All entries

Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models

arXiv:2606.31699v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated featu

local-aiarxiv-cs-ai

Look who stopped by today! Great time chatting with @dylan522p.

DGX agent

Dylan Patel, a notable tech industry figure, was visited by the post author (Sassine Ghazi), and they had a positive conversation together. The post appears to be a casual social media update sharing

hardwaredylan-patel--x

1 Jul 2026

LOPA: Enhancing Spoken Language Assessment via Latent Ordinal Prototype Alignment

model-releasesarxiv-cs-cl

arXiv:2606.31310v1 Announce Type: new Abstract: Fueled by increasing model scale and multimodal inputs, Multimodal Large Language Models (MLLMs) have emerged as a promising paradigm for Spoken Languag

Loved the chat between @trq212 @_catwu @simonw at AI Eng summit. My top 13 takeaways from their session -> 1. Engineers should become better…

Loved the chat between @trq212 @_catwu @simonw at AI Eng summit. My top 13 takeaways from their session -> 1. Engineers should become better at product/business sense. 2. Don't worry about major rewri

model-releasesswyx--x

Tutorials

Low-dimensional topology of deep neural networks

arXiv:2606.31856v1 Announce Type: new Abstract: We study layered models, including feedforward networks, ResNets, and transformers, by limiting each layer to a width of d = 3, i.e., R^3 as representat

tutorialsarxiv-cs-lg

LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents

arXiv:2606.30697v1 Announce Type: cross Abstract: Current operating systems expose interfaces optimized for human users but not for AI agents. Humans benefit from pixels, icons, windows, visual groupi

LUNA: Learning Universal 3D Human Animation Beyond Skinning

arXiv:2606.31981v1 Announce Type: cross Abstract: Creating photorealistic, animatable 3D human avatars from monocular images still largely depends on Linear Blend Skinning (LBS) and parametric body mo

local-aiarxiv-cs-ai

LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish

model-releasesarxiv-cs-cl

arXiv:2606.31947v1 Announce Type: new Abstract: State-of-the-art speech datasets predominantly focus on widely spoken languages, often overlooking low-resource languages such as Luxembourgish, which r

M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding

model-releasesarxiv-cs-cv

arXiv:2601.08758v4 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models by encouraging step-by-step intermediate reasoning, a

Machine Learning-based Feedback Linearization Control of Quadrotor Subject to Unmodeled Dynamics

arXiv:2606.31199v1 Announce Type: cross Abstract: The control of agile quadrotors in dynamic and uncertain environments remains an open area of investigation to this day, particularly when the complet

Make your first $1 → https://replit.com/partners/whop

Replit partnered with Whop to offer a program helping users earn their first dollar, likely through building and monetizing projects or applications on the Replit platform. The initiative promotes Rep

toolsreplit--x

Agents

Making AI search smarter

Search is how we find nearly everything on the web — creators, merchants, answers. AI is rewriting the rules, leaving creators caught between staying discoverable in an agentic era and getting paid fo

agentscloudflare-ai

Making Sense of Touch from the Child's View for Contrastive Learning

arXiv:2606.31943v1 Announce Type: new Abstract: Is the sense of touch a mechanism for human babies' learning of visual concepts? If so, can we quantify its importance, and to what extent do babies rel

making some last minute changes to my deck- see you tomorrow at AIE!

making some last minute changes to my deck- see you tomorrow at AIE! I'll be giving the the Day 2 opening keynote at AI Engineer World's Fair on July 1st at 9am. Hope to see you there, here's a quick

toolsthariq--x

Making your first dollar online just got so much easier with Replit's new Whop integration. 1) Build it on Replit 2) Integrate payments with…

Making your first dollar online just got so much easier with Replit's new Whop integration. 1) Build it on Replit 2) Integrate payments with Whop (no setup required) 3) Publish and promote Replit 🤝 Wh

toolsreplit--x

Mantis: Lightweight Foundation Model for Time Series Classification

arXiv:2502.15637v2 Announce Type: replace-cross Abstract: While foundation models have revolutionized various domains, their application to time series classification remains rather under-explored, wi

MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Elimination

arXiv:2606.31378v1 Announce Type: new Abstract: Neural networks are vulnerable to meticulously crafted adversarial examples, leading to high-confidence misclassifications in image classification tasks

Mapping the Artificial Intelligence Divide in Africa: Infrastructure, Accessibility and Capacity

arXiv:2606.30656v1 Announce Type: cross Abstract: Artificial Intelligence (AI) has the potential to be transformative for development, but Africa is currently facing a fragmented and challenging 'AI d

local-aiarxiv-cs-ai

Mean-Field Model for Two-Layer Neural Networks Trained with Consensus-Based Optimization

arXiv:2511.21466v3 Announce Type: replace Abstract: We study Consensus-Based Optimization (CBO) for two-layer neural network training. We compare the performance of CBO against Adam on two test cases

Measuring Judgment Quality in Natural-Language Explanations: Evidence from Forecasting Tournaments

arXiv:2606.30987v1 Announce Type: new Abstract: Decision-makers routinely rely on expert judgments accompanied by written explanations, yet explanation quality is difficult to measure at scale. Foreca

researcharxiv-cs-cl

Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts

arXiv:2606.23375v2 Announce Type: replace-cross Abstract: While the wider applicability of LLMs in the legal field is currently debated due to their reliability and the gravity of any errors, narrow u

MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments

arXiv:2606.31966v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have strong potential as embodied agents, but their ability to collaborate in visually grounded enviro

Medical Image Spatial Grounding with Semantic Sampling

model-releasesarxiv-cs-cv

arXiv:2603.14579v3 Announce Type: replace Abstract: Vision language models (VLMs) have shown significant promise in visual grounding for images as well as videos. In medical imaging research, VLMs rep

MediEncoder: Nonlinear Representation Learning for High-Dimensional Causal Mediation Analysis

arXiv:2606.30648v1 Announce Type: cross Abstract: Causal mediation analysis decomposes a treatment effect into indirect pathways through mediators and direct pathways not operating through them. Moder

Applications

MemLearner: Learning to Query Context memory for Video World Models

arXiv:2606.31734v1 Announce Type: new Abstract: Video World Models are interactive video generation models that predict future world states based on user actions and history video frames. A critical c

applicationsarxiv-cs-cv

Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation

arXiv:2606.31777v1 Announce Type: new Abstract: Autoregressive (AR) modeling has recently achieved remarkable progress in native 3D mesh generation, largely due to its natural ability to handle variab

Industry

Meta introduces a $20/month Meta One Premium tier for its glasses and limits its Conversation Focus feature to three hours of use per month for free users (Sean Hollister/The Verge)

Sean Hollister / The Verge: Meta introduces a 20/month Meta One Premium tier for its glasses and limits its Conversation Focus feature to three hours of use per month for free users — “All AI glasses

industrytechmeme

Industry

Meta names Chief Marketing Officer Alex Schultz as its first-ever chief data officer, to manage AI analytics across the company, and names Denise Moreno as CMO (Sara Fischer/Axios)

Sara Fischer / Axios: Meta names Chief Marketing Officer Alex Schultz as its first-ever chief data officer, to manage AI analytics across the company, and names Denise Moreno as CMO — Meta has named i

industrytechmeme

Industry

Meta shares jump 9% on reported plan to offer AI infrastructure services

Meta Platforms Inc. reportedly plans to rent its artificial intelligence infrastructure to other companies. Sources told Bloomberg and CNBC today that the Facebook parent will sell excess capacity not

industrysiliconangle

MetricHMSR:Metric Human Mesh and Scene Recovery from Monocular Images

arXiv:2506.09919v4 Announce Type: replace Abstract: We introduce MetricHMSR, a novel framework for recovering metric human meshes and 3D scenes from a single monocular image. Existing methods struggle

local-aiarxiv-cs-cv

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

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

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

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

Safety

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

Agents

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

Tutorials

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

Agents

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