model releases

LLM-as-a-Verifier: A General-Purpose Verification Framework

arXiv:2607.05391v1 Announce Type: new Abstract: Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we id

Model Releases

LLM-Based Test Oracles: Source-of-Authority Taxonomy -- A Systematic Literature Review

DGX agent

arXiv:2607.05031v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to produce test oracles, the part of a test that decides whether observed behavior is correct. Yet

model-releasesarxiv-cs-ai

7 Jul 2026

LLM-Driven CI-CD Workflow Intelligence for Cyber Systems Engineering

arXiv:2607.04579v1 Announce Type: cross Abstract: CI/CD workflows have become executable operational policy: they decide what gets built, tested, released, and deployed, and they mediate how maintaine

LLMs Encode Harmfulness and Refusal Separately

arXiv:2507.11878v5 Announce Type: replace Abstract: LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refu

Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing

arXiv:2607.05114v1 Announce Type: cross Abstract: Large Language Models (LLMs) and high-dimensional perception networks increasingly rely on parameter-efficient fine-tuning (PEFT) to adapt to diverse

Longitudinal-Motion-Aware Lateral Control for Autonomous Vehicles: A Robust Nonlinear Control Framework

model-releasesarxiv-cs-ro

arXiv:2607.02924v1 Announce Type: new Abstract: As autonomous vehicles (AVs) operate in increasingly dynamic traffic conditions, lateral control must be performed while longitudinal speed and accelera

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL).…

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. M

model-releasesdair-ai--x

LuxSQA: Ask Me in Luxembourgish with TTS-Augmented Spoken Question Answering

arXiv:2607.02763v1 Announce Type: new Abstract: Spoken Question Answering (SQA) remains largely focused on high-resource languages and carefully recorded speech, limiting the reach of speech-LLM metho

MAI-1 has no independent benchmarks yet, but the ones they released suggest it is worse than Sonnet 4.6. Not sure it is going to be great as…

model-releasesethan-mollick--x

MAI-1 has no independent benchmarks yet, but the ones they released suggest it is worse than Sonnet 4.6. Not sure it is going to be great as a Copilot at Excel and Outlook, especially as there are alr

MARLIN: De Novo Molecular Structure Elucidation from Tandem Mass Spectra without a Ground-Truth Formula

arXiv:2607.04774v1 Announce Type: new Abstract: Untargeted tandem mass spectrometry (MS/MS) detects thousands of small molecules per biological sample, yet most go unidentified because they are absent

Mask2Real-WM: Segmentation Masks as a Sim-to-Real Bridge for Controllable Dexterous World Models

arXiv:2607.04546v1 Announce Type: cross Abstract: Action-conditioned world models allow robots to predict the future consequences of candidate actions without additional physical interaction, supporti

MatPhaseBench: A Semantics-Guided Benchmark for Materials Phase Diagrams Understanding

arXiv:2607.02934v1 Announce Type: cross Abstract: Materials phase diagrams are a core knowledge representation in materials science, encoding temperature,composition, phase stability, and phase transf

Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents

arXiv:2607.04528v1 Announce Type: new Abstract: Software-agent benchmarks usually report whether an agent solves a task, but the agent reaches that outcome through a harness that controls what it sees

Mechanism-level routing failure in LLMs over Lean-verified algebraic structures

arXiv:2607.04534v1 Announce Type: new Abstract: We present an empirical study of structural routing failure in large language models (LLMs) over a formally verified algebraic corpus. The task requires

MedCalc-Pro: Solving Complex Medical Calculations with LLM Agents

arXiv:2607.02879v1 Announce Type: new Abstract: Current benchmarks for evaluating large language models (LLMs) in medical calculation are largely based on simplified settings, where each patient case

Medi-Gemma: A Hybrid Clinical Decision Support System Integrating Deterministic EMR Analytics and Retrieval-Augmented Generation

arXiv:2607.04907v1 Announce Type: new Abstract: Deploying Large Language Models (LLMs) in high-stakes clinical settings remains limited by structural hallucinations, weak deterministic reasoning over

