under distribution shifts such as cha

On the Limits of Token Reduction for Efficient Unified Vision Language Training

arXiv:2606.01503v1 Announce Type: cross Abstract: Unified vision-language models (VLMs) integrate visual understanding and visual generation within a single autoregressive backbone, but their joint tr

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

arXiv:2606.02437v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) is usually treated as a cheaper alternative to full fine-tuning. We study a broader role: small trainable adapt

On the Theoretical Limitations of Embedding-based Link Prediction

arXiv:2506.22271v3 Announce Type: replace Abstract: Neural networks often map low-dimensional embeddings to high-dimensional output spaces. Usually, the output layer is linear, which can create a 'ran

On Wednesdays, We Ask Questions: Optimizing 'Active Listening' in Automated Legal Triage and Referral

arXiv:2606.00272v1 Announce Type: new Abstract: The FETCH classifier generates follow-up questions to help refine the best match for the applicant's legal problem, using a low-cost ensemble of LLMs. I

OncoReason: Structuring Clinical Reasoning in LLMs for Robust and Interpretable Survival Prediction

arXiv:2510.17532v2 Announce Type: replace Abstract: Predicting cancer treatment outcomes requires models that are both accurate and interpretable, particularly in the presence of heterogeneous clinica

OneVLA: A Unified Framework for Embodied Tasks

model-releasesarxiv-cs-ro

arXiv:2606.01241v1 Announce Type: new Abstract: Navigation and manipulation are fundamental capabilities of embodied intelligence, enabling robots to interpret natural language commands and interact p

Ontology-Guided Reasoning for Affordance-Based Explanations of Robot Navigation

model-releasesarxiv-cs-ro

arXiv:2606.00117v1 Announce Type: new Abstract: This paper proposes ontology-guided reasoning for affordance-based explanations of robot navigation. In human environments, it is not sufficient for a r

OpenAI extends Codex with productivity tools for nontechnical users

model-releasessiliconangle

OpenAI Group PBC today released a set of features that will make it easier for nontechnical people to use its Codex automation tool. The update comes five months after Anthropic PBC added similar capa

OpenAI releases a new report on knowledge work: Codex now has 5M+ weekly active users, up 6x+ since February, and knowledge workers are ~20% of Codex users (OpenAI)

OpenAI: OpenAI releases a new report on knowledge work: Codex now has 5M+ weekly active users, up 6x+ since February, and knowledge workers are ~20% of Codex users — OpenAI today released a new report

model-releasestechmeme

OpenDPR: Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for Remote Sensing Imagery

arXiv:2603.27645v2 Announce Type: replace Abstract: Open-vocabulary change detection (OVCD) seeks to recognize arbitrary changes of interest by enabling generalization beyond a fixed set of predefined

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

arXiv:2606.02031v1 Announce Type: cross Abstract: Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despit

Optimal Regularization for Performative Learning

arXiv:2510.12249v2 Announce Type: replace Abstract: In performative learning, the data distribution reacts to the deployed model - for example, because strategic users adapt their features to game it

Order within Chaos: Capturing Intrinsic Energy Anomalies for AI-Manipulated Image Forgery Localization

arXiv:2606.02178v1 Announce Type: cross Abstract: Recent advancements in generative AI have led to image editing models capable of producing realistic forgeries that evade traditional image forgery lo

PaintBench: Deterministic Evaluation of Precise Visual Editing

arXiv:2606.00188v1 Announce Type: cross Abstract: While current multimodal models are proficient at open-ended visual editing, executing precise single-answer edits remains an important obstacle. To p

PaperVoyager : Building Interactive Web with Visual Language Models

arXiv:2603.22999v3 Announce Type: replace Abstract: Recent advances in visual language models have enabled autonomous agents for complex reasoning, tool use, and document understanding. However, exist

Parameter Alignment Mitigates Catastrophic Forgetting in Multilingual Expert Language Models

arXiv:2606.00284v1 Announce Type: new Abstract: While continual pretraining~(CPT) is a practical way to extend large language models to new languages, naive finetuning on targeted data erodes existing

Parameter-efficient Dual-encoder Architecture with Differentiable Choquet Integral Fusion for Underwater Acoustic Classification

arXiv:2606.02341v1 Announce Type: cross Abstract: Underwater acoustic classification has a wide array of oceanic applications, but faces challenges due to an increasingly complex acoustic environment.

Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks

arXiv:2606.01947v1 Announce Type: cross Abstract: Research and applications in artificial intelligence have recently shifted with the rise of large pretrained models, which deliver state-of-the-art re

Parameter-Free and Group Conditional Online Conformal Prediction

arXiv:2606.00419v1 Announce Type: cross Abstract: Uncertainty quantification (UQ) is critical for the deployment of machine learning predictors in real-world scenarios where the data distribution may

PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning

arXiv:2606.02443v1 Announce Type: cross Abstract: Between the first visible sign of danger and the moment an accident occurs, there is often a window where intervention remains possible. Video-capable

Pasted File Editor

model-releasessimon-willison

Tool: Pasted File Editor I really like how you can paste a large volume of text into claude.ai (or the Claude desktop/mobile apps) and it will detect it as a large paste and turn it into a file attach

Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion

arXiv:2606.00616v1 Announce Type: cross Abstract: Recent Vision-Language Models (VLMs) struggle with grounded reasoning, temporal consistency, and context aware planning in videos. We introduce pause-

People who say this kind of thing are completely lost about what I actually said about deep learning, and I would strongly encourage them to…

model-releasesgary-marcus--x

People who say this kind of thing are completely lost about what I actually said about deep learning, and I would strongly encourage them to read “Deep learning is hitting a wall” (2022). What I said

Perception First: A Frontier Native-Video Model with Self-Consistency for Implicit Video Question Answering

arXiv:2606.01485v1 Announce Type: new Abstract: We describe our submission to the VRR Challenge @ CVPR 2026, built on the ImplicitQA / VRR-QA benchmark~ite{implicitqa}: multiple-choice video question

Permissive Safety Through Trusted Inference: Verifiable Belief-Space Neural Safety Filters for Assured Interactive Robotics

arXiv:2606.02562v1 Announce Type: cross Abstract: Autonomous robots that interact with people must make safe and efficient decisions under human-induced uncertainty, such as their preferences, goals,

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models

arXiv:2606.00150v1 Announce Type: cross Abstract: As Large Language Models evolve for user convenience, vulnerability to jailbreak attacks continues to be reported despite ongoing efforts in safety tr

Personalized 3D Myocardial Infarct Geometry Reconstruction from Cine MRI for Cardiac Digital Twins

arXiv:2606.01808v1 Announce Type: new Abstract: Accurate 3D geometric characterization of myocardial infarction (MI) is essential for building cardiac digital twins (CDTs) to precisely simulate infarc

Perturbative methods for non-parametric instrumental variable

arXiv:2606.00322v1 Announce Type: new Abstract: We introduce a perturbative approach for nonparametric instrumental variable (NPIV) estimation. By drawing inspiration from perturbation theory in physi

PFT: Phonon Fine-tuning for Machine Learned Interatomic Potentials

arXiv:2601.07742v4 Announce Type: replace-cross Abstract: Many materials properties depend on higher-order derivatives of the potential energy surface, yet machine learned interatomic potentials (MLIP

Physics-Encoded Inverse Modeling for Arctic Snow Depth Prediction

arXiv:2601.17074v4 Announce Type: replace-cross Abstract: Accurate estimation in time-varying inverse problems under limited and sparse observations remains a fundamental challenge across scientific d

Physics from Video: Identifiability of Time-Invariant Second-Order ODEs under Minimal Trajectory Conditions

arXiv:2606.00115v1 Announce Type: new Abstract: Bridging the gap between visual realism and physical understanding is a core challenge for video-based world models. We study the structural identifiabi

Physics-Guided Attention in a Lightweight TCN for Efficient WiFi CSI-Based Human Activity Recognition

arXiv:2606.01834v1 Announce Type: cross Abstract: Human Action Recognition (HAR) using WiFi Channel State Information (CSI) has gained increasing attention due to its non-contact, low-cost, and privac

Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling

arXiv:2505.17659v4 Announce Type: replace-cross Abstract: Safe and feasible trajectory planning is critical for real-world autonomous driving systems. However, existing learning-based planners rely he

POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems

arXiv:2606.02282v1 Announce Type: new Abstract: Orchestrating Large Language Models into Multi-Agent Systems (LLM-MAS) has unlocked remarkable reasoning capabilities, yet emergent failures and halluci

PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects

arXiv:2606.01016v1 Announce Type: cross Abstract: While End-to-End (E2E) Speech-Large Language Models (Speech-LLMs) are rapidly evolving, their evaluation methodologies remain limited to the era of si

Position Paper: Post-Solve Robustness in Decision Engines: Feasible Regions and Smoothness Under Perturbations

arXiv:2606.00002v1 Announce Type: new Abstract: Mixed-Integer Linear Programming (MILP) decision engines routinely output nominally optimal plans for high-stakes industrial systems. Yet deployment rar

Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates

arXiv:2606.00984v1 Announce Type: cross Abstract: We study linear contextual bandits under rare parameter updates: the learner may incorporate reward feedback into its parameter estimate only at a sma

Pramana: Fine-Tuning Large Language Models for Epistemic Reasoning through Navya-Nyaya

arXiv:2604.04937v1 Announce Type: cross Abstract: Large language models produce fluent text but struggle with systematic reasoning, often hallucinating confident but unfounded claims. When Apple resea

Pre-Deployment Robustness Stress Testing for CT Segmentation Systems Using Clinically Motivated Multi-Corruption Augmentation

arXiv:2606.00491v1 Announce Type: cross Abstract: Deep learning-based CT segmentation systems often achieve high accuracy on clean benchmark images, but their performance may degrade under heterogeneo

Predicted-Flow Control Barrier Functions for Real-Time Safe Optimal Control

model-releasesarxiv-cs-ro

arXiv:2606.00297v1 Announce Type: cross Abstract: Control barrier functions (CBFs) provide real-time safety guarantees through pointwise conditions on the state. However, synthesizing a valid CBF is d

Prep faster. Sell smarter. The sales plugin for Codex.

OpenAI announced a sales plugin for Codex that streamlines sales preparation and improves selling strategies through AI-assisted tools. The plugin leverages Codex's code generation capabilities to hel

model-releasesopenai--x

Princeton365: A Diverse Dataset with Accurate Camera Pose

arXiv:2506.09035v2 Announce Type: replace Abstract: We introduce Princeton365, a large-scale diverse dataset of 365 videos with accurate camera pose. Our dataset bridges the gap between accuracy and d

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

arXiv:2606.00152v1 Announce Type: cross Abstract: LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users. However, agents often acquire mor

Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design

arXiv:2606.00555v1 Announce Type: new Abstract: Structure-based drug design increasingly employs LLM agents to iteratively refine ligands against a target pocket, yet a viable ligand must satisfy two