All entries

Articulating then Matching: Zero-Shot Shape Matching for Uncurated Data

arXiv:2606.29167v1 Announce Type: new Abstract: Finding dense correspondences between 3D shapes is a fundamental yet unresolved challenge, especially in real-world environments. These environments pre

applicationsarxiv-cs-cv

Research

As a European, I don't understand how the sitting U.S. president—who has to pay $5 million to a woman he r@ped and defamed—can remain in off…

DGX agent

I can't provide a summary of this post without access to its actual content. The title appears to reference legal judgments involving a U.S. president, but I would need to verify the specific claims a

researchyann-lecun--x

30 Jun 2026

As open models get stronger, more workloads move into the competitive inference market. That pushes the real fight toward speed, cost, relia…

applicationstogether-ai--x

As open models get stronger, more workloads move into the competitive inference market. That pushes the real fight toward speed, cost, reliability, and control. Together AI is where open models become

Industry

As OpenAI and Anthropic prepare to go public, San Francisco tech workers making six figures say they cannot compete with the new AI elite and may have to leave (Emmy Martin/New York Times)

Emmy Martin / New York Times: As OpenAI and Anthropic prepare to go public, San Francisco tech workers making six figures say they cannot compete with the new AI elite and may have to leave — As OpenA

industrytechmeme

Assessing the Business Process Modeling Competences of Large Language Models

model-releasesarxiv-cs-ai

arXiv:2601.21787v2 Announce Type: replace-cross Abstract: The creation of Business Process Model and Notation (BPMN) models is a complex and time-consuming task requiring both domain knowledge and pro

Assortment Planning with Sponsored Products

arXiv:2402.06158v2 Announce Type: replace-cross Abstract: In the rapidly evolving landscape of retail, assortment planning plays a crucial role in determining the success of a business. With the rise

researcharxiv-cs-ai

ASTAD: Asymmetric Style Transfer for Synthetic-to-Real Adaptation in Autonomous Driving

arXiv:2606.29286v1 Announce Type: new Abstract: Synthetic data mitigates the data scarcity problem in autonomous driving perception. However, the synthetic-to-real gap leads to performance degradation

agentsarxiv-cs-cv

AsyncMDE: Real-Time Monocular Depth Estimation via Asynchronous Spatial Memory

arXiv:2603.10438v2 Announce Type: replace-cross Abstract: Foundation-model-based monocular depth estimation offers a viable alternative to active sensors for robot perception, yet its computational co

researcharxiv-cs-cv

Industry

'At this very moment China is giving its AI technology away. It's releasing open-weight AI models that are cheap, capable, and they're fast …

'At this very moment China is giving its AI technology away. It's releasing open-weight AI models that are cheap, capable, and they're fast becoming the world's default.' We can overcome this. @neil_c

industryclem-delangue--x

Atompack: A Storage and Distribution Layer for Read-Heavy Atomistic ML Training Datasets

arXiv:2606.29975v1 Announce Type: new Abstract: Atomistic machine learning datasets are increasingly used for training: large immutable snapshots are read repeatedly, shuffled across epochs, staged ac

researcharxiv-cs-lg

Attention Enhanced Entity Recommendation for Intelligent Monitoring in Cloud Systems

arXiv:2510.20640v2 Announce Type: replace Abstract: In this paper, we present DiRecGNN, an attention-enhanced entity recommendation framework for monitoring cloud services at Microsoft. We provide ins

applicationsarxiv-cs-lg

Attractor States Emerge in Multi-Turn LLM Conversations

model-releasesarxiv-cs-cl

arXiv:2606.30571v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in open-ended multi-agent settings, but the long-run dynamics of model--model interaction remain po

Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning

model-releasesarxiv-cs-ai

arXiv:2510.12957v4 Announce Type: replace-cross Abstract: We treat the internals of generative models as mechanistic objects rather than black boxes. We introduce extbf{Attribution Graphs} (AGs), whic

Audio-Visual Continual Test-Time Adaptation without Forgetting

arXiv:2602.18528v2 Announce Type: replace Abstract: Audio-visual continual test-time adaptation involves continually adapting a source audio-visual model at test-time, to unlabeled non-stationary doma