Memory chipmaker SK hynix seeks to raise $28B through US IPO

model-releasessiliconangle

SK hynix Inc., the South Korean firm that rivals Samsung Electronics Co. Ltd. and Micron Technology Inc. as one of the world’s top memory chipmakers, said today it will sell almost 17.8 million shares

Memory-Efficient FastText: A Comprehensive Approach Using Double-Array Trie Structures and Mark-Compact Memory Management

arXiv:2506.01254v2 Announce Type: replace Abstract: FastText remains a practical choice for industrial word representation because it can synthesize vectors for out-of-vocabulary words from character

MemPose: Category-level Object Pose Estimation with Memory

arXiv:2607.04930v1 Announce Type: cross Abstract: In the pursuit of robust and generalizable category-level object pose estimation, most existing methods adopt parametric formulations that learn effec

Metallic Ultrasound Waveguides as a Distributed Tactile Sensing Platform for Contact Localization, Force Estimation, and Material Class Discrimination

model-releasesarxiv-cs-ro

arXiv:2607.02827v1 Announce Type: new Abstract: Tactile sensing is central to how robotic systems interact with the real world, yet current solutions face a tradeoff between sensing area and system co

// MetaSkill-Evolve // Great paper on self-improving agents. Most self-improving agents rewrite what the agent does and leave how it improve…

// MetaSkill-Evolve // Great paper on self-improving agents. Most self-improving agents rewrite what the agent does and leave how it improves frozen and hand-authored. That improvement procedure never

model-releasesdair-ai--x

Metronome: Bound the Cache, Keep the Beat for Real-Time Interaction Model Serving

arXiv:2607.02640v1 Announce Type: cross Abstract: Real-time interaction models -- Moshi, MiniCPM-o, Qwen-Omni -- turn serving into a periodic real-time task: on every frame a session ingests streaming

MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training

arXiv:2602.06285v2 Announce Type: replace Abstract: Recent research in geospatial machine learning has demonstrated that models pretrained with self-supervised learning on Earth observation data can p

Modular Foundation Models for Time-Series Perception in Digital Twins

arXiv:2607.03585v1 Announce Type: new Abstract: Engineering Digital Twins and Prognostics and Health Management (PHM) systems rely on robust perception modules to extract actionable information from h

Moonstone: A Multimodal Foundation Model and Benchmark for Lunar Remote Sensing

arXiv:2607.03644v1 Announce Type: cross Abstract: Decades of orbital missions have produced multi-modal remote sensing data for the Moon, spanning optical imagery, spectroscopy, thermal emission, rada

MORE: A Multilingual Document Parsing Benchmark and Evaluation

arXiv:2607.02956v1 Announce Type: cross Abstract: Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machi

MTEB-PT: A Text Embedding Benchmark for Brazilian Portuguese

arXiv:2607.04581v1 Announce Type: new Abstract: Text embeddings for Portuguese have no dedicated benchmark: evaluation rests on translated corpora such as English MS MARCO or on thin multilingual cove

Multi-Agent Reinforcement Learning for V2X Resource Allocation: Disentangling MARL Challenges Through Benchmarking

arXiv:2603.06607v2 Announce Type: replace-cross Abstract: Radio resource allocation (RRA) is a critical function in cellular vehicle-to-everything (C-V2X) networks, where vehicles must share limited w

Multiplayer Interactive World Models with Representation Autoencoders

arXiv:2607.05352v1 Announce Type: cross Abstract: We introduce the first multiplayer world model for highly dynamic environments governed by complex physical interactions. Whereas single-player world

MUSON: A Reasoning-oriented Multimodal Dataset for Socially Compliant Navigation in Urban Environments

arXiv:2512.22867v2 Announce Type: replace Abstract: Socially compliant navigation requires structured reasoning about dynamic pedestrians and physical constraints to ensure safe and interpretable deci

Natural Language Camera Movement Understanding

arXiv:2607.03043v1 Announce Type: new Abstract: Understanding camera movement in natural language is critical for training and evaluating video generation models, among other applications. However, we

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs

arXiv:2607.04371v1 Announce Type: new Abstract: We present Nemotron-Labs-3-Puzzle-75B-A9B, a compressed variant of Nemotron-3-Super optimized for interactive deployment. We designed the model to maxim

