All entries

Mind the Residual Gap: Probabilistic Downscaling under Real-World Bias

model-releasesarxiv-cs-lg

arXiv:2606.30821v1 Announce Type: new Abstract: Probabilistic downscaling is the task of modeling the conditional distribution of high-resolution fields given coarse inputs, and is a central challenge

Minimizing Quantized Semantic Age of Information (QSAoI) in Foundation Model-Based Semantic Communications

DGX agent

arXiv:2606.31303v1 Announce Type: cross Abstract: The emerging techniques of semantic communications and edge computing in 6G networks necessitate a paradigm shift toward co-designed semantic-aware an

researcharxiv-cs-ai

1 Jul 2026

MIRTH: Mutual-Information Reasoning with Temporal Hubs for Vision-Language-Action Agents

arXiv:2606.31167v1 Announce Type: cross Abstract: VLA models have emerged as a powerful paradigm for transferring semantic knowledge from web-scale data to physical robotic control. However, current s

Tools

Missed our talk with @togethercompute on @MiniMax_AI sparse attention and kernel optimizations? Catch us tomorrow at 10:45am PT.

Together AI is promoting a rescheduled presentation about sparse attention mechanisms and kernel optimizations in collaboration with MiniMax AI, scheduled for 10:45am PT. The session focuses on techni

toolstogether-ai--x

Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning

arXiv:2606.31570v1 Announce Type: cross Abstract: Masked autoencoding has emerged as a prominent paradigm for self-supervised learning on 3D point clouds, achieving competitive performance across down

Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models

arXiv:2606.31397v1 Announce Type: cross Abstract: State-based fine-tuning has emerged as a compelling alternative to weight-based adaptation for transformers, updating lightweight controls into states

MNAR-k-means: A k-means Clustering for Data Missing Not at Random with Magnitude-Decaying Probability

arXiv:2606.31253v1 Announce Type: cross Abstract: The classical k-means clustering, based on distances computed from all data features, cannot be directly applied to incomplete data with missing value

safetyarxiv-cs-lg

Modal CEGAR-tableaux with RECAR and resolution-based SAT-shortcuts

arXiv:2606.31878v1 Announce Type: cross Abstract: We investigate two approaches for extending CEGAR-tableaux with SAT-shortcuts using a previously known approach called RECAR but also a totally new ap

Modality-Driven Search with Holistic Trace Judging for ARC-AGI-2

arXiv:2606.31543v1 Announce Type: new Abstract: Large language models can produce fluent, internally coherent reasoning traces for abstract reasoning tasks while still being confidently wrong - making

Model subsidies are ending. What do you do now?

Flat-rate AI plans are subsidizing agentic workloads. Learn why LLM inference costs are moving to metered pricing and how evals reveal cost per successful task. The post Model subsidies are ending. Wh

agentsarize-ai

Modeling Cell-Cycle-Aware Single-Cell Drug Perturbation Responses

arXiv:2606.30695v1 Announce Type: cross Abstract: Single-cell drug perturbation models should predict not only transcriptional response magnitude, but also whether a treatment alters the proliferative

Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues

model-releasesarxiv-cs-cl

arXiv:2606.31644v1 Announce Type: new Abstract: As large language models take on morally consequential roles in healthcare, legal, and hiring contexts, we need to examine whether their ethical behavio

More and more developers turning to glm5.2 as a daily driver for coding Here’s how to use it with deepagents code

tutorialsharrison-chase--x

More and more developers turning to glm5.2 as a daily driver for coding Here’s how to use it with deepagents code You can start building with GLM 5.2 in minutes: 1️⃣ Download dcode 2️⃣ Select your mod

Motion Planning in Compressed Representation Spaces

arXiv:2606.30940v1 Announce Type: cross Abstract: Deep learning methods have vastly expanded the capabilities of motion planning in robotics applications, as learning priors from large-scale data has

agentsarxiv-cs-ai

MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs

arXiv:2606.31383v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) typically employ resampling-based projectors to transform dense visual features into a compact token sequence f

MSNN-LINet: Cross-Modal Learning via Continuous Linear Integration

arXiv:2606.31135v1 Announce Type: new Abstract: We present LINet (Linear Integration Network), a Multi-Stream Neural Network (MSNN) for RGB-D scene classification. Current multi-modal architectures tr

Multi-Channel Uncertainty-Weighted Score Matching for Conditional Diffusion in Medical UDA

arXiv:2509.22476v2 Announce Type: replace Abstract: Robust medical image segmentation across modalities remains challenging due to severe domain shifts and the lack of target-domain labels. While diff