Auditing LLM-Governed Social Robots with Culture-Specific Moral Gradients

arXiv:2606.28345v1 Announce Type: cross Abstract: LLM-governed social robots increasingly decide who receives real-world assistance first. As prioritization norms vary across cultures by age, status,

applicationsarxiv-cs-ai

AURORA: Asymmetry and Update-Induced Rotation for Robust Hallucination Detection in Large Language Models

model-releasesarxiv-cs-cl

arXiv:2606.29545v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. However, their tendency

AUSLUN: A Fixed-Hover UAV--USV System for GNSS-Denied Maritime Search and Navigation

arXiv:2606.29875v1 Announce Type: new Abstract: Global navigation satellite system (GNSS) denial can prevent an unmanned surface vehicle (USV) from both finding a distant vessel and maintaining a glob

researcharxiv-cs-ro

AutoB2G: Agentic Simulation and Reinforcement Learning for Spatio-Temporal Grid-Interactive Building Control

arXiv:2603.26005v2 Announce Type: replace Abstract: Grid-interactive building control has emerged as a promising approach for improving demand-side flexibility in modern power systems. Realistic studi

Automated Quality Assessment of Geospatial Vector Data: A GeoAI Approach using Spatial Representation Learning

arXiv:2606.28390v1 Announce Type: cross Abstract: Geospatial vector data quality is a foundational research topic in GIS, yet classic rule-based quality assessment algorithms often struggle with diver

Automatic Extraction of Road Networks by using Teacher-Student Adaptive Structural Deep Belief Network and Its Application to Landslide Disaster

arXiv:2511.05567v2 Announce Type: replace-cross Abstract: An adaptive structural learning method of Restricted Boltzmann Machine (RBM) and Deep Belief Network (DBN) has been developed as one of promin

researcharxiv-cs-ai

Automating the Design of Embodied AgentArchitectures

arXiv:2606.30111v1 Announce Type: cross Abstract: Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules. This modularity exposes a large

AWS launches an internal organization for AI-focused forward-deployed engineers, backed by $1B in resources, following OpenAI and others in launching FDE teams (Russell Brandom/TechCrunch)

Russell Brandom / TechCrunch: AWS launches an internal organization for AI-focused forward-deployed engineers, backed by $1B in resources, following OpenAI and others in launching FDE teams — As compa

model-releasestechmeme

AWS launches forward-deployed engineering team to speed enterprise agentic AI adoption

model-releasessiliconangle

Amazon Web Services Inc. said today it’s rolling out a new dedicated organization to bring agentic artificial intelligence systems, built on the same technology, to customers by embedding engineers in

B3O: Scalable Boltzmann Batch Bayesian Optimization

arXiv:2606.30228v1 Announce Type: new Abstract: Modern engineering workflows increasingly rely on massive parallel simulation, driving the need for scalable, large-batch Bayesian Optimization (BO). Ex

researcharxiv-cs-lg

b9843

b9843 is a release of llama.cpp that reverts 'sched: reintroduce less synchronizations during split compute (#20793)' . The release includes pre-built binaries for multiple platforms including macOS,

b9844

llama.cpp is a C/C++ implementation for LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware. Release b9844 is an intermediate build of the llama.cpp project f

b9846

Release build b9846 is an intermediate build of llama.cpp, an open-source C/C++ project for LLM inference. The llama.cpp project is the main playground for developing new features for the ggml library

b9847

B9847 is a build release in the llama.cpp project, which is an open-source tool that enables LLM inference with minimal setup on a wide range of hardware . This specific build release likely contains

b9848

llama.cpp uses continuous build-tagged releases rather than traditional semantic versions. Release b9848 is a specific build from the ggml-org/llama.cpp project, which is an LLM inference implementati

b9849

b9849 is a build release from llama.cpp, which enables LLM inference in C/C++ . The release represents an intermediate build version of the llama.cpp library, a widely-used open-source project for run

b9850

Release b9850 is a version of llama.cpp, an open-source software library for large language model inference developed alongside the GGML tensor library. This release likely includes updates, bug fixes

b9851

B9851 is a release of llama.cpp, an LLM inference project written in C/C++ . The release represents a version update in the llama.cpp development timeline maintained on GitHub. This build tag typicall

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings

arXiv:2509.15001v3 Announce Type: replace-cross Abstract: Child-centered daylong recordings are essential for studying early language development, but existing speech models trained on clean adult dat

researcharxiv-cs-lg

BackTranslation2.0 -- A Linguistically Motivated Metric to Assess Sign Language Production

arXiv:2606.28673v1 Announce Type: new Abstract: Sign Languages (SLs) are the primary means of communication for millions of deaf individuals, yet existing evaluation metrics for generated SL remain si

agentsarxiv-cs-cv

Bandwidth Selection in Kernel Density Estimation for Model Calibration

arXiv:2606.29925v1 Announce Type: new Abstract: As deep learning models are increasingly deployed in high-stakes applications, providing well-calibrated uncertainty estimates has become as critical as

safetyarxiv-cs-lg

BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning

arXiv:2606.29184v1 Announce Type: new Abstract: While Low-rank adaptation (LoRA) enables highly efficient fine-tuning by constraining task-specific updates to fixed low-rank subspaces, this rigid desi

BayesEvolve: Explicit Belief States for Autonomous Scientific Discovery

arXiv:2606.30335v1 Announce Type: new Abstract: Autonomous scientific discovery systems increasingly use large language models (LLMs) to propose new hypotheses, but many such systems condition primari

Bayesian Best-Arm Identification with Abstention: A Polynomial-to-Exponential Phase Transition

arXiv:2606.29203v1 Announce Type: new Abstract: We study the Bayesian fixed-budget best-arm identification problem in which a learner can abstain from making a terminal recommendation. Subject to an a

Be Faithful When Response: Returning Fluent and Grounded Answers for Vision-Language Models Reinforcement Learning

arXiv:2606.29984v1 Announce Type: new Abstract: Reinforcement Learning (RL) is an important paradigm for improving the reasoning capabilities of Vision-Language Models (VLMs). However, directly applyi

safetyarxiv-cs-ai

BEACON: A Bayesian Optimization Inspired Strategy for Efficient Novelty Search

arXiv:2406.03616v5 Announce Type: replace-cross Abstract: Novelty search (NS) aims to uncover diverse system behaviors through simulation or experiment without requiring a pre-specified scalar objecti

Tutorials

Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning

arXiv:2606.30217v1 Announce Type: new Abstract: Large multimodal models have achieved strong reasoning on complex visual tasks, but their inference efficiency is often restricted by long chains of tho

tutorialsarxiv-cs-cl

Behavior Prompting Policy: Demonstrations as Prompts for Manipulation

arXiv:2606.30457v1 Announce Type: new Abstract: We study behavior prompting, a paradigm that enables robots to perform new tasks at inference time given a single human demonstration, which we call a b

safetyarxiv-cs-ro

Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering

arXiv:2606.29201v1 Announce Type: cross Abstract: Behavior-cloned policies often learn multiple behavior modes from demonstration datasets, including modes that are unsafe or otherwise undesired at de

safetyarxiv-cs-ai

Being at the launch of Cybercab two years ago was magic. A decade from now there will be millions of these things rolling around the world. …

Being at the launch of Cybercab two years ago was magic. A decade from now there will be millions of these things rolling around the world. The war over autonomous vehicles is on, as everyone in San F

safetyelon-musk--x

Benchmark AUC Is Not Deployable Reliability: A Cross-Dataset Audit of Off-the-Shelf Features for Surveillance Video Anomaly Detection

model-releasesarxiv-cs-cv

arXiv:2606.29506v1 Announce Type: new Abstract: Automated 'suspicious behavior' flagging is a headline promise of AI surveillance, and the field reports high frame-level ROC-AUC on standard video anom

Benchmarking Geospatial Foundation Models for Agriculture Applications

model-releasesarxiv-cs-cv

arXiv:2606.29664v1 Announce Type: new Abstract: Geospatial foundation models pretrained on satellite imagery promise broad generalization across remote sensing tasks and regions, but their geographic

Benchmarking LLM Agents on Meta-Analysis Articles from Nature Portfolio

arXiv:2606.17041v4 Announce Type: replace Abstract: Meta-analysis is a demanding form of evidence synthesis that combines literature retrieval, PI/ECO-guided study selection, and statistical aggregati

agentsarxiv-cs-cl

BERTomelo: Your Portuguese Encoder Best Friend

model-releasesarxiv-cs-ai

arXiv:2606.28999v1 Announce Type: cross Abstract: Encoders have become the state of the art for multiple NLP tasks, especially those requiring deep contextual understanding. While multilingual models