NEST: Nascent Encoded Steganographic Thoughts

arXiv:2602.14095v2 Announce Type: replace Abstract: Monitoring chain-of-thought (CoT) reasoning is a foundational safety technique for large language model agents; however, this oversight is compromis

Neural-Network Inverse Design of SRF Cavities and Transmons for Bosonic Quantum Computation

arXiv:2607.02289v1 Announce Type: cross Abstract: Three-dimensional superconducting radio-frequency (SRF) cavities provide exceptionally long-lived electromagnetic modes and, when coupled to nonlinear

NEW AI paper worth bookmarking. This is something I called early, and this paper confirms it: verification has emerged as a new important sc…

NEW AI paper worth bookmarking. This is something I called early, and this paper confirms it: verification has emerged as a new important scaling axis. Here is the simple explainer and what this paper

model-releasesdair-ai--x

NKI-Agent: Domain-Specific Fine-Tuning and Agentic Tool Use for Neuron Kernel Generation

arXiv:2607.04395v1 Announce Type: new Abstract: Recent agentic approaches to LLM-based kernel generation have achieved impressive results on CUDA. For emerging AI accelerators such as AWS Trainium and

No Reliable Evidence of Self-Reported Sentience in Small Large Language Models

arXiv:2601.15334v2 Announce Type: replace-cross Abstract: Whether language models possess sentience has no empirical answer. But whether they believe themselves to be sentient can, in principle, be te

Non-Convex Sparse Reinforcement Learning via Non-Monotone Inclusions

arXiv:2607.04990v1 Announce Type: new Abstract: This work delivers two key contributions: one to efficient feature selection in reinforcement learning (RL), the other to the theory of non-monotone inc

Nonparametric Control Koopman Operators

arXiv:2405.07312v5 Announce Type: replace-cross Abstract: This paper presents a novel Koopman composition operator representation framework for control systems in reproducing kernel Hilbert spaces (RK

NormWorlds-CF: Solver-Verified Counterfactual Normative Reasoning with Metamorphic-Relation GRPO

arXiv:2607.03957v1 Announce Type: cross Abstract: Language models can reach the right normative verdict for the wrong reason. We introduce NormWorlds-CF, a solver-verified environment for counterfactu

Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale

arXiv:2607.02714v1 Announce Type: cross Abstract: There is no doubt that safety alignment is an essential step in LLM training. However, conceptually it does not distinguish between various domains an

NRT-Bench: Benchmarking Multi-Turn Red-Teaming of LLM Operator Agents in Safety-Critical Control Rooms

arXiv:2606.20408v3 Announce Type: replace-cross Abstract: Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under

nvidia ai just handed dgx spark owners a real gift. nemotron labs 3 puzzle 75b a9b nvfp4 is basically built for this box. 75b total, 9.3b ac…

model-releasesclem-delangue--x

nvidia ai just handed dgx spark owners a real gift. nemotron labs 3 puzzle 75b a9b nvfp4 is basically built for this box. 75b total, 9.3b active, nvfp4, mamba plus moe, 256k context in the config, and

Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse

arXiv:2607.04537v1 Announce Type: cross Abstract: Code language models are now trusted collaborators in production workflows for debugging, refactoring, and iterative repair, and every benchmark that

Octax: Accelerated CHIP-8 Arcade Environments for Reinforcement Learning in JAX

arXiv:2510.01764v3 Announce Type: replace Abstract: Reinforcement learning (RL) research requires diverse, challenging environments that are both tractable and scalable. While modern video games may o

OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models

arXiv:2607.03050v1 Announce Type: cross Abstract: Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate larg

OmniLayout: A Schematic-Coupled Multimodal Benchmark for Constraint-Aware Geometric Reasoning in PCB Layout

arXiv:2607.03261v1 Announce Type: new Abstract: Recent large language models (LLMs) have demonstrated remarkable progress in 3D spatial reasoning, spatial grounding, and fine-grained geometric underst

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

arXiv:2607.04033v1 Announce Type: cross Abstract: Optimizer selection for large-scale model training has become a system-level design decision constrained jointly by compute, memory, tuning budget, an