Multi-GPU kernels are the real test for coding models. Today at @aiDotEngineer, @simran_s_arora shared ParallelKernelBench, an open-source b…

model-releasestogether-ai--x

Multi-GPU kernels are the real test for coding models. Today at @aiDotEngineer, @simran_s_arora shared ParallelKernelBench, an open-source benchmark for evaluating whether LLMs can write fast CUDA ker

Multi-Robot Coordination for Planning under Context Uncertainty

arXiv:2603.13748v3 Announce Type: replace Abstract: Real-world robots often operate in settings where objective priorities depend on the underlying context of operation. When the underlying context is

tutorialsarxiv-cs-ro

Tools

Multi-token Residual Prediction

Multi-token Residual Prediction is a technique for improving language model inference efficiency by predicting multiple tokens simultaneously rather than one at a time, reducing latency and computatio

toolsmodal-blog

Multilingual Polarization Detection Using Transformer-Based Models with Class Weighting and Threshold Tuning

arXiv:2606.30857v1 Announce Type: new Abstract: This paper describes our submission to SemEval-2026 Task 9 on detecting multilingual, multicultural, and multievent online polarization. We address all

researcharxiv-cs-cl

Multimodal Benchmark for Safety Assessment in Industrial Inspection Scenarios

model-releasesarxiv-cs-cv

arXiv:2601.21173v2 Announce Type: replace-cross Abstract: With the rapid development of industrial intelligence and unmanned inspection, reliable perception and safety assessment for AI systems in com

Multiple Testing of Linear Forms for Noisy Matrix Completion

arXiv:2312.00305v3 Announce Type: replace-cross Abstract: Many important tasks of large-scale recommender systems can be naturally cast as testing multiple linear forms for noisy matrix completion. Th

safetyarxiv-cs-lg

Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining

model-releasesarxiv-cs-lg

arXiv:2509.10406v4 Announce Type: replace Abstract: Pretraining transformers on long sequences (entire code repositories, collections of related documents) is bottlenecked by quadratic attention costs

Multisensory Continual Learning: Adapting Pretrained Visuomotor Policies to Force

arXiv:2606.30988v1 Announce Type: new Abstract: Robot manipulation often relies on sensory feedback beyond vision, particularly in contact-rich settings where force, tactile, or audio signals reveal i

safetyarxiv-cs-ro

Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again

arXiv:2606.30995v1 Announce Type: new Abstract: Recent work has shown that well-optimized individual decision trees can match complex black box models in some settings, primarily in noisy domains. For

researcharxiv-cs-lg

MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning

arXiv:2606.31073v1 Announce Type: new Abstract: Large language models (LLMs) provide a promising interface for high-level robotic task planning, but their use in multi-UAV collaboration remains diffic

Applications

MuSViT: A Foundation Vision Model for Sheet Music Representation

arXiv:2606.31811v1 Announce Type: new Abstract: Foundation models have transformed vision and language processing by providing rich, reusable representations that transfer across diverse tasks. Sheet

applicationsarxiv-cs-cv

MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes

arXiv:2606.31533v1 Announce Type: new Abstract: Identifying and grounding precise geometric entities, such as edges, planar regions, and curved surfaces within 3D objects, is foundational to computer-

MVP-Nav: Multi-layer Value Map Planner Navigator

arXiv:2606.31919v1 Announce Type: cross Abstract: Zero-shot Object Goal Navigation (ZSON) with RGB-only perception poses a fundamental challenge for embodied agents, as the absence of explicit depth i

tutorialsarxiv-cs-ai

My prediction: the excitement for Fable 5 will wear off really fast. Reposting this to help those who will be extremely disappointed after t…

My prediction: the excitement for Fable 5 will wear off really fast. Reposting this to help those who will be extremely disappointed after they play with Fable 5 and run out of tokens or can't do much

model-releasesdair-ai--x

Local Ai

Nano Banana 2 Lite: Image Edit https://links.comfy.org/4eSb7GB

Nano Banana 2 Lite is an image editing tool or model available through ComfyUI, a node-based interface for AI image generation and manipulation. This resource likely provides a lightweight version of

local-aicomfyui--x

Local Ai

Nano Banana 2 Lite is now in Comfy. The fastest, cheapest model in the Nano Banana family. → 4-second image gen → $0.034 per 1K images If yo…

Nano Banana 2 Lite is now in Comfy. The fastest, cheapest model in the Nano Banana family. → 4-second image gen → $0.034 per 1K images If your pipeline runs on iteration volume, this changes the game.

local-aicomfyui--x

Local Ai

Nano Banana 2 Lite: Text To Image https://links.comfy.org/3RdZ92j

Nano Banana 2 Lite is a text-to-image model optimized for efficiency and speed, likely designed for use within the ComfyUI node-based interface. This lightweight version of the model enables users to

local-aicomfyui--x

Industry

NASA chief praises progress Blue Origin is making after launch failure

NASA Administrator Jared Isaacman acknowledged the May 28, 2026 New Glenn rocket explosion at Cape Canaveral, noting that spaceflight development is extraordinarily difficult and pledging NASA's suppo

industryars-technica

Industry

NASA inspector general suggests Boeing's Starliner will now be a decade late

A NASA Office of Inspector General audit released June 30 found that Boeing's Starliner capsule will not achieve human-rating certification until 2027 at the earliest , representing a significant dela

industryars-technica

Nazrin: An Atomic Neural Proof Automation Tactic in Lean 4

arXiv:2602.18767v3 Announce Type: replace-cross Abstract: In Machine-Assisted Theorem Proving, a theorem proving agent searches for a sequence of expressions and tactics that can prove a statement in

agentsarxiv-cs-lg

Nemotron 3 Ultra is taking off on Together AI 🚀 In just days, it's climbed to 35B tokens/day on @OpenRouter. That's the community voting wi…

model-releasestogether-ai--x

Nemotron 3 Ultra is taking off on Together AI 🚀 In just days, it's climbed to 35B tokens/day on @OpenRouter. That's the community voting with their tokens for open models that are fast, efficient, and

Neuro-Bayesian-Symbolic Residual Attention Shallow Network: Explainable Deep Learning for Cybersecurity Risk Assessment

arXiv:2606.30953v1 Announce Type: new Abstract: We introduce the Neuro-Bayesian-Symbolic Residual Attention Shallow Network (NBS-RASN), a hybrid neural architecture for explainable cybersecurity risk

Neurologyca launches research labs to help frontier AI models understand people

model-releasessiliconangle

Neurologyca, a company working on human-centric artificial intelligence, announced the launch of a research division on Tuesday dedicated to advancing AI models’ ability to understand and adapt to peo

New IDC study: The business value of Mandiant Consulting

Security leaders are now expected to protect business growth and clearly articulate security value to their board of directors, in addition to managing risk. While translating technical defense into m

tutorialsgoogle-cloud-ai

NEW paper worth reading. (bookmark it) Autonomous research systems usually prove themselves on cherry-picked wins, human-framed topics, or a…

NEW paper worth reading. (bookmark it) Autonomous research systems usually prove themselves on cherry-picked wins, human-framed topics, or a handful of preset tasks. FARS runs the full loop at scale i

agentsdair-ai--x

No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation

arXiv:2606.30937v1 Announce Type: new Abstract: LiDAR semantic segmentation often degrades under real-world deployment due to evolving sensing conditions, while collecting new annotations for retraini

safetyarxiv-cs-cv

No country wins a race to superintelligence. An AI vastly smarter than us wouldn't be a weapon we control, we'd be handing control over to i…

No country wins a race to superintelligence. An AI vastly smarter than us wouldn't be a weapon we control, we'd be handing control over to it. ControlAI's US Director Connor Leahy (@NPCollapse) on why

safetyconnor-leahy--x

No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs

model-releasesarxiv-cs-cv

arXiv:2606.31933v1 Announce Type: new Abstract: We introduce VidPair-Halluc, a new benchmark for evaluating video hallucination in large video models (LVMs) under rigorous and controlled conditions. U

No Prompt, No Leaks: A Robust Generative Steganography Framework via Prompt-Free Diffusion

arXiv:2606.31427v1 Announce Type: new Abstract: Generative image steganography synthesizes stego images directly from secret information to achieve inherent security advantages. Latent Diffusion Model

Nonlinearity-Aware LoRA: Structured Gate Adaptation under Low-Rank Constraints

model-releasesarxiv-cs-lg

arXiv:2606.31717v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) is commonly viewed as an update-space approximation to full fine-tuning, yet this view is incomplete for self-gated Transform

Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning

arXiv:2510.17917v2 Announce Type: replace-cross Abstract: Data unlearning aims to remove the influence of specific training samples from a trained model. In fine-tuning methods, data unlearning relies