model releases

OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning

arXiv:2505.22039v2 Announce Type: replace Abstract: While anomaly detection has made significant progress, generating detailed analyses that incorporate industrial knowledge remains a challenge. To ad

Model Releases

Online Handwriting Trajectory Reconstruction from Kinematic Sensors using Temporal Convolutional Network

DGX agent

arXiv:2607.26733v1 Announce Type: new Abstract: Handwriting with digital pens is a common way to facilitate human-computer interaction through the use of Online Handwriting (OH) trajectory reconstruct

model-releasesarxiv-cs-cv

30 Jul 2026

OpenAI says it is cutting the price of GPT-5.6 Luna by ~80% and the price of GPT-5.6 Terra by 20% after improving the efficiency of the systems that serve them (Ina Fried/Axios)

Ina Fried / Axios: OpenAI says it is cutting the price of GPT-5.6 Luna by ~80% and the price of GPT-5.6 Terra by 20% after improving the efficiency of the systems that serve them — OpenAI said Thursda

model-releasestechmeme

Our partners at @depthfirstlabs just released dfs-large1, a specialized model built for finding and validating real vulnerabilities in large…

model-releasesfireworks-ai--x

Our partners at @depthfirstlabs just released dfs-large1, a specialized model built for finding and validating real vulnerabilities in large enterprise codebases. We helped them to scale the training

P.A.I. — Sleek Native Desktop AI Overlayer for Local Ollama Models 🤖⚡

Greetings Community! 👋 I hope everyone is doing well! I'm Tauhid — Senior EEE student from a Bangladeshi University Today I'd like to share an open-source project I’ve been developing called P.A.I. (P

model-releasesr-ollama

Parameter-Free Dynamic Regret for Online Convex Optimization under Heavy-Tailed Noise

arXiv:2607.27073v1 Announce Type: new Abstract: We study online convex optimization (OCO) in non-stationary environments under heavy-tailed noise, where the stochastic gradient oracle admits only a fi

PatchDenoiser: Parameter-efficient multi-scale patch learning and fusion denoiser for Low-dose CT imaging

arXiv:2602.21987v3 Announce Type: replace Abstract: Low-dose CT images are essential for reducing radiation exposure in cancer screening, pediatric imaging, and longitudinal monitoring protocols, but

Persistence Spheres: a Bi-continuous Linear Representation of Measures for Partial Optimal Transport

arXiv:2603.15384v2 Announce Type: replace-cross Abstract: We improve and extend persistence spheres, introduced in~ite{pegoraro2025persistence}. Persistence spheres map an integrable measure mu on the

Phoneme- vs. Character-Level Targets and Selective State-Space Models for Intracortical Brain-to-Text

arXiv:2607.26751v1 Announce Type: new Abstract: State-of-the-art intracortical brain-to-text systems pair a neural-sequence phone decoder with an external language model. Two design axes remain undere

PolyAI launches new real-time voice conversation model to make AI-driven calls more human

model-releasessiliconangle

Voice assistant and conversational AI agent developer PolyAI Ltd. today announced the release of Dialog-RSN-1, a voice dialog artificial intelligence model capable of directly perceiving and respondin

Position: Evaluation Scores Are Perishable Knowledge Claims

arXiv:2607.26191v1 Announce Type: cross Abstract: Evaluation methodologies for language models increasingly combine multiple signals, from automated metrics and LLM-as-judge ratings to human assessmen

Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning

arXiv:2607.26358v1 Announce Type: new Abstract: Reinforcement learning (RL) fine-tuning is widely used in language model training to improve model performance on a target task while limiting drift fro

PowerAtlas: Towards Electricity-Computing Co-Scheduling for Power Systems

arXiv:2607.26710v1 Announce Type: new Abstract: The rapid growth of AI workloads is turning data centers into large-scale, volatile, yet spatiotemporally flexible grid loads, creating an urgent need f

Progressive Multimodal Alignment for Continual Instruction Tuning

arXiv:2607.26947v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) rely on a projector to align visual representations with the language embedding space, making it central to cro

Projective Graph Residualization: Variation-Allocation Frontiers for Control-Function IV

arXiv:2606.14636v2 Announce Type: replace Abstract: Control-function instrumental-variable estimators pass an estimated first-stage residual to an outcome model. The residual must retain the latent co

Prosody-driven Jailbreaks in Audio LLMs: A Controlled Study and Mechanistic Analysis

arXiv:2607.26541v1 Announce Type: cross Abstract: Audio-capable foundation models enable end-to-end spoken interaction, but they also introduce safety risks beyond transcript content. It remains uncle

Quick reminder of what's ok vs not ok with harnesses used for playing ARC-AGI-3: 1. Not okay: harnesses that were custom-made to solve the b…

model-releasesfrancois-chollet--x

Quick reminder of what's ok vs not ok with harnesses used for playing ARC-AGI-3: 1. Not okay: harnesses that were custom-made to solve the benchmark or that contain knowledge about the benchmark forma

Rad-JEPA 3D: Radiology Joint-Embedding Predictive Model for 3D Computed Tomography

arXiv:2607.26196v1 Announce Type: new Abstract: Self-supervised pretraining is central to 3D medical image analysis, where unlabeled CT volumes are abundant but expert annotations are scarce. Yet exis

RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning

arXiv:2607.26339v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems ground large language models (LLMs) in external corpora, but this reliance exposes them to corpus poisoning

ReCo: Reweighting GRPO Against Distributional Concentration

arXiv:2607.26862v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has become a standard reinforcement learning method for post-training language models. Recent work shows that

Reeling It In: Flexible Needle Pick Up via Thread Manipulation for Autonomous Suturing

arXiv:2607.26337v1 Announce Type: new Abstract: Suture-needle pickup is necessary for autonomous suturing, as a needle can be unexpectedly dropped or strategically released to adjust the grasping conf

Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting

arXiv:2607.26643v1 Announce Type: cross Abstract: Enabling large language model (LLM) agents to accumulate and reuse experience from past interactions remains a central challenge in real-world applica

Risk-Aware Motion Planning with Learned Trajectory Primitives and Probabilistic Safety Assessment

arXiv:2607.26802v1 Announce Type: new Abstract: This paper presents a radial basis function network (RBFN)-informed motion planning framework for safe and efficient urban autonomous driving. The propo

Route by Kinematics, Act by Observation: Kinematics-Supervised Expert Routing in MoE-Augmented VLA

arXiv:2607.26807v1 Announce Type: new Abstract: While MoE augments VLA via expert specialization, router suffers from ineffective expert routing owing to the kinematic heterogeneity of actions across

Same Evidence, Different Target: Decoding How Diagnostic Evidence Bears on Causal Questions from Language-Model States

arXiv:2607.26929v1 Announce Type: new Abstract: The same diagnostic result can support or challenge one causal claim yet fail to address another when the claims concern different populations, outcomes

SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context

arXiv:2607.27084v1 Announce Type: new Abstract: Scientific images are the core elements of presenting experimental conclusions, elaborating system architecture, and supporting comparative arguments in

SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response

arXiv:2607.26791v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces

Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models

arXiv:2607.26326v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance by integrating visual inputs with the rich priors of pretrained language models. How

Semantic-Aware Temporal Adaptation for UAV Anti-UAV Tracking

arXiv:2607.26511v1 Announce Type: new Abstract: UAV Anti-UAV tracking is an emerging low-altitude security task for localizing an adversarial UAV using the onboard camera of a moving observer UAV. It

SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning

arXiv:2607.26873v1 Announce Type: new Abstract: Test-time reinforcement learning (TTRL) enables language models to self-evolve at inference time without labeled feedback. Existing methods rely on answ

Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data

arXiv:2607.27056v1 Announce Type: cross Abstract: Personalized agents are increasingly applied to assist users across a wide range of tasks. Effective personalized assistance requires not only retriev

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models

arXiv:2607.26173v1 Announce Type: new Abstract: Alignment training, model organisms, and toy models are usually treated as separate research areas. But projects in all three frequently use supervised

Simultaneous Coverage and Efficiency Guarantee in Online Conformal Prediction

arXiv:2607.26577v1 Announce Type: new Abstract: Adaptive conformal inference (ACI) of Gibbs and Cand{es and its variants are the standard approach to online conformal prediction under distribution shi

SpatialQ: Understanding 3D Gaussian Splatting Scene Quality via Visual-based MLLM

arXiv:2607.26595v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as an effective representation for novel view synthesis and 3D scene reconstruction, creating an increasing dem

Structurally Separated Uncertainty in Supervised Latent Variable Models

arXiv:2602.11219v2 Announce Type: replace Abstract: Predictive uncertainty is commonly decomposed into epistemic and aleatoric components, but standard decompositions often produce strongly correlated

sure we lose money on every inference but we make it up in volume

model-releasesgary-marcus--x

sure we lose money on every inference but we make it up in volume We are committed to pushing the model frontier across cost efficiency, capability, and speed. Starting today, we are reducing prices f

Symphony of Bias: Exploring Gender Associations with Musical Instruments in Multimodal LLMs

arXiv:2607.26355v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in everyday life and widely used for information seeking, raising concerns about their potential

Temporally Centered SIGReg Improves Multi-Task LeWorldModel Learning: From Analysis to Method

arXiv:2607.26924v1 Announce Type: new Abstract: Recent work on LeWorldModel (LeWM) has shown that the Sketched Isotropic Gaussian Regularizer (SIGReg) enables stable end-to-end world-model learning fr

The Art of Not Forgetting A Local Learning Architecture for Continual Learning

arXiv:2607.26523v1 Announce Type: new Abstract: We introduce CMP (Cognitive Memory Primitive), a continual-learning architecture that repre?sents inputs as sparse relational codes, stores them in a tw

The Reliability of LLMs for Medical Diagnosis: An Examination of Consistency, Manipulation, and Contextual Awareness

arXiv:2503.10647v2 Announce Type: replace Abstract: This study evaluated the diagnostic reliability of two Large Language Models (LLMs), Google Gemini 2.0 Flash and OpenAI ChatGPT-4o, across three dim

Thinking Machines just released Inkling-Small: 276B total, 12B active. A faster Inkling that matches or beats its 975B big brother in many b…

model-releasessoumith-chintala--x

Thinking Machines just released Inkling-Small: 276B total, 12B active. A faster Inkling that matches or beats its 975B big brother in many benchmarks. To test its speed, we plugged it into HF's speech

This is absolutely wild... Anthropic reviewed their logs and found out that their own supposedly-sandboxed cyber evals had hacked three sepa…

model-releasessimon-willison--x

This is absolutely wild... Anthropic reviewed their logs and found out that their own supposedly-sandboxed cyber evals had hacked three separate companies back in April without them noticing! In a rev

Tight Generalization Bound for AdaBoost

arXiv:2607.26838v1 Announce Type: new Abstract: In this paper we show that the generalization error of AdaBoost is Thetaig(frac{dln(ngamma^{2}/d)}{ngamma^2}+frac{ln(1/elta)}{n}ig), where gamma is the

TiPToP: A Modular Open-Vocabulary Robot Manipulation System That Plans

arXiv:2603.09971v2 Announce Type: replace Abstract: We present TiPToP, a modular manipulation system that integrates pretrained foundation models with a GPU-accelerated Task and Motion Planner to solv

Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels

arXiv:2607.26121v1 Announce Type: new Abstract: Embodied intelligence integrates learned perception and decision making with real-time computation, control, and physical interaction. Because failures

ToxScreen: Detecting Whether an LLM Has Been Poisoned

arXiv:2607.26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that c

TPCD: Tone-Pressure Contrastive Decoding and the Label-Free Gating Bottleneck in Vision-Language Models

arXiv:2607.26536v1 Announce Type: new Abstract: High-pressure prompts can push vision-language models (VLMs) into unsupported commitments, such as reading illegible text, reporting indeterminate times

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation

arXiv:2510.00192v3 Announce Type: replace Abstract: Low-rank adaptation (LoRA) has become a widely used paradigm for parameter-efficient fine-tuning of large language models, yet its